EDA Deepfake experiment All videos
Dilrukshi
2023-06-09
##Deepfake EDA with All type of videos - Pilitical and Entertainment
#Clean Political data frame to explore the effect of measured other variables
data_raw_pol <- read_csv("C:/Users/Dell/OneDrive/Documents/CREST Postdoc/Deepfakes Experiment/Analysis/Study_1aPolitical/DeepF_Study1a_Politics.csv")## New names:
## Rows: 130 Columns: 261
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (261): StartDate, EndDate, Status, Progress, Duration (in seconds), Fini...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `1P_R_IMPT` -> `1P_R_IMPT...27`
## • `1P_R_INTEREST` -> `1P_R_INTEREST...28`
## • `1P_R_FAMILIAR` -> `1P_R_FAMILIAR...29`
## • `1P_R_NOVEL` -> `1P_R_NOVEL...30`
## • `1P_R_SHARE` -> `1P_R_SHARE...31`
## • `1P_R_SHARE_REASONS` -> `1P_R_SHARE_REASONS...32`
## • `1P_R_SHARE_OTHER` -> `1P_R_SHARE_OTHER...33`
## • `1P_R_DNSHARE_REASONS` -> `1P_R_DNSHARE_REASONS...34`
## • `1P_R_DNSHARE_OTHER` -> `1P_R_DNSHARE_OTHER...35`
## • `2P_DF_IMPT` -> `2P_DF_IMPT...37`
## • `2P_DF_INTEREST` -> `2P_DF_INTEREST...38`
## • `2P_DF_FAMILIAR` -> `2P_DF_FAMILIAR...39`
## • `2P_DF_NOVEL` -> `2P_DF_NOVEL...40`
## • `2P_DF_SHARE` -> `2P_DF_SHARE...41`
## • `2P_DF_SHARE_REASONS` -> `2P_DF_SHARE_REASONS...42`
## • `2P_DF_SHARE_OTHER` -> `2P_DF_SHARE_OTHER...43`
## • `2P_DF_DNSHARE_REASON` -> `2P_DF_DNSHARE_REASON...44`
## • `2P_DF_DNSHARE_OTHER` -> `2P_DF_DNSHARE_OTHER...45`
## • `4P_DF_IMPT` -> `4P_DF_IMPT...47`
## • `4P_DF_INTEREST` -> `4P_DF_INTEREST...48`
## • `4P_DF_FAMILIAR` -> `4P_DF_FAMILIAR...49`
## • `4P_DF_NOVEL` -> `4P_DF_NOVEL...50`
## • `4P_DF_SHARE` -> `4P_DF_SHARE...51`
## • `4P_DF_SHARE_REASONS` -> `4P_DF_SHARE_REASONS...52`
## • `4P_DF_SHARE_OTHER` -> `4P_DF_SHARE_OTHER...53`
## • `4P_DF_DNSHARE_REASON` -> `4P_DF_DNSHARE_REASON...54`
## • `4P_DF_DNSHARE_OTHER` -> `4P_DF_DNSHARE_OTHER...55`
## • `5P_R_IMPT` -> `5P_R_IMPT...57`
## • `5P_R_INTEREST` -> `5P_R_INTEREST...58`
## • `5P_R_FAMILIAR` -> `5P_R_FAMILIAR...59`
## • `5P_R_NOVEL` -> `5P_R_NOVEL...60`
## • `5P_R_SHARE` -> `5P_R_SHARE...61`
## • `5P_R_SHARE_REASONS` -> `5P_R_SHARE_REASONS...62`
## • `5P_R_SHARE_OTHER` -> `5P_R_SHARE_OTHER...63`
## • `5P_R_DNSHARE_REASONS` -> `5P_R_DNSHARE_REASONS...64`
## • `5P_R_DNSHARE_OTHER` -> `5P_R_DNSHARE_OTHER...65`
## • `6P_DF_IMPT` -> `6P_DF_IMPT...67`
## • `6P_DF_INTEREST` -> `6P_DF_INTEREST...68`
## • `6P_DF_FAMILIAR` -> `6P_DF_FAMILIAR...69`
## • `6P_DF_NOVEL` -> `6P_DF_NOVEL...70`
## • `6P_DF_SHARE` -> `6P_DF_SHARE...71`
## • `6P_DF_SHARE_REASONS` -> `6P_DF_SHARE_REASONS...72`
## • `6P_DF_SHARE_OTHER` -> `6P_DF_SHARE_OTHER...73`
## • `6P_DF_DNSHARE_REASON` -> `6P_DF_DNSHARE_REASON...74`
## • `6P_DF_DNSHARE_OTHER` -> `6P_DF_DNSHARE_OTHER...75`
## • `7P_R_IMPT` -> `7P_R_IMPT...77`
## • `7P_R_INTEREST` -> `7P_R_INTEREST...78`
## • `7P_R_FAMILIAR` -> `7P_R_FAMILIAR...79`
## • `7P_R_NOVEL` -> `7P_R_NOVEL...80`
## • `7P_R_SHARE` -> `7P_R_SHARE...81`
## • `7P_R_SHARE_REASONS` -> `7P_R_SHARE_REASONS...82`
## • `7P_R_SHARE_OTHER` -> `7P_R_SHARE_OTHER...83`
## • `7P_R_DNSHARE_REASONS` -> `7P_R_DNSHARE_REASONS...84`
## • `7P_R_DNSHARE_OTHER` -> `7P_R_DNSHARE_OTHER...85`
## • `13P_DF_IMPT` -> `13P_DF_IMPT...87`
## • `13P_DF_INTEREST` -> `13P_DF_INTEREST...88`
## • `13P_DF_FAMILIAR` -> `13P_DF_FAMILIAR...89`
## • `13P_DF_NOVEL` -> `13P_DF_NOVEL...90`
## • `13P_DF_SHARE` -> `13P_DF_SHARE...91`
## • `13P_DF_SHARE_REASONS` -> `13P_DF_SHARE_REASONS...92`
## • `13P_DF_SHARE_OTHER` -> `13P_DF_SHARE_OTHER...93`
## • `13P_DF_DNSHARE_REASO` -> `13P_DF_DNSHARE_REASO...94`
## • `13P_DF_DNSHARE_OTHER` -> `13P_DF_DNSHARE_OTHER...95`
## • `15P_DF_IMPT` -> `15P_DF_IMPT...97`
## • `15P_DF_INTEREST` -> `15P_DF_INTEREST...98`
## • `15P_DF_FAMILIAR` -> `15P_DF_FAMILIAR...99`
## • `15P_DF_NOVEL` -> `15P_DF_NOVEL...100`
## • `15P_DF_SHARE` -> `15P_DF_SHARE...101`
## • `15P_DF_SHARE_REASONS` -> `15P_DF_SHARE_REASONS...102`
## • `15P_DF_SHARE_OTHER` -> `15P_DF_SHARE_OTHER...103`
## • `15P_DF_DNSHARE_REASO` -> `15P_DF_DNSHARE_REASO...104`
## • `15P_DF_DNSHARE_OTHER` -> `15P_DF_DNSHARE_OTHER...105`
## • `17P_R_IMPT` -> `17P_R_IMPT...107`
## • `17P_R_INTEREST` -> `17P_R_INTEREST...108`
## • `17P_R_FAMILIAR` -> `17P_R_FAMILIAR...109`
## • `17P_R_NOVEL` -> `17P_R_NOVEL...110`
## • `17P_R_SHARE` -> `17P_R_SHARE...111`
## • `17P_R_SHARE_REASONS` -> `17P_R_SHARE_REASONS...112`
## • `17P_R_SHARE_OTHER` -> `17P_R_SHARE_OTHER...113`
## • `17P_R_DNSHARE_REASON` -> `17P_R_DNSHARE_REASON...114`
## • `17P_R_DNSHARE_OTHER` -> `17P_R_DNSHARE_OTHER...115`
## • `19P_DF_IMPT` -> `19P_DF_IMPT...117`
## • `19P_DF_INTEREST` -> `19P_DF_INTEREST...118`
## • `19P_DF_FAMILIAR` -> `19P_DF_FAMILIAR...119`
## • `19P_DF_NOVEL` -> `19P_DF_NOVEL...120`
## • `19P_DF_SHARE` -> `19P_DF_SHARE...121`
## • `19P_DF_SHARE_REASONS` -> `19P_DF_SHARE_REASONS...122`
## • `19P_DF_SHARE_OTHER` -> `19P_DF_SHARE_OTHER...123`
## • `19P_DF_DNSHARE_REASO` -> `19P_DF_DNSHARE_REASO...124`
## • `19P_DF_DNSHARE_OTHER` -> `19P_DF_DNSHARE_OTHER...125`
## • `21P_R_IMPT` -> `21P_R_IMPT...127`
## • `21P_R_INTEREST` -> `21P_R_INTEREST...128`
## • `21P_R_FAMILIAR` -> `21P_R_FAMILIAR...129`
## • `21P_R_NOVEL` -> `21P_R_NOVEL...130`
## • `21P_R_SHARE` -> `21P_R_SHARE...131`
## • `21P_R_SHARE_REASONS` -> `21P_R_SHARE_REASONS...132`
## • `21P_R_SHARE_OTHER` -> `21P_R_SHARE_OTHER...133`
## • `21P_R_DNSHARE_REASON` -> `21P_R_DNSHARE_REASON...134`
## • `21P_R_DNSHARE_OTHER` -> `21P_R_DNSHARE_OTHER...135`
## • `23P_R_IMPT` -> `23P_R_IMPT...137`
## • `23P_R_INTEREST` -> `23P_R_INTEREST...138`
## • `23P_R_FAMILIAR` -> `23P_R_FAMILIAR...139`
## • `23P_R_NOVEL` -> `23P_R_NOVEL...140`
## • `23P_R_SHARE` -> `23P_R_SHARE...141`
## • `23P_R_SHARE_REASONS` -> `23P_R_SHARE_REASONS...142`
## • `23P_R_SHARE_OTHER` -> `23P_R_SHARE_OTHER...143`
## • `23P_R_DNSHARE_REASON` -> `23P_R_DNSHARE_REASON...144`
## • `23P_R_DNSHARE_OTHER` -> `23P_R_DNSHARE_OTHER...145`
## • `CTRL_SHARING_PERSP` -> `CTRL_SHARING_PERSP...147`
## • `CTRL_SHARING_PERSP` -> `CTRL_SHARING_PERSP...148`
## • `1P_R_IMPT` -> `1P_R_IMPT...150`
## • `1P_R_INTEREST` -> `1P_R_INTEREST...151`
## • `1P_R_FAMILIAR` -> `1P_R_FAMILIAR...152`
## • `1P_R_NOVEL` -> `1P_R_NOVEL...153`
## • `1P_R_SHARE` -> `1P_R_SHARE...154`
## • `1P_R_SHARE_REASONS` -> `1P_R_SHARE_REASONS...155`
## • `1P_R_SHARE_OTHER` -> `1P_R_SHARE_OTHER...156`
## • `1P_R_DNSHARE_REASONS` -> `1P_R_DNSHARE_REASONS...157`
## • `1P_R_DNSHARE_OTHER` -> `1P_R_DNSHARE_OTHER...158`
## • `2P_DF_IMPT` -> `2P_DF_IMPT...159`
## • `2P_DF_INTEREST` -> `2P_DF_INTEREST...160`
## • `2P_DF_FAMILIAR` -> `2P_DF_FAMILIAR...161`
## • `2P_DF_NOVEL` -> `2P_DF_NOVEL...162`
## • `2P_DF_SHARE` -> `2P_DF_SHARE...163`
## • `2P_DF_SHARE_REASONS` -> `2P_DF_SHARE_REASONS...164`
## • `2P_DF_SHARE_OTHER` -> `2P_DF_SHARE_OTHER...165`
## • `2P_DF_DNSHARE_REASON` -> `2P_DF_DNSHARE_REASON...166`
## • `2P_DF_DNSHARE_OTHER` -> `2P_DF_DNSHARE_OTHER...167`
## • `4P_DF_IMPT` -> `4P_DF_IMPT...168`
## • `4P_DF_INTEREST` -> `4P_DF_INTEREST...169`
## • `4P_DF_FAMILIAR` -> `4P_DF_FAMILIAR...170`
## • `4P_DF_NOVEL` -> `4P_DF_NOVEL...171`
## • `4P_DF_SHARE` -> `4P_DF_SHARE...172`
## • `4P_DF_SHARE_REASONS` -> `4P_DF_SHARE_REASONS...173`
## • `4P_DF_SHARE_OTHER` -> `4P_DF_SHARE_OTHER...174`
## • `4P_DF_DNSHARE_REASON` -> `4P_DF_DNSHARE_REASON...175`
## • `4P_DF_DNSHARE_OTHER` -> `4P_DF_DNSHARE_OTHER...176`
## • `5P_R_IMPT` -> `5P_R_IMPT...177`
## • `5P_R_INTEREST` -> `5P_R_INTEREST...178`
## • `5P_R_FAMILIAR` -> `5P_R_FAMILIAR...179`
## • `5P_R_NOVEL` -> `5P_R_NOVEL...180`
## • `5P_R_SHARE` -> `5P_R_SHARE...181`
## • `5P_R_SHARE_REASONS` -> `5P_R_SHARE_REASONS...182`
## • `5P_R_SHARE_OTHER` -> `5P_R_SHARE_OTHER...183`
## • `5P_R_DNSHARE_REASONS` -> `5P_R_DNSHARE_REASONS...184`
## • `5P_R_DNSHARE_OTHER` -> `5P_R_DNSHARE_OTHER...185`
## • `6P_DF_IMPT` -> `6P_DF_IMPT...186`
## • `6P_DF_INTEREST` -> `6P_DF_INTEREST...187`
## • `6P_DF_FAMILIAR` -> `6P_DF_FAMILIAR...188`
## • `6P_DF_NOVEL` -> `6P_DF_NOVEL...189`
## • `6P_DF_SHARE` -> `6P_DF_SHARE...190`
## • `6P_DF_SHARE_REASONS` -> `6P_DF_SHARE_REASONS...191`
## • `6P_DF_SHARE_OTHER` -> `6P_DF_SHARE_OTHER...192`
## • `6P_DF_DNSHARE_REASON` -> `6P_DF_DNSHARE_REASON...193`
## • `6P_DF_DNSHARE_OTHER` -> `6P_DF_DNSHARE_OTHER...194`
## • `7P_R_IMPT` -> `7P_R_IMPT...195`
## • `7P_R_INTEREST` -> `7P_R_INTEREST...196`
## • `7P_R_FAMILIAR` -> `7P_R_FAMILIAR...197`
## • `7P_R_NOVEL` -> `7P_R_NOVEL...198`
## • `7P_R_SHARE` -> `7P_R_SHARE...199`
## • `7P_R_SHARE_REASONS` -> `7P_R_SHARE_REASONS...200`
## • `7P_R_SHARE_OTHER` -> `7P_R_SHARE_OTHER...201`
## • `7P_R_DNSHARE_REASONS` -> `7P_R_DNSHARE_REASONS...202`
## • `7P_R_DNSHARE_OTHER` -> `7P_R_DNSHARE_OTHER...203`
## • `13P_DF_IMPT` -> `13P_DF_IMPT...204`
## • `13P_DF_INTEREST` -> `13P_DF_INTEREST...205`
## • `13P_DF_FAMILIAR` -> `13P_DF_FAMILIAR...206`
## • `13P_DF_NOVEL` -> `13P_DF_NOVEL...207`
## • `13P_DF_SHARE` -> `13P_DF_SHARE...208`
## • `13P_DF_SHARE_REASONS` -> `13P_DF_SHARE_REASONS...209`
## • `13P_DF_SHARE_OTHER` -> `13P_DF_SHARE_OTHER...210`
## • `13P_DF_DNSHARE_REASO` -> `13P_DF_DNSHARE_REASO...211`
## • `13P_DF_DNSHARE_OTHER` -> `13P_DF_DNSHARE_OTHER...212`
## • `15P_DF_IMPT` -> `15P_DF_IMPT...213`
## • `15P_DF_INTEREST` -> `15P_DF_INTEREST...214`
## • `15P_DF_FAMILIAR` -> `15P_DF_FAMILIAR...215`
## • `15P_DF_NOVEL` -> `15P_DF_NOVEL...216`
## • `15P_DF_SHARE` -> `15P_DF_SHARE...217`
## • `15P_DF_SHARE_REASONS` -> `15P_DF_SHARE_REASONS...218`
## • `15P_DF_SHARE_OTHER` -> `15P_DF_SHARE_OTHER...219`
## • `15P_DF_DNSHARE_REASO` -> `15P_DF_DNSHARE_REASO...220`
## • `15P_DF_DNSHARE_OTHER` -> `15P_DF_DNSHARE_OTHER...221`
## • `17P_R_IMPT` -> `17P_R_IMPT...222`
## • `17P_R_INTEREST` -> `17P_R_INTEREST...223`
## • `17P_R_FAMILIAR` -> `17P_R_FAMILIAR...224`
## • `17P_R_NOVEL` -> `17P_R_NOVEL...225`
## • `17P_R_SHARE` -> `17P_R_SHARE...226`
## • `17P_R_SHARE_REASONS` -> `17P_R_SHARE_REASONS...227`
## • `17P_R_SHARE_OTHER` -> `17P_R_SHARE_OTHER...228`
## • `17P_R_DNSHARE_REASON` -> `17P_R_DNSHARE_REASON...229`
## • `17P_R_DNSHARE_OTHER` -> `17P_R_DNSHARE_OTHER...230`
## • `19P_DF_IMPT` -> `19P_DF_IMPT...231`
## • `19P_DF_INTEREST` -> `19P_DF_INTEREST...232`
## • `19P_DF_FAMILIAR` -> `19P_DF_FAMILIAR...233`
## • `19P_DF_NOVEL` -> `19P_DF_NOVEL...234`
## • `19P_DF_SHARE` -> `19P_DF_SHARE...235`
## • `19P_DF_SHARE_REASONS` -> `19P_DF_SHARE_REASONS...236`
## • `19P_DF_SHARE_OTHER` -> `19P_DF_SHARE_OTHER...237`
## • `19P_DF_DNSHARE_REASO` -> `19P_DF_DNSHARE_REASO...238`
## • `19P_DF_DNSHARE_OTHER` -> `19P_DF_DNSHARE_OTHER...239`
## • `21P_R_IMPT` -> `21P_R_IMPT...240`
## • `21P_R_INTEREST` -> `21P_R_INTEREST...241`
## • `21P_R_FAMILIAR` -> `21P_R_FAMILIAR...242`
## • `21P_R_NOVEL` -> `21P_R_NOVEL...243`
## • `21P_R_SHARE` -> `21P_R_SHARE...244`
## • `21P_R_SHARE_REASONS` -> `21P_R_SHARE_REASONS...245`
## • `21P_R_SHARE_OTHER` -> `21P_R_SHARE_OTHER...246`
## • `21P_R_DNSHARE_REASON` -> `21P_R_DNSHARE_REASON...247`
## • `21P_R_DNSHARE_OTHER` -> `21P_R_DNSHARE_OTHER...248`
## • `23P_R_IMPT` -> `23P_R_IMPT...249`
## • `23P_R_INTEREST` -> `23P_R_INTEREST...250`
## • `23P_R_FAMILIAR` -> `23P_R_FAMILIAR...251`
## • `23P_R_NOVEL` -> `23P_R_NOVEL...252`
## • `23P_R_SHARE` -> `23P_R_SHARE...253`
## • `23P_R_SHARE_REASONS` -> `23P_R_SHARE_REASONS...254`
## • `23P_R_SHARE_OTHER` -> `23P_R_SHARE_OTHER...255`
## • `23P_R_DNSHARE_REASON` -> `23P_R_DNSHARE_REASON...256`
## • `23P_R_DNSHARE_OTHER` -> `23P_R_DNSHARE_OTHER...257`data_raw_ent <- read_csv("C:/Users/Dell/OneDrive/Documents/CREST Postdoc/Deepfakes Experiment/Analysis/Study_1bEntertainment/DeepF_Study1b_Entertainment.csv")## New names:
## Rows: 131 Columns: 261
## ── Column specification
## ──────────────────────────────────────────────────────── Delimiter: "," chr
## (261): StartDate, EndDate, Status, Progress, Duration (in seconds), Fini...
## ℹ Use `spec()` to retrieve the full column specification for this data. ℹ
## Specify the column types or set `show_col_types = FALSE` to quiet this message.
## • `3E_R_IMPT` -> `3E_R_IMPT...27`
## • `3E_R_INTEREST` -> `3E_R_INTEREST...28`
## • `3E_R_FAMILIAR` -> `3E_R_FAMILIAR...29`
## • `3E_R_NOVEL` -> `3E_R_NOVEL...30`
## • `3E_R_SHARE` -> `3E_R_SHARE...31`
## • `3E_R_SHARE_REASONS` -> `3E_R_SHARE_REASONS...32`
## • `3E_R_SHARE_OTHER` -> `3E_R_SHARE_OTHER...33`
## • `3E_R_DNSHARE_REASONS` -> `3E_R_DNSHARE_REASONS...34`
## • `3E_R_DNSHARE_OTHER` -> `3E_R_DNSHARE_OTHER...35`
## • `8E_DF_IMPT` -> `8E_DF_IMPT...37`
## • `8E_DF_INTEREST` -> `8E_DF_INTEREST...38`
## • `8E_DF_FAMILIAR` -> `8E_DF_FAMILIAR...39`
## • `8E_DF_NOVEL` -> `8E_DF_NOVEL...40`
## • `8E_DF_SHARE` -> `8E_DF_SHARE...41`
## • `8E_DF_SHARE_REASONS` -> `8E_DF_SHARE_REASONS...42`
## • `8E_DF_SHARE_OTHER` -> `8E_DF_SHARE_OTHER...43`
## • `8E_DF_DNSHARE_REASON` -> `8E_DF_DNSHARE_REASON...44`
## • `8E_DF_DNSHARE_OTHER` -> `8E_DF_DNSHARE_OTHER...45`
## • `9E_R_IMPT` -> `9E_R_IMPT...47`
## • `9E_R_INTEREST` -> `9E_R_INTEREST...48`
## • `9E_R_FAMILIAR` -> `9E_R_FAMILIAR...49`
## • `9E_R_NOVEL` -> `9E_R_NOVEL...50`
## • `9E_R_SHARE` -> `9E_R_SHARE...51`
## • `9E_R_SHARE_REASONS` -> `9E_R_SHARE_REASONS...52`
## • `9E_R_SHARE_OTHER` -> `9E_R_SHARE_OTHER...53`
## • `9E_R_DNSHARE_REASONS` -> `9E_R_DNSHARE_REASONS...54`
## • `9E_R_DNSHARE_OTHER` -> `9E_R_DNSHARE_OTHER...55`
## • `10E_DF_IMPT` -> `10E_DF_IMPT...57`
## • `10E_DF_INTEREST` -> `10E_DF_INTEREST...58`
## • `10E_DF_FAMILIAR` -> `10E_DF_FAMILIAR...59`
## • `10E_DF_NOVEL` -> `10E_DF_NOVEL...60`
## • `10E_DF_SHARE` -> `10E_DF_SHARE...61`
## • `10E_DF_SHARE_REASONS` -> `10E_DF_SHARE_REASONS...62`
## • `10E_DF_SHARE_OTHER` -> `10E_DF_SHARE_OTHER...63`
## • `10E_DF_DNSHARE_REASO` -> `10E_DF_DNSHARE_REASO...64`
## • `10E_DF_DNSHARE_OTHER` -> `10E_DF_DNSHARE_OTHER...65`
## • `11E_R_IMPT` -> `11E_R_IMPT...67`
## • `11E_R_INTEREST` -> `11E_R_INTEREST...68`
## • `11E_R_FAMILIAR` -> `11E_R_FAMILIAR...69`
## • `11E_R_NOVEL` -> `11E_R_NOVEL...70`
## • `11E_R_SHARE` -> `11E_R_SHARE...71`
## • `11E_R_SHARE_REASONS` -> `11E_R_SHARE_REASONS...72`
## • `11E_R_SHARE_OTHER` -> `11E_R_SHARE_OTHER...73`
## • `11E_R_DNSHARE_REASON` -> `11E_R_DNSHARE_REASON...74`
## • `11E_R_DNSHARE_OTHER` -> `11E_R_DNSHARE_OTHER...75`
## • `12E_DF_IMPT` -> `12E_DF_IMPT...77`
## • `12E_DF_INTEREST` -> `12E_DF_INTEREST...78`
## • `12E_DF_FAMILIAR` -> `12E_DF_FAMILIAR...79`
## • `12E_DF_NOVEL` -> `12E_DF_NOVEL...80`
## • `12E_DF_SHARE` -> `12E_DF_SHARE...81`
## • `12E_DF_SHARE_REASONS` -> `12E_DF_SHARE_REASONS...82`
## • `12E_DF_SHARE_OTHER` -> `12E_DF_SHARE_OTHER...83`
## • `12E_DF_DNSHARE_REASO` -> `12E_DF_DNSHARE_REASO...84`
## • `12E_DF_DNSHARE_OTHER` -> `12E_DF_DNSHARE_OTHER...85`
## • `14E_DF_IMPT` -> `14E_DF_IMPT...87`
## • `14E_DF_INTEREST` -> `14E_DF_INTEREST...88`
## • `14E_DF_FAMILIAR` -> `14E_DF_FAMILIAR...89`
## • `14E_DF_NOVEL` -> `14E_DF_NOVEL...90`
## • `14E_DF_SHARE` -> `14E_DF_SHARE...91`
## • `14E_DF_SHARE_REASONS` -> `14E_DF_SHARE_REASONS...92`
## • `14E_DF_SHARE_OTHER` -> `14E_DF_SHARE_OTHER...93`
## • `14E_DF_DNSHARE_REASO` -> `14E_DF_DNSHARE_REASO...94`
## • `14E_DF_DNSHARE_OTHER` -> `14E_DF_DNSHARE_OTHER...95`
## • `16E_DF_IMPT` -> `16E_DF_IMPT...97`
## • `16E_DF_INTEREST` -> `16E_DF_INTEREST...98`
## • `16E_DF_FAMILIAR` -> `16E_DF_FAMILIAR...99`
## • `16E_DF_NOVEL` -> `16E_DF_NOVEL...100`
## • `16E_DF_SHARE` -> `16E_DF_SHARE...101`
## • `16E_DF_SHARE_REASONS` -> `16E_DF_SHARE_REASONS...102`
## • `16E_DF_SHARE_OTHER` -> `16E_DF_SHARE_OTHER...103`
## • `16E_DF_DNSHARE_REASO` -> `16E_DF_DNSHARE_REASO...104`
## • `16E_DF_DNSHARE_OTHER` -> `16E_DF_DNSHARE_OTHER...105`
## • `18P_R_IMPT` -> `18P_R_IMPT...107`
## • `18P_R_INTEREST` -> `18P_R_INTEREST...108`
## • `18P_R_FAMILIAR` -> `18P_R_FAMILIAR...109`
## • `18P_R_NOVEL` -> `18P_R_NOVEL...110`
## • `18P_R_SHARE` -> `18P_R_SHARE...111`
## • `18P_R_SHARE_REASONS` -> `18P_R_SHARE_REASONS...112`
## • `18P_R_SHARE_OTHER` -> `18P_R_SHARE_OTHER...113`
## • `18P_R_DNSHARE_REASON` -> `18P_R_DNSHARE_REASON...114`
## • `18P_R_DNSHARE_OTHER` -> `18P_R_DNSHARE_OTHER...115`
## • `20E_R_IMPT` -> `20E_R_IMPT...117`
## • `20E_R_INTEREST` -> `20E_R_INTEREST...118`
## • `20E_R_FAMILIAR` -> `20E_R_FAMILIAR...119`
## • `20E_R_NOVEL` -> `20E_R_NOVEL...120`
## • `20E_R_SHARE` -> `20E_R_SHARE...121`
## • `20E_R_SHARE_REASONS` -> `20E_R_SHARE_REASONS...122`
## • `20E_R_SHARE_OTHER` -> `20E_R_SHARE_OTHER...123`
## • `20E_R_DNSHARE_REASON` -> `20E_R_DNSHARE_REASON...124`
## • `20E_R_DNSHARE_OTHER` -> `20E_R_DNSHARE_OTHER...125`
## • `22E_R_IMPT` -> `22E_R_IMPT...127`
## • `22E_R_INTEREST` -> `22E_R_INTEREST...128`
## • `22E_R_FAMILIAR` -> `22E_R_FAMILIAR...129`
## • `22E_R_NOVEL` -> `22E_R_NOVEL...130`
## • `22E_R_SHARE` -> `22E_R_SHARE...131`
## • `22E_R_SHARE_REASONS` -> `22E_R_SHARE_REASONS...132`
## • `22E_R_SHARE_OTHER` -> `22E_R_SHARE_OTHER...133`
## • `22E_R_DNSHARE_REASON` -> `22E_R_DNSHARE_REASON...134`
## • `22E_R_DNSHARE_OTHER` -> `22E_R_DNSHARE_OTHER...135`
## • `24E_DF_IMPT` -> `24E_DF_IMPT...137`
## • `24E_DF_INTEREST` -> `24E_DF_INTEREST...138`
## • `24E_DF_FAMILIAR` -> `24E_DF_FAMILIAR...139`
## • `24E_DF_NOVEL` -> `24E_DF_NOVEL...140`
## • `24E_DF_SHARE` -> `24E_DF_SHARE...141`
## • `24E_DF_SHARE_REASONS` -> `24E_DF_SHARE_REASONS...142`
## • `24E_DF_SHARE_OTHER` -> `24E_DF_SHARE_OTHER...143`
## • `24E_DF_DNSHARE_REASO` -> `24E_DF_DNSHARE_REASO...144`
## • `24E_DF_DNSHARE_OTHER` -> `24E_DF_DNSHARE_OTHER...145`
## • `CTRL_SHARING_PERSP` -> `CTRL_SHARING_PERSP...147`
## • `CTRL_SHARING_PERSP` -> `CTRL_SHARING_PERSP...148`
## • `3E_R_IMPT` -> `3E_R_IMPT...150`
## • `3E_R_INTEREST` -> `3E_R_INTEREST...151`
## • `3E_R_FAMILIAR` -> `3E_R_FAMILIAR...152`
## • `3E_R_NOVEL` -> `3E_R_NOVEL...153`
## • `3E_R_SHARE` -> `3E_R_SHARE...154`
## • `3E_R_SHARE_REASONS` -> `3E_R_SHARE_REASONS...155`
## • `3E_R_SHARE_OTHER` -> `3E_R_SHARE_OTHER...156`
## • `3E_R_DNSHARE_REASONS` -> `3E_R_DNSHARE_REASONS...157`
## • `3E_R_DNSHARE_OTHER` -> `3E_R_DNSHARE_OTHER...158`
## • `8E_DF_IMPT` -> `8E_DF_IMPT...159`
## • `8E_DF_INTEREST` -> `8E_DF_INTEREST...160`
## • `8E_DF_FAMILIAR` -> `8E_DF_FAMILIAR...161`
## • `8E_DF_NOVEL` -> `8E_DF_NOVEL...162`
## • `8E_DF_SHARE` -> `8E_DF_SHARE...163`
## • `8E_DF_SHARE_REASONS` -> `8E_DF_SHARE_REASONS...164`
## • `8E_DF_SHARE_OTHER` -> `8E_DF_SHARE_OTHER...165`
## • `8E_DF_DNSHARE_REASON` -> `8E_DF_DNSHARE_REASON...166`
## • `8E_DF_DNSHARE_OTHER` -> `8E_DF_DNSHARE_OTHER...167`
## • `9E_R_IMPT` -> `9E_R_IMPT...168`
## • `9E_R_INTEREST` -> `9E_R_INTEREST...169`
## • `9E_R_FAMILIAR` -> `9E_R_FAMILIAR...170`
## • `9E_R_NOVEL` -> `9E_R_NOVEL...171`
## • `9E_R_SHARE` -> `9E_R_SHARE...172`
## • `9E_R_SHARE_REASONS` -> `9E_R_SHARE_REASONS...173`
## • `9E_R_SHARE_OTHER` -> `9E_R_SHARE_OTHER...174`
## • `9E_R_DNSHARE_REASONS` -> `9E_R_DNSHARE_REASONS...175`
## • `9E_R_DNSHARE_OTHER` -> `9E_R_DNSHARE_OTHER...176`
## • `10E_DF_IMPT` -> `10E_DF_IMPT...177`
## • `10E_DF_INTEREST` -> `10E_DF_INTEREST...178`
## • `10E_DF_FAMILIAR` -> `10E_DF_FAMILIAR...179`
## • `10E_DF_NOVEL` -> `10E_DF_NOVEL...180`
## • `10E_DF_SHARE` -> `10E_DF_SHARE...181`
## • `10E_DF_SHARE_REASONS` -> `10E_DF_SHARE_REASONS...182`
## • `10E_DF_SHARE_OTHER` -> `10E_DF_SHARE_OTHER...183`
## • `10E_DF_DNSHARE_REASO` -> `10E_DF_DNSHARE_REASO...184`
## • `10E_DF_DNSHARE_OTHER` -> `10E_DF_DNSHARE_OTHER...185`
## • `11E_R_IMPT` -> `11E_R_IMPT...186`
## • `11E_R_INTEREST` -> `11E_R_INTEREST...187`
## • `11E_R_FAMILIAR` -> `11E_R_FAMILIAR...188`
## • `11E_R_NOVEL` -> `11E_R_NOVEL...189`
## • `11E_R_SHARE` -> `11E_R_SHARE...190`
## • `11E_R_SHARE_REASONS` -> `11E_R_SHARE_REASONS...191`
## • `11E_R_SHARE_OTHER` -> `11E_R_SHARE_OTHER...192`
## • `11E_R_DNSHARE_REASON` -> `11E_R_DNSHARE_REASON...193`
## • `11E_R_DNSHARE_OTHER` -> `11E_R_DNSHARE_OTHER...194`
## • `12E_DF_IMPT` -> `12E_DF_IMPT...195`
## • `12E_DF_INTEREST` -> `12E_DF_INTEREST...196`
## • `12E_DF_FAMILIAR` -> `12E_DF_FAMILIAR...197`
## • `12E_DF_NOVEL` -> `12E_DF_NOVEL...198`
## • `12E_DF_SHARE` -> `12E_DF_SHARE...199`
## • `12E_DF_SHARE_REASONS` -> `12E_DF_SHARE_REASONS...200`
## • `12E_DF_SHARE_OTHER` -> `12E_DF_SHARE_OTHER...201`
## • `12E_DF_DNSHARE_REASO` -> `12E_DF_DNSHARE_REASO...202`
## • `12E_DF_DNSHARE_OTHER` -> `12E_DF_DNSHARE_OTHER...203`
## • `14E_DF_IMPT` -> `14E_DF_IMPT...204`
## • `14E_DF_INTEREST` -> `14E_DF_INTEREST...205`
## • `14E_DF_FAMILIAR` -> `14E_DF_FAMILIAR...206`
## • `14E_DF_NOVEL` -> `14E_DF_NOVEL...207`
## • `14E_DF_SHARE` -> `14E_DF_SHARE...208`
## • `14E_DF_SHARE_REASONS` -> `14E_DF_SHARE_REASONS...209`
## • `14E_DF_SHARE_OTHER` -> `14E_DF_SHARE_OTHER...210`
## • `14E_DF_DNSHARE_REASO` -> `14E_DF_DNSHARE_REASO...211`
## • `14E_DF_DNSHARE_OTHER` -> `14E_DF_DNSHARE_OTHER...212`
## • `16E_DF_IMPT` -> `16E_DF_IMPT...213`
## • `16E_DF_INTEREST` -> `16E_DF_INTEREST...214`
## • `16E_DF_FAMILIAR` -> `16E_DF_FAMILIAR...215`
## • `16E_DF_NOVEL` -> `16E_DF_NOVEL...216`
## • `16E_DF_SHARE` -> `16E_DF_SHARE...217`
## • `16E_DF_SHARE_REASONS` -> `16E_DF_SHARE_REASONS...218`
## • `16E_DF_SHARE_OTHER` -> `16E_DF_SHARE_OTHER...219`
## • `16E_DF_DNSHARE_REASO` -> `16E_DF_DNSHARE_REASO...220`
## • `16E_DF_DNSHARE_OTHER` -> `16E_DF_DNSHARE_OTHER...221`
## • `18P_R_IMPT` -> `18P_R_IMPT...222`
## • `18P_R_INTEREST` -> `18P_R_INTEREST...223`
## • `18P_R_FAMILIAR` -> `18P_R_FAMILIAR...224`
## • `18P_R_NOVEL` -> `18P_R_NOVEL...225`
## • `18P_R_SHARE` -> `18P_R_SHARE...226`
## • `18P_R_SHARE_REASONS` -> `18P_R_SHARE_REASONS...227`
## • `18P_R_SHARE_OTHER` -> `18P_R_SHARE_OTHER...228`
## • `18P_R_DNSHARE_REASON` -> `18P_R_DNSHARE_REASON...229`
## • `18P_R_DNSHARE_OTHER` -> `18P_R_DNSHARE_OTHER...230`
## • `20E_R_IMPT` -> `20E_R_IMPT...231`
## • `20E_R_INTEREST` -> `20E_R_INTEREST...232`
## • `20E_R_FAMILIAR` -> `20E_R_FAMILIAR...233`
## • `20E_R_NOVEL` -> `20E_R_NOVEL...234`
## • `20E_R_SHARE` -> `20E_R_SHARE...235`
## • `20E_R_SHARE_REASONS` -> `20E_R_SHARE_REASONS...236`
## • `20E_R_SHARE_OTHER` -> `20E_R_SHARE_OTHER...237`
## • `20E_R_DNSHARE_REASON` -> `20E_R_DNSHARE_REASON...238`
## • `20E_R_DNSHARE_OTHER` -> `20E_R_DNSHARE_OTHER...239`
## • `22E_R_IMPT` -> `22E_R_IMPT...240`
## • `22E_R_INTEREST` -> `22E_R_INTEREST...241`
## • `22E_R_FAMILIAR` -> `22E_R_FAMILIAR...242`
## • `22E_R_NOVEL` -> `22E_R_NOVEL...243`
## • `22E_R_SHARE` -> `22E_R_SHARE...244`
## • `22E_R_SHARE_REASONS` -> `22E_R_SHARE_REASONS...245`
## • `22E_R_SHARE_OTHER` -> `22E_R_SHARE_OTHER...246`
## • `22E_R_DNSHARE_REASON` -> `22E_R_DNSHARE_REASON...247`
## • `22E_R_DNSHARE_OTHER` -> `22E_R_DNSHARE_OTHER...248`
## • `24E_DF_IMPT` -> `24E_DF_IMPT...249`
## • `24E_DF_INTEREST` -> `24E_DF_INTEREST...250`
## • `24E_DF_FAMILIAR` -> `24E_DF_FAMILIAR...251`
## • `24E_DF_NOVEL` -> `24E_DF_NOVEL...252`
## • `24E_DF_SHARE` -> `24E_DF_SHARE...253`
## • `24E_DF_SHARE_REASONS` -> `24E_DF_SHARE_REASONS...254`
## • `24E_DF_SHARE_OTHER` -> `24E_DF_SHARE_OTHER...255`
## • `24E_DF_DNSHARE_REASO` -> `24E_DF_DNSHARE_REASO...256`
## • `24E_DF_DNSHARE_OTHER` -> `24E_DF_DNSHARE_OTHER...257`##Data cleaning Political and Entertainment type data ### Likert scales to order levels
#Likert scale has
likely_values <- c(
"very unlikely",
"moderately unlikely",
"slightly unlikely",
"slightly likely",
"moderately likely",
"very likely"
)
consume_values <- c(
"Less than 1 hour per day",
"1-2 hours per day",
"2-3 hours per day",
"3-4 hours per day",
"5+ hours per day"
)
interest_levels <- c ( "not at all interested in this",
"not interested",
"neither not interested nor interested",
"interested",
"very much interested"
)
likley_shory_values <- c("Very unlikely",
"Unlikely",
"Neither likely nor unlikely",
"Likely",
"Very likely")
knowledgable_values <- c(
"Very unknowledgeable",
"Somewhat Unknowledgeable",
"Neither",
"Somewhat Knowledgeable",
"Very knowledgeable"
)
easy_levels <- c("Very difficult",
"Difficult",
"Neither difficult nor easy",
"Easy",
"Very easy")
boolen_q <- c( "Yes", "No")
importance_levels <- c ("very unimportant" ,
"unimportant",
"neither important nor unimportant",
"important" ,
"very important"
)
novel_levels <-c ("not at all novel",
"not novel",
"neither novel nor not novel",
"novel",
"very novel")
familiar_levels <-c ("not at all familiar",
"not familiar",
"neither familiar nor unfamiliar",
"familiar",
"very familiar")
believe_levels <- c("very unlikely",
"unlikely",
"neither likely nor unlikely",
"likely",
"very likely" )ent_individual_df <- data_raw_ent |> filter(Finished == "True") |>
mutate(Duration = as.numeric(`Duration (in seconds)`),
AGE = as.numeric(AGE),
BROWSE_INTERNET = ordered(BROWSE_INTERNET, levels = consume_values),
browse_internet = as.numeric(BROWSE_INTERNET, levels = consume_values),
USE_SNS = ordered(USE_SNS, levels = consume_values),
use_sns = as.numeric(USE_SNS, levels = consume_values),
WATCHING_BEHAVIOR = ordered(WATCHING_BEHAVIOR, levels =likley_shory_values),
watching_behavior = as.numeric (WATCHING_BEHAVIOR, levels =likley_shory_values),
SHARING_BEHAVIOR = ordered(SHARING_BEHAVIOR, levels = likley_shory_values),
sharing_behavior = as.numeric(SHARING_BEHAVIOR, levels = likley_shory_values),
KNOW_DEEPFAKE = KNOW_DEEPFAKE == "Yes",
EXP_CREATE_DF = EXP_CREATE_DF == "Yes",
KNOW_CREATE_DF = ordered(KNOW_CREATE_DF, levels = knowledgable_values),
know_create_df = as.numeric(KNOW_CREATE_DF, levels = knowledgable_values),
EASE_CREATE_DF = ordered(EASE_CREATE_DF, levels = easy_levels),
ease_create_df = as.numeric(EASE_CREATE_DF, levels = easy_levels)
) |>
select(
ResponseId,
Duration,
AGE,
BROWSE_INTERNET,
browse_internet,
USE_SNS,
use_sns,
SNS_PLATFORM_USE,
WATCHING_BEHAVIOR,
watching_behavior,
SHARING_BEHAVIOR,
sharing_behavior,
KNOW_DEEPFAKE,
KNOW_CREATE_DF,
know_create_df,
EXP_CREATE_DF,
EASE_CREATE_DF,
ease_create_df
) |> mutate(
SNS_PLATFORM_USE = strsplit(SNS_PLATFORM_USE,split = ","),
value = TRUE
) |>
unnest() |>
mutate(SNS_PLATFORM_USE = paste0("Plat_",SNS_PLATFORM_USE)) |>
pivot_wider(names_from = SNS_PLATFORM_USE, values_fill = FALSE)## Warning: `cols` is now required when using `unnest()`.
## ℹ Please use `cols = c(SNS_PLATFORM_USE)`.pol_individual_df <- data_raw_pol |> filter(Finished == "True") |>
mutate(Duration = as.numeric(`Duration (in seconds)`),
AGE = as.numeric(AGE),
BROWSE_INTERNET = ordered(BROWSE_INTERNET, levels = consume_values),
browse_internet = as.numeric(BROWSE_INTERNET, levels = consume_values),
USE_SNS = ordered(USE_SNS, levels = consume_values),
use_sns = as.numeric(USE_SNS, levels = consume_values),
WATCHING_BEHAVIOR = ordered(WATCHING_BEHAVIOR, levels =likley_shory_values),
watching_behavior = as.numeric (WATCHING_BEHAVIOR, levels =likley_shory_values),
SHARING_BEHAVIOR = ordered(SHARING_BEHAVIOR, levels = likley_shory_values),
sharing_behavior = as.numeric(SHARING_BEHAVIOR, levels = likley_shory_values),
KNOW_DEEPFAKE = KNOW_DEEPFAKE == "Yes",
EXP_CREATE_DF = EXP_CREATE_DF == "Yes",
KNOW_CREATE_DF = ordered(KNOW_CREATE_DF, levels = knowledgable_values),
know_create_df = as.numeric(KNOW_CREATE_DF, levels = knowledgable_values),
EASE_CREATE_DF = ordered(EASE_CREATE_DF, levels = easy_levels),
ease_create_df = as.numeric(EASE_CREATE_DF, levels = easy_levels)
) |>
select(
ResponseId,
Duration,
AGE,
BROWSE_INTERNET,
browse_internet,
USE_SNS,
use_sns,
SNS_PLATFORM_USE,
WATCHING_BEHAVIOR,
watching_behavior,
SHARING_BEHAVIOR,
sharing_behavior,
KNOW_DEEPFAKE,
KNOW_CREATE_DF,
know_create_df,
EXP_CREATE_DF,
EASE_CREATE_DF,
ease_create_df
) |> mutate(
SNS_PLATFORM_USE = strsplit(SNS_PLATFORM_USE,split = ","),
value = TRUE
) |>
unnest() |>
mutate(SNS_PLATFORM_USE = paste0("Plat_",SNS_PLATFORM_USE)) |>
pivot_wider(names_from = SNS_PLATFORM_USE, values_fill = FALSE)## Warning: `cols` is now required when using `unnest()`.
## ℹ Please use `cols = c(SNS_PLATFORM_USE)`.#Combining the two data frames of Pol and Ent
#data needed to be selected since columns were uneven from tables on sns_use
pol_df<-pol_individual_df|> select ( ResponseId,
Duration,
AGE ,
BROWSE_INTERNET ,
browse_internet ,
USE_SNS ,
use_sns ,
WATCHING_BEHAVIOR,
watching_behavior,
SHARING_BEHAVIOR ,
sharing_behavior ,
KNOW_DEEPFAKE ,
EXP_CREATE_DF ,
KNOW_CREATE_DF,
know_create_df ,
EASE_CREATE_DF,
ease_create_df,
)
ent_df<-ent_individual_df|> select ( ResponseId,
Duration,
AGE ,
BROWSE_INTERNET ,
browse_internet ,
USE_SNS ,
use_sns ,
WATCHING_BEHAVIOR,
watching_behavior,
SHARING_BEHAVIOR ,
sharing_behavior ,
KNOW_DEEPFAKE ,
EXP_CREATE_DF ,
KNOW_CREATE_DF,
know_create_df ,
EASE_CREATE_DF,
ease_create_df,
)
combined_individual_df <- rbind(pol_df, ent_df)# Sharability behavior after watching each video
pol_behavior_df <-data_raw_pol |> filter(Finished == "True") |>
select(ResponseId, matches ("_R_"), matches ("_DF_")) |>
pivot_longer(-ResponseId, values_drop_na = TRUE) |>
separate(name, c("video", "fake", "question", "question_detail")) |>
group_by(ResponseId) |>
mutate(condition = if_else(any(grepl("BELIEVE", question)), "Treatment", "Control")) |>
ungroup() |>
filter(question_detail != "REASONS", question_detail != "OTHER") |> group_by(ResponseId) |>
select(-question_detail) |> pivot_wider(names_from = question, values_from = value)|>
mutate(SHARE = str_to_lower(SHARE),
share_numerical = as.numeric(ordered(SHARE, levels = likely_values)),
IMPT = str_to_lower (IMPT),
impt_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
INTEREST = str_to_lower(INTEREST),
INTEREST = str_replace (INTEREST, "uninterested" , "not interested" ),
interest_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
FAMILIAR = str_to_lower (FAMILIAR),
familiar_numerical = as.numeric(ordered(FAMILIAR, levels = familiar_levels)),
NOVEL = str_to_lower(NOVEL),
novel_numerical = as.numeric(ordered(NOVEL, levels = novel_levels)),
fake = as.factor(fake),
isvideodeepfake= ifelse(fake=="R",0,1)
)## Warning: Expected 4 pieces. Additional pieces discarded in 1621 rows [6, 12, 18, 24, 30,
## 36, 42, 48, 54, 60, 66, 72, 79, 80, 87, 94, 101, 108, 109, 116, ...].## Warning: Expected 4 pieces. Missing pieces filled with `NA` in 756 rows [73, 81, 88, 95,
## 102, 110, 118, 125, 132, 139, 146, 153, 232, 239, 246, 253, 260, 267, 274, 281,
## ...].# Sharability behavior after watching each video
ent_behavior_df <-data_raw_ent |> filter(Finished == "True") |>
select(ResponseId, matches ("_R_"), matches ("_DF_")) |>
pivot_longer(-ResponseId, values_drop_na = TRUE) |>
separate(name, c("video", "fake", "question", "question_detail")) |>
group_by(ResponseId) |>
mutate(condition = if_else(any(grepl("BELIEVE", question)), "Treatment", "Control")) |>
ungroup() |>
filter(question_detail != "REASONS", question_detail != "OTHER") |> group_by(ResponseId) |>
select(-question_detail) |> pivot_wider(names_from = question, values_from = value)|>
mutate(SHARE = str_to_lower(SHARE),
share_numerical = as.numeric(ordered(SHARE, levels = likely_values)),
IMPT = str_to_lower (IMPT),
impt_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
INTEREST = str_to_lower(INTEREST),
INTEREST = str_replace (INTEREST, "uninterested" , "not interested" ),
interest_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
FAMILIAR = str_to_lower (FAMILIAR),
familiar_numerical = as.numeric(ordered(FAMILIAR, levels = familiar_levels)),
NOVEL = str_to_lower(NOVEL),
novel_numerical = as.numeric(ordered(NOVEL, levels = novel_levels)),
fake = as.factor(fake),
isvideodeepfake= ifelse(fake=="R",0,1)
)## Warning: Expected 4 pieces. Additional pieces discarded in 1610 rows [7, 14, 21, 28, 35,
## 42, 49, 56, 63, 70, 77, 84, 90, 96, 102, 108, 114, 120, 126, 132, ...].## Warning: Expected 4 pieces. Missing pieces filled with `NA` in 780 rows [1, 8, 15, 22,
## 29, 36, 43, 50, 57, 64, 71, 78, 230, 237, 244, 251, 258, 265, 272, 279, ...].combined_behavior_df <- rbind(pol_behavior_df,ent_behavior_df)# combined all indivual and behavior
combined_df<- merge(combined_individual_df, combined_behavior_df, by.x = "ResponseId", by.y = "ResponseId")
Individuals_behavior_combined_df <- combined_df |> mutate(video_subject= if_else(grepl("P", video), "Political", "Entertrianment"))##Understanding the demography of both pol and ent data on their previous deepfake experience
# Histogram By Category
ggplot(Individuals_behavior_combined_df, aes(x=SHARING_BEHAVIOR, fill = condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2) 
ggplot(Individuals_behavior_combined_df, aes(x=WATCHING_BEHAVIOR,fill = condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=BROWSE_INTERNET, fill = condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=USE_SNS,fill = condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=KNOW_DEEPFAKE,fill = condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
Understanding the sharing behavior based on individual data
###Behaviors after watching videos
ggplot(Individuals_behavior_combined_df, aes(x=share_numerical, fill= condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=interest_numerical, fill= condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=novel_numerical, fill=condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(x=impt_numerical, fill= condition)) +
geom_bar() +
facet_wrap(~condition, nrow=2)
ggplot(Individuals_behavior_combined_df, aes(share_numerical)) +
geom_histogram(color = "#000000", fill = "#0099F8")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
ggplot(Individuals_behavior_combined_df, aes(x=share_numerical, color=condition)) +
geom_histogram(fill="white", alpha=0.5, position="identity")## `stat_bin()` using `bins = 30`. Pick better value with `binwidth`.
Regression model
Regreasion_model_df<-Individuals_behavior_combined_df |>select ( ResponseId, video, fake, isvideodeepfake, condition, share_numerical, impt_numerical, interest_numerical, familiar_numerical, novel_numerical, use_sns, watching_behavior, sharing_behavior, know_create_df, ease_create_df, browse_internet)
sharing_deepfakes_df<-Individuals_behavior_combined_df |>select ( ResponseId, fake, isvideodeepfake, condition, share_numerical)
corelations_df <-Individuals_behavior_combined_df |>select ( share_numerical, impt_numerical, interest_numerical, familiar_numerical, novel_numerical, use_sns, watching_behavior, sharing_behavior, know_create_df, ease_create_df, browse_internet, isvideodeepfake)
lmshare = lm(share_numerical~ impt_numerical+ interest_numerical + familiar_numerical+ novel_numerical+ condition + fake + video, data = Regreasion_model_df)
summary(lmshare)##
## Call:
## lm(formula = share_numerical ~ impt_numerical + interest_numerical +
## familiar_numerical + novel_numerical + condition + fake +
## video, data = Regreasion_model_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.6748 -0.6938 -0.0969 0.4496 4.1864
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.11219 0.11612 0.966 0.334051
## impt_numerical 0.19598 0.01860 10.537 < 2e-16 ***
## interest_numerical NA NA NA NA
## familiar_numerical 0.03625 0.01603 2.262 0.023792 *
## novel_numerical 0.48425 0.01888 25.651 < 2e-16 ***
## conditionTreatment -0.08304 0.03781 -2.196 0.028138 *
## fakeR 0.11837 0.13305 0.890 0.373737
## video11E 0.16459 0.13333 1.234 0.217123
## video12E -0.12001 0.13178 -0.911 0.362556
## video13P -0.19540 0.13362 -1.462 0.143759
## video14E -0.03341 0.13064 -0.256 0.798149
## video15P -0.40541 0.13311 -3.046 0.002342 **
## video16E -0.09286 0.13448 -0.690 0.489938
## video17P -0.25753 0.13183 -1.953 0.050856 .
## video18P -0.09609 0.13117 -0.733 0.463901
## video19P -0.37629 0.13139 -2.864 0.004213 **
## video1P -0.47483 0.13372 -3.551 0.000390 ***
## video20E -0.01507 0.13088 -0.115 0.908350
## video21P -0.23660 0.13407 -1.765 0.077702 .
## video22E 0.13536 0.13376 1.012 0.311650
## video23P -0.46610 0.13200 -3.531 0.000420 ***
## video24E -0.01982 0.13102 -0.151 0.879785
## video2P -0.44458 0.13143 -3.382 0.000727 ***
## video3E -0.14944 0.13365 -1.118 0.263585
## video4P -0.16882 0.13404 -1.259 0.207951
## video5P -0.12907 0.13529 -0.954 0.340141
## video6P -0.51765 0.13339 -3.881 0.000106 ***
## video7P -0.51069 0.13217 -3.864 0.000114 ***
## video8E -0.21575 0.13121 -1.644 0.100216
## video9E NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.048 on 3056 degrees of freedom
## Multiple R-squared: 0.3298, Adjusted R-squared: 0.3239
## F-statistic: 55.7 on 27 and 3056 DF, p-value: < 2.2e-16tab_model(lmshare)## Model matrix is rank deficient. Parameters `interest_numerical, video9E`
## were not estimable.| share_numerical | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.11 | -0.12 – 0.34 | 0.334 |
| impt numerical | 0.20 | 0.16 – 0.23 | <0.001 |
| familiar numerical | 0.04 | 0.00 – 0.07 | 0.024 |
| novel numerical | 0.48 | 0.45 – 0.52 | <0.001 |
| condition [Treatment] | -0.08 | -0.16 – -0.01 | 0.028 |
| fake [R] | 0.12 | -0.14 – 0.38 | 0.374 |
| video [11E] | 0.16 | -0.10 – 0.43 | 0.217 |
| video [12E] | -0.12 | -0.38 – 0.14 | 0.363 |
| video [13P] | -0.20 | -0.46 – 0.07 | 0.144 |
| video [14E] | -0.03 | -0.29 – 0.22 | 0.798 |
| video [15P] | -0.41 | -0.67 – -0.14 | 0.002 |
| video [16E] | -0.09 | -0.36 – 0.17 | 0.490 |
| video [17P] | -0.26 | -0.52 – 0.00 | 0.051 |
| video [18P] | -0.10 | -0.35 – 0.16 | 0.464 |
| video [19P] | -0.38 | -0.63 – -0.12 | 0.004 |
| video [1P] | -0.47 | -0.74 – -0.21 | <0.001 |
| video [20E] | -0.02 | -0.27 – 0.24 | 0.908 |
| video [21P] | -0.24 | -0.50 – 0.03 | 0.078 |
| video [22E] | 0.14 | -0.13 – 0.40 | 0.312 |
| video [23P] | -0.47 | -0.72 – -0.21 | <0.001 |
| video [24E] | -0.02 | -0.28 – 0.24 | 0.880 |
| video [2P] | -0.44 | -0.70 – -0.19 | 0.001 |
| video [3E] | -0.15 | -0.41 – 0.11 | 0.264 |
| video [4P] | -0.17 | -0.43 – 0.09 | 0.208 |
| video [5P] | -0.13 | -0.39 – 0.14 | 0.340 |
| video [6P] | -0.52 | -0.78 – -0.26 | <0.001 |
| video [7P] | -0.51 | -0.77 – -0.25 | <0.001 |
| video [8E] | -0.22 | -0.47 – 0.04 | 0.100 |
| Observations | 3084 | ||
| R2 / R2 adjusted | 0.330 / 0.324 | ||
#does the share depends on video being a deepfake
dfshare = lm(isvideodeepfake~share_numerical, data = Regreasion_model_df)
summary(dfshare)##
## Call:
## lm(formula = isvideodeepfake ~ share_numerical, data = Regreasion_model_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.53497 -0.53497 0.07544 0.46503 0.68584
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 0.579130 0.015445 37.496 < 2e-16 ***
## share_numerical -0.044162 0.007025 -6.286 3.72e-10 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 0.497 on 3082 degrees of freedom
## Multiple R-squared: 0.01266, Adjusted R-squared: 0.01234
## F-statistic: 39.51 on 1 and 3082 DF, p-value: 3.717e-10tab_model(dfshare)| isvideodeepfake | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 0.58 | 0.55 – 0.61 | <0.001 |
| share numerical | -0.04 | -0.06 – -0.03 | <0.001 |
| Observations | 3084 | ||
| R2 / R2 adjusted | 0.013 / 0.012 | ||
#Anova between two groups, to check if there is a diference in deepfake or real videos
sharability_deepfake_df <-Individuals_behavior_combined_df |>select ( ResponseId, fake, isvideodeepfake, condition, share_numerical)
share_deepfakes_or_not <- aov(share_numerical~fake, data= sharability_deepfake_df)
summary(share_deepfakes_or_not)## Df Sum Sq Mean Sq F value Pr(>F)
## fake 1 63 63.35 39.51 3.72e-10 ***
## Residuals 3082 4941 1.60
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tab_model(share_deepfakes_or_not)| share_numerical | |
|---|---|
| Predictors | p |
| fake | <0.001 |
| Residuals | |
| Observations | 3084 |
| R2 / R2 adjusted | 0.013 / 0.012 |
TukeyHSD(share_deepfakes_or_not, conf.level=.95)## Tukey multiple comparisons of means
## 95% family-wise confidence level
##
## Fit: aov(formula = share_numerical ~ fake, data = sharability_deepfake_df)
##
## $fake
## diff lwr upr p adj
## R-DF 0.2866407 0.1972314 0.3760501 0pairwise.t.test(sharability_deepfake_df$share_numerical, sharability_deepfake_df$fake, p.adj = "bonf")##
## Pairwise comparisons using t tests with pooled SD
##
## data: sharability_deepfake_df$share_numerical and sharability_deepfake_df$fake
##
## DF
## R 3.7e-10
##
## P value adjustment method: bonferroniggplot(sharability_deepfake_df, aes(fake,share_numerical)) +
# facet_wrap(vars(video)) +
stat_summary(
fun.data = mean_cl_boot,
geom = "pointrange",
shape = 21,
fill = "white"
)
ggplot(sharability_deepfake_df, aes(x=share_numerical, fill = fake)) +
geom_bar() +
facet_wrap(~fake, nrow=2)
ggplot(sharability_deepfake_df, aes(x=fake, y= share_numerical,group=fake)) +
geom_boxplot(aes(fill=fake))
corelation_behavior <-cor(corelations_df)
print(corelation_behavior)## share_numerical impt_numerical interest_numerical
## share_numerical 1.00000000 0.359276962 0.359276962
## impt_numerical 0.35927696 1.000000000 1.000000000
## interest_numerical 0.35927696 1.000000000 1.000000000
## familiar_numerical 0.15470677 0.256001917 0.256001917
## novel_numerical 0.52199955 0.389133784 0.389133784
## use_sns 0.15526789 0.119024866 0.119024866
## watching_behavior 0.06824486 0.099735605 0.099735605
## sharing_behavior 0.27160075 0.076250190 0.076250190
## know_create_df 0.03252887 -0.007354733 -0.007354733
## ease_create_df 0.01191750 0.004865348 0.004865348
## browse_internet 0.16725007 0.137174348 0.137174348
## isvideodeepfake -0.11250999 -0.198593869 -0.198593869
## familiar_numerical novel_numerical use_sns
## share_numerical 0.1547067738 0.521999554 0.1552678896
## impt_numerical 0.2560019165 0.389133784 0.1190248664
## interest_numerical 0.2560019165 0.389133784 0.1190248664
## familiar_numerical 1.0000000000 0.191947879 -0.0006834883
## novel_numerical 0.1919478786 1.000000000 0.0886806342
## use_sns -0.0006834883 0.088680634 1.0000000000
## watching_behavior 0.1119849637 0.008414933 0.3473773536
## sharing_behavior 0.0541559044 0.145934137 0.2587550930
## know_create_df 0.0874720865 -0.015285694 -0.0050098789
## ease_create_df -0.0519797982 0.010469816 0.1204580288
## browse_internet 0.0323313344 0.112576414 0.5465527147
## isvideodeepfake 0.0304437259 -0.023325180 0.0000000000
## watching_behavior sharing_behavior know_create_df
## share_numerical 0.068244857 0.27160075 0.032528874
## impt_numerical 0.099735605 0.07625019 -0.007354733
## interest_numerical 0.099735605 0.07625019 -0.007354733
## familiar_numerical 0.111984964 0.05415590 0.087472086
## novel_numerical 0.008414933 0.14593414 -0.015285694
## use_sns 0.347377354 0.25875509 -0.005009879
## watching_behavior 1.000000000 0.26078604 0.052366378
## sharing_behavior 0.260786044 1.00000000 0.069391589
## know_create_df 0.052366378 0.06939159 1.000000000
## ease_create_df -0.013183927 -0.02990752 0.105552370
## browse_internet 0.264180750 0.18943918 0.195119814
## isvideodeepfake 0.000000000 0.00000000 0.000000000
## ease_create_df browse_internet isvideodeepfake
## share_numerical 0.011917504 0.16725007 -0.11250999
## impt_numerical 0.004865348 0.13717435 -0.19859387
## interest_numerical 0.004865348 0.13717435 -0.19859387
## familiar_numerical -0.051979798 0.03233133 0.03044373
## novel_numerical 0.010469816 0.11257641 -0.02332518
## use_sns 0.120458029 0.54655271 0.00000000
## watching_behavior -0.013183927 0.26418075 0.00000000
## sharing_behavior -0.029907517 0.18943918 0.00000000
## know_create_df 0.105552370 0.19511981 0.00000000
## ease_create_df 1.000000000 0.07597182 0.00000000
## browse_internet 0.075971819 1.00000000 0.00000000
## isvideodeepfake 0.000000000 0.00000000 1.00000000confint(lmshare)## 2.5 % 97.5 %
## (Intercept) -0.115492100 0.3398664553
## impt_numerical 0.159506583 0.2324438988
## interest_numerical NA NA
## familiar_numerical 0.004822706 0.0676836956
## novel_numerical 0.447237362 0.5212707026
## conditionTreatment -0.157162677 -0.0089090974
## fakeR -0.142515410 0.3792505067
## video11E -0.096833305 0.4260159771
## video12E -0.378395088 0.1383837060
## video13P -0.457399756 0.0666021857
## video14E -0.289567452 0.2227401779
## video15P -0.666410036 -0.1444066980
## video16E -0.356549757 0.1708291077
## video17P -0.516025857 0.0009596433
## video18P -0.353272925 0.1611028970
## video19P -0.633922173 -0.1186658950
## video1P -0.737015141 -0.2126432488
## video20E -0.271689490 0.2415533110
## video21P -0.499465158 0.0262729612
## video22E -0.126914788 0.3976327010
## video23P -0.724927771 -0.2072808711
## video24E -0.276707093 0.2370731992
## video2P -0.702284497 -0.1868655646
## video3E -0.411480876 0.1126064400
## video4P -0.431646075 0.0939978486
## video5P -0.394332459 0.1361945546
## video6P -0.779182082 -0.2561150004
## video7P -0.769847307 -0.2515312102
## video8E -0.473030412 0.0415205906
## video9E NA NAlibrary("Hmisc")##
## Attaching package: 'Hmisc'## The following object is masked from 'package:sjmisc':
##
## %nin%## The following objects are masked from 'package:dplyr':
##
## src, summarize## The following objects are masked from 'package:base':
##
## format.pval, unitscor <- rcorr(as.matrix(corelations_df))
print(cor)## share_numerical impt_numerical interest_numerical
## share_numerical 1.00 0.36 0.36
## impt_numerical 0.36 1.00 1.00
## interest_numerical 0.36 1.00 1.00
## familiar_numerical 0.15 0.26 0.26
## novel_numerical 0.52 0.39 0.39
## use_sns 0.16 0.12 0.12
## watching_behavior 0.07 0.10 0.10
## sharing_behavior 0.27 0.08 0.08
## know_create_df 0.03 -0.01 -0.01
## ease_create_df 0.01 0.00 0.00
## browse_internet 0.17 0.14 0.14
## isvideodeepfake -0.11 -0.20 -0.20
## familiar_numerical novel_numerical use_sns watching_behavior
## share_numerical 0.15 0.52 0.16 0.07
## impt_numerical 0.26 0.39 0.12 0.10
## interest_numerical 0.26 0.39 0.12 0.10
## familiar_numerical 1.00 0.19 0.00 0.11
## novel_numerical 0.19 1.00 0.09 0.01
## use_sns 0.00 0.09 1.00 0.35
## watching_behavior 0.11 0.01 0.35 1.00
## sharing_behavior 0.05 0.15 0.26 0.26
## know_create_df 0.09 -0.02 -0.01 0.05
## ease_create_df -0.05 0.01 0.12 -0.01
## browse_internet 0.03 0.11 0.55 0.26
## isvideodeepfake 0.03 -0.02 0.00 0.00
## sharing_behavior know_create_df ease_create_df
## share_numerical 0.27 0.03 0.01
## impt_numerical 0.08 -0.01 0.00
## interest_numerical 0.08 -0.01 0.00
## familiar_numerical 0.05 0.09 -0.05
## novel_numerical 0.15 -0.02 0.01
## use_sns 0.26 -0.01 0.12
## watching_behavior 0.26 0.05 -0.01
## sharing_behavior 1.00 0.07 -0.03
## know_create_df 0.07 1.00 0.11
## ease_create_df -0.03 0.11 1.00
## browse_internet 0.19 0.20 0.08
## isvideodeepfake 0.00 0.00 0.00
## browse_internet isvideodeepfake
## share_numerical 0.17 -0.11
## impt_numerical 0.14 -0.20
## interest_numerical 0.14 -0.20
## familiar_numerical 0.03 0.03
## novel_numerical 0.11 -0.02
## use_sns 0.55 0.00
## watching_behavior 0.26 0.00
## sharing_behavior 0.19 0.00
## know_create_df 0.20 0.00
## ease_create_df 0.08 0.00
## browse_internet 1.00 0.00
## isvideodeepfake 0.00 1.00
##
## n= 3084
##
##
## P
## share_numerical impt_numerical interest_numerical
## share_numerical 0.0000 0.0000
## impt_numerical 0.0000 0.0000
## interest_numerical 0.0000 0.0000
## familiar_numerical 0.0000 0.0000 0.0000
## novel_numerical 0.0000 0.0000 0.0000
## use_sns 0.0000 0.0000 0.0000
## watching_behavior 0.0001 0.0000 0.0000
## sharing_behavior 0.0000 0.0000 0.0000
## know_create_df 0.0709 0.6831 0.6831
## ease_create_df 0.5082 0.7871 0.7871
## browse_internet 0.0000 0.0000 0.0000
## isvideodeepfake 0.0000 0.0000 0.0000
## familiar_numerical novel_numerical use_sns watching_behavior
## share_numerical 0.0000 0.0000 0.0000 0.0001
## impt_numerical 0.0000 0.0000 0.0000 0.0000
## interest_numerical 0.0000 0.0000 0.0000 0.0000
## familiar_numerical 0.0000 0.9697 0.0000
## novel_numerical 0.0000 0.0000 0.6404
## use_sns 0.9697 0.0000 0.0000
## watching_behavior 0.0000 0.6404 0.0000
## sharing_behavior 0.0026 0.0000 0.0000 0.0000
## know_create_df 0.0000 0.3961 0.7809 0.0036
## ease_create_df 0.0039 0.5611 0.0000 0.4642
## browse_internet 0.0726 0.0000 0.0000 0.0000
## isvideodeepfake 0.0910 0.1953 1.0000 1.0000
## sharing_behavior know_create_df ease_create_df
## share_numerical 0.0000 0.0709 0.5082
## impt_numerical 0.0000 0.6831 0.7871
## interest_numerical 0.0000 0.6831 0.7871
## familiar_numerical 0.0026 0.0000 0.0039
## novel_numerical 0.0000 0.3961 0.5611
## use_sns 0.0000 0.7809 0.0000
## watching_behavior 0.0000 0.0036 0.4642
## sharing_behavior 0.0001 0.0968
## know_create_df 0.0001 0.0000
## ease_create_df 0.0968 0.0000
## browse_internet 0.0000 0.0000 0.0000
## isvideodeepfake 1.0000 1.0000 1.0000
## browse_internet isvideodeepfake
## share_numerical 0.0000 0.0000
## impt_numerical 0.0000 0.0000
## interest_numerical 0.0000 0.0000
## familiar_numerical 0.0726 0.0910
## novel_numerical 0.0000 0.1953
## use_sns 0.0000 1.0000
## watching_behavior 0.0000 1.0000
## sharing_behavior 0.0000 1.0000
## know_create_df 0.0000 1.0000
## ease_create_df 0.0000 1.0000
## browse_internet 1.0000
## isvideodeepfake 1.0000library(corrplot)## corrplot 0.92 loadedcorrplot(corelation_behavior, type = "upper", order = "hclust",
tl.col = "black", tl.srt = 45)
cor.mtest <- function(mat, ...) {
mat <- as.matrix(mat)
n <- ncol(mat)
p.mat<- matrix(NA, n, n)
diag(p.mat) <- 0
for (i in 1:(n - 1)) {
for (j in (i + 1):n) {
tmp <- cor.test(mat[, i], mat[, j], ...)
p.mat[i, j] <- p.mat[j, i] <- tmp$p.value
}
}
colnames(p.mat) <- rownames(p.mat) <- colnames(mat)
p.mat
}
# matrix of the p-value of the correlation
p.mat <- cor.mtest(corelations_df)
print(p.mat[, 1:5])## share_numerical impt_numerical interest_numerical
## share_numerical 0.000000e+00 1.281352e-94 1.281352e-94
## impt_numerical 1.281352e-94 0.000000e+00 0.000000e+00
## interest_numerical 1.281352e-94 0.000000e+00 0.000000e+00
## familiar_numerical 5.619676e-18 2.418161e-47 2.418161e-47
## novel_numerical 3.461304e-215 4.766198e-112 4.766198e-112
## use_sns 4.255107e-18 3.338649e-11 3.338649e-11
## watching_behavior 1.489700e-04 2.851924e-08 2.851924e-08
## sharing_behavior 2.739896e-53 2.246015e-05 2.246015e-05
## know_create_df 7.088761e-02 6.830710e-01 6.830710e-01
## ease_create_df 5.082410e-01 7.870962e-01 7.870962e-01
## browse_internet 8.748798e-21 1.995574e-14 1.995574e-14
## isvideodeepfake 3.716949e-10 8.447731e-29 8.447731e-29
## familiar_numerical novel_numerical
## share_numerical 5.619676e-18 3.461304e-215
## impt_numerical 2.418161e-47 4.766198e-112
## interest_numerical 2.418161e-47 4.766198e-112
## familiar_numerical 0.000000e+00 5.587541e-27
## novel_numerical 5.587541e-27 0.000000e+00
## use_sns 9.697345e-01 8.118628e-07
## watching_behavior 4.487577e-10 6.404056e-01
## sharing_behavior 2.625664e-03 3.804588e-16
## know_create_df 1.144494e-06 3.961163e-01
## ease_create_df 3.884202e-03 5.610999e-01
## browse_internet 7.261827e-02 3.629166e-10
## isvideodeepfake 9.095884e-02 1.953250e-01col <- colorRampPalette(c("#BB4444", "#EE9988", "#E0E0E0", "#77AADD", "#4477AA"))
corrplot(corelation_behavior, method="color", col=col(200),
type="upper", order="hclust",
addCoef.col = "black", # Add coefficient of correlation
tl.col="black", tl.srt=45, #Text label color and rotation
# Combine with significance
p.mat = p.mat, sig.level = 0.01, insig = "blank",
# hide correlation coefficient on the principal diagonal
diag=FALSE
)
#Treatment “Believe its a deepfake or not”
# Beliveability
pol_beliveble_vs_sharability_df <-data_raw_pol |> filter(Finished == "True") |>
select(ResponseId, matches ("_R_"), matches ("_DF_")) |>
pivot_longer(-ResponseId, values_drop_na = TRUE) |>
separate(name, c("video", "fake", "question", "question_detail"), "_", extra= "merge") |>
filter (question != "SHARE", question != "DNSHARE") |>
separate(question, c("question", "other")) |>
select(-question_detail, -other)|>
pivot_wider(names_from = question, values_from = value) |>
mutate (condition = if_else(is.na(BELIEVE), "Control", "Treatment" )) |>
select (ResponseId, fake, video, condition,SHARE, BELIEVE, IMPT, NOVEL, INTEREST, FAMILIAR)|>
filter (condition=="Treatment") |>
mutate(SHARE = str_to_lower(SHARE),share_numerical = as.numeric(ordered(SHARE, levels = likely_values)),
BELIEVE= str_to_lower(BELIEVE),
believe_numerical = as.numeric(ordered(BELIEVE, levels = believe_levels)),
IMPT= str_to_lower(IMPT),
impt_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
INTEREST = str_to_lower(INTEREST),
INTEREST = str_replace (INTEREST, "uninterested" , "not interested" ),
interest_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
FAMILIAR = str_to_lower (FAMILIAR),
familiar_numerical = as.numeric(ordered(FAMILIAR, levels = familiar_levels)),
NOVEL = str_to_lower(NOVEL),
novel_numerical = as.numeric(ordered(NOVEL, levels = novel_levels)))## Warning: Expected 4 pieces. Missing pieces filled with `NA` in 8436 rows [1, 2, 3, 4, 5,
## 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 19, 20, 21, 22, 23, ...].## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 756 rows [61, 67, 73, 79,
## 85, 91, 97, 103, 109, 115, 121, 127, 193, 199, 205, 211, 217, 223, 229, 235,
## ...].ent_beliveble_vs_sharability_df <-data_raw_ent |> filter(Finished == "True") |>
select(ResponseId, matches ("_R_"), matches ("_DF_")) |>
pivot_longer(-ResponseId, values_drop_na = TRUE) |>
separate(name, c("video", "fake", "question", "question_detail"), "_", extra= "merge") |>
filter (question != "SHARE", question != "DNSHARE") |>
separate(question, c("question", "other")) |>
select(-question_detail, -other)|>
pivot_wider(names_from = question, values_from = value) |>
mutate (condition = if_else(is.na(BELIEVE), "Control", "Treatment" )) |>
select (ResponseId, fake, video, condition,SHARE, BELIEVE, IMPT, NOVEL, INTEREST, FAMILIAR)|>
filter (condition=="Treatment") |>
mutate(SHARE = str_to_lower(SHARE),share_numerical = as.numeric(ordered(SHARE, levels = likely_values)),
BELIEVE= str_to_lower(BELIEVE),
believe_numerical = as.numeric(ordered(BELIEVE, levels = believe_levels)),
IMPT= str_to_lower(IMPT),
impt_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
INTEREST = str_to_lower(INTEREST),
INTEREST = str_replace (INTEREST, "uninterested" , "not interested" ),
interest_numerical = as.numeric(ordered(IMPT, levels = importance_levels)),
FAMILIAR = str_to_lower (FAMILIAR),
familiar_numerical = as.numeric(ordered(FAMILIAR, levels = familiar_levels)),
NOVEL = str_to_lower(NOVEL),
novel_numerical = as.numeric(ordered(NOVEL, levels = novel_levels)))## Warning: Expected 4 pieces. Missing pieces filled with `NA` in 8520 rows [1, 2, 3, 4, 5,
## 6, 8, 9, 10, 11, 12, 13, 15, 16, 17, 18, 19, 20, 22, 23, ...].## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 780 rows [1, 7, 13, 19,
## 25, 31, 37, 43, 49, 55, 61, 67, 193, 199, 205, 211, 217, 223, 229, 235, ...].combined_df <- rbind(ent_beliveble_vs_sharability_df, pol_beliveble_vs_sharability_df )
#aading the Video_Subject column as political or entertainment
pol_ent_combined_df <- combined_df |> mutate(video_subject= if_else(grepl("P", video), "Political", "Entertrianment"))
share_vs_believe_lm_df <- pol_ent_combined_df |> select(ResponseId, fake, video, believe_numerical, share_numerical, video_subject)
ggplot(share_vs_believe_lm_df, aes(x=believe_numerical, fill= video_subject)) +
geom_bar() +
facet_wrap(~video_subject, nrow=2)
share_vs_believe_lm1 = lm (share_numerical~believe_numerical+ fake + video + video_subject, data=share_vs_believe_lm_df)
summary(share_vs_believe_lm1)##
## Call:
## lm(formula = share_numerical ~ believe_numerical + fake + video +
## video_subject, data = share_vs_believe_lm_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3369 -0.6744 -0.4669 0.3819 4.6135
##
## Coefficients: (2 not defined because of singularities)
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.64836 0.17469 9.436 < 2e-16 ***
## believe_numerical -0.03292 0.02759 -1.193 0.23291
## fakeR 0.14410 0.21266 0.678 0.49813
## video11E 0.57733 0.21004 2.749 0.00605 **
## video12E 0.42399 0.21006 2.018 0.04372 *
## video13P 0.47254 0.21163 2.233 0.02570 *
## video14E 0.02843 0.21046 0.135 0.89257
## video15P 0.15730 0.21299 0.739 0.46031
## video16E -0.14847 0.21065 -0.705 0.48105
## video17P -0.07322 0.21159 -0.346 0.72937
## video18P 0.06356 0.20994 0.303 0.76210
## video19P -0.10157 0.21424 -0.474 0.63550
## video1P -0.15363 0.21160 -0.726 0.46793
## video20E -0.09129 0.20993 -0.435 0.66372
## video21P 0.11778 0.21159 0.557 0.57785
## video22E 0.57651 0.21004 2.745 0.00613 **
## video23P -0.29074 0.21161 -1.374 0.16968
## video24E -0.01722 0.21043 -0.082 0.93479
## video2P 0.19061 0.21315 0.894 0.37131
## video3E -0.03754 0.21006 -0.179 0.85817
## video4P -0.15245 0.21163 -0.720 0.47141
## video5P 0.51618 0.21159 2.439 0.01482 *
## video6P 0.49971 0.21241 2.353 0.01877 *
## video7P -0.16114 0.21166 -0.761 0.44659
## video8E -0.09725 0.21104 -0.461 0.64502
## video9E NA NA NA NA
## video_subjectPolitical NA NA NA NA
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.197 on 1511 degrees of freedom
## Multiple R-squared: 0.05311, Adjusted R-squared: 0.03807
## F-statistic: 3.531 on 24 and 1511 DF, p-value: 1.967e-08tab_model(share_vs_believe_lm1)## Model matrix is rank deficient. Parameters `video9E,
## video_subjectPolitical` were not estimable.| share_numerical | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 1.65 | 1.31 – 1.99 | <0.001 |
| believe numerical | -0.03 | -0.09 – 0.02 | 0.233 |
| fake [R] | 0.14 | -0.27 – 0.56 | 0.498 |
| video [11E] | 0.58 | 0.17 – 0.99 | 0.006 |
| video [12E] | 0.42 | 0.01 – 0.84 | 0.044 |
| video [13P] | 0.47 | 0.06 – 0.89 | 0.026 |
| video [14E] | 0.03 | -0.38 – 0.44 | 0.893 |
| video [15P] | 0.16 | -0.26 – 0.58 | 0.460 |
| video [16E] | -0.15 | -0.56 – 0.26 | 0.481 |
| video [17P] | -0.07 | -0.49 – 0.34 | 0.729 |
| video [18P] | 0.06 | -0.35 – 0.48 | 0.762 |
| video [19P] | -0.10 | -0.52 – 0.32 | 0.636 |
| video [1P] | -0.15 | -0.57 – 0.26 | 0.468 |
| video [20E] | -0.09 | -0.50 – 0.32 | 0.664 |
| video [21P] | 0.12 | -0.30 – 0.53 | 0.578 |
| video [22E] | 0.58 | 0.16 – 0.99 | 0.006 |
| video [23P] | -0.29 | -0.71 – 0.12 | 0.170 |
| video [24E] | -0.02 | -0.43 – 0.40 | 0.935 |
| video [2P] | 0.19 | -0.23 – 0.61 | 0.371 |
| video [3E] | -0.04 | -0.45 – 0.37 | 0.858 |
| video [4P] | -0.15 | -0.57 – 0.26 | 0.471 |
| video [5P] | 0.52 | 0.10 – 0.93 | 0.015 |
| video [6P] | 0.50 | 0.08 – 0.92 | 0.019 |
| video [7P] | -0.16 | -0.58 – 0.25 | 0.447 |
| video [8E] | -0.10 | -0.51 – 0.32 | 0.645 |
| Observations | 1536 | ||
| R2 / R2 adjusted | 0.053 / 0.038 | ||
share_vs_believe_lm2 = lm (share_numerical~believe_numerical+ fake , data=share_vs_believe_lm_df)
summary(share_vs_believe_lm2)##
## Call:
## lm(formula = share_numerical ~ believe_numerical + fake, data = share_vs_believe_lm_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8541 -0.7777 -0.6186 0.3050 4.4196
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.77134 0.10678 16.589 <2e-16 ***
## believe_numerical -0.03819 0.02634 -1.450 0.147
## fakeR 0.12096 0.07414 1.631 0.103
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.217 on 1533 degrees of freedom
## Multiple R-squared: 0.006787, Adjusted R-squared: 0.005491
## F-statistic: 5.238 on 2 and 1533 DF, p-value: 0.005408tab_model(share_vs_believe_lm2)| share_numerical | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 1.77 | 1.56 – 1.98 | <0.001 |
| believe numerical | -0.04 | -0.09 – 0.01 | 0.147 |
| fake [R] | 0.12 | -0.02 – 0.27 | 0.103 |
| Observations | 1536 | ||
| R2 / R2 adjusted | 0.007 / 0.005 | ||
share_vs_believe_lm3 = lm (share_numerical~believe_numerical+ video , data=share_vs_believe_lm_df)
summary(share_vs_believe_lm3)##
## Call:
## lm(formula = share_numerical ~ believe_numerical + video, data = share_vs_believe_lm_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -1.3369 -0.6744 -0.4669 0.3819 4.6135
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.648364 0.174691 9.436 < 2e-16 ***
## believe_numerical -0.032920 0.027586 -1.193 0.232906
## video11E 0.721432 0.211681 3.408 0.000671 ***
## video12E 0.423994 0.210055 2.018 0.043717 *
## video13P 0.472540 0.211630 2.233 0.025705 *
## video14E 0.028428 0.210456 0.135 0.892570
## video15P 0.157299 0.212991 0.739 0.460312
## video16E -0.148466 0.210651 -0.705 0.481047
## video17P 0.070882 0.214423 0.331 0.741013
## video18P 0.207663 0.212395 0.978 0.328369
## video19P -0.101569 0.214238 -0.474 0.635501
## video1P -0.009528 0.214566 -0.044 0.964588
## video20E 0.052804 0.212525 0.248 0.803814
## video21P 0.261881 0.214352 1.222 0.221999
## video22E 0.720610 0.213848 3.370 0.000771 ***
## video23P -0.146637 0.213820 -0.686 0.492947
## video24E -0.017220 0.210427 -0.082 0.934791
## video2P 0.190612 0.213145 0.894 0.371313
## video3E 0.106554 0.211627 0.503 0.614686
## video4P -0.152453 0.211634 -0.720 0.471414
## video5P 0.660274 0.214146 3.083 0.002084 **
## video6P 0.499712 0.212415 2.353 0.018774 *
## video7P -0.017040 0.213516 -0.080 0.936401
## video8E -0.097247 0.211044 -0.461 0.645015
## video9E 0.144098 0.212659 0.678 0.498128
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.197 on 1511 degrees of freedom
## Multiple R-squared: 0.05311, Adjusted R-squared: 0.03807
## F-statistic: 3.531 on 24 and 1511 DF, p-value: 1.967e-08tab_model(share_vs_believe_lm3)| share_numerical | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 1.65 | 1.31 – 1.99 | <0.001 |
| believe numerical | -0.03 | -0.09 – 0.02 | 0.233 |
| video [11E] | 0.72 | 0.31 – 1.14 | 0.001 |
| video [12E] | 0.42 | 0.01 – 0.84 | 0.044 |
| video [13P] | 0.47 | 0.06 – 0.89 | 0.026 |
| video [14E] | 0.03 | -0.38 – 0.44 | 0.893 |
| video [15P] | 0.16 | -0.26 – 0.58 | 0.460 |
| video [16E] | -0.15 | -0.56 – 0.26 | 0.481 |
| video [17P] | 0.07 | -0.35 – 0.49 | 0.741 |
| video [18P] | 0.21 | -0.21 – 0.62 | 0.328 |
| video [19P] | -0.10 | -0.52 – 0.32 | 0.636 |
| video [1P] | -0.01 | -0.43 – 0.41 | 0.965 |
| video [20E] | 0.05 | -0.36 – 0.47 | 0.804 |
| video [21P] | 0.26 | -0.16 – 0.68 | 0.222 |
| video [22E] | 0.72 | 0.30 – 1.14 | 0.001 |
| video [23P] | -0.15 | -0.57 – 0.27 | 0.493 |
| video [24E] | -0.02 | -0.43 – 0.40 | 0.935 |
| video [2P] | 0.19 | -0.23 – 0.61 | 0.371 |
| video [3E] | 0.11 | -0.31 – 0.52 | 0.615 |
| video [4P] | -0.15 | -0.57 – 0.26 | 0.471 |
| video [5P] | 0.66 | 0.24 – 1.08 | 0.002 |
| video [6P] | 0.50 | 0.08 – 0.92 | 0.019 |
| video [7P] | -0.02 | -0.44 – 0.40 | 0.936 |
| video [8E] | -0.10 | -0.51 – 0.32 | 0.645 |
| video [9E] | 0.14 | -0.27 – 0.56 | 0.498 |
| Observations | 1536 | ||
| R2 / R2 adjusted | 0.053 / 0.038 | ||
share_vs_believe_lm4 = lm (share_numerical~believe_numerical+ video_subject, data=share_vs_believe_lm_df)
summary(share_vs_believe_lm4)##
## Call:
## lm(formula = share_numerical ~ believe_numerical + video_subject,
## data = share_vs_believe_lm_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.8445 -0.7718 -0.6488 0.2897 4.4127
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.90604 0.07794 24.456 < 2e-16 ***
## believe_numerical -0.06150 0.02210 -2.783 0.00546 **
## video_subjectPolitical -0.01128 0.06236 -0.181 0.85653
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.218 on 1533 degrees of freedom
## Multiple R-squared: 0.005084, Adjusted R-squared: 0.003786
## F-statistic: 3.917 on 2 and 1533 DF, p-value: 0.02011tab_model(share_vs_believe_lm4)| share_numerical | |||
|---|---|---|---|
| Predictors | Estimates | CI | p |
| (Intercept) | 1.91 | 1.75 – 2.06 | <0.001 |
| believe numerical | -0.06 | -0.10 – -0.02 | 0.005 |
| video subject [Political] | -0.01 | -0.13 – 0.11 | 0.857 |
| Observations | 1536 | ||
| R2 / R2 adjusted | 0.005 / 0.004 | ||
Believe behaviors for two video types
ggplot(share_vs_believe_lm_df, aes(x=believe_numerical, fill= video_subject)) +
geom_bar() +
facet_wrap(~video_subject, nrow=2)
#Anova diference between two groups of having political and
entertainment belive status
belive_deepfakes_anova <- aov(believe_numerical~video_subject, data= share_vs_believe_lm_df)
summary(belive_deepfakes_anova)## Df Sum Sq Mean Sq F value Pr(>F)
## video_subject 1 5.6 5.633 2.845 0.0918 .
## Residuals 1534 3037.1 1.980
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1tab_model(belive_deepfakes_anova)| believe_numerical | |
|---|---|
| Predictors | p |
| video_subject | 0.092 |
| Residuals | |
| Observations | 1536 |
| R2 / R2 adjusted | 0.002 / 0.001 |
ggplot(share_vs_believe_lm_df, aes(video_subject,believe_numerical, fill= video_subject)) +
stat_summary(
fun.data = mean_cl_boot,
geom = "pointrange",
shape = 21,
fill = "white"
)
t.test(believe_numerical ~ video_subject, data = share_vs_believe_lm_df , var.equal = TRUE)##
## Two Sample t-test
##
## data: believe_numerical by video_subject
## t = -1.6868, df = 1534, p-value = 0.09184
## alternative hypothesis: true difference in means between group Entertrianment and group Political is not equal to 0
## 95 percent confidence interval:
## -0.26258990 0.01977157
## sample estimates:
## mean in group Entertrianment mean in group Political
## 2.861538 2.982948#t.test(believe_numerical ~ share_numerical, video_subject, data = pol_ent_combined_df , var.equal = TRUE)
believe_t_test_results <- nice_t_test(data = share_vs_believe_lm_df,
response = "believe_numerical",
group = "video_subject",
warning = FALSE)
believe_t_test_results## Dependent Variable t df p d CI_lower
## 1 believe_numerical -1.689773 1514.636 0.09127719 -0.08628552 -0.186576
## CI_upper
## 1 0.014033believe_t_test_table <- nice_table(believe_t_test_results)
believe_t_test_tableDependent Variable | t | df | p | d | 95% CI |
|---|---|---|---|---|---|
believe_numerical | -1.69 | 1,514.64 | .091 | -0.09 | [-0.19, 0.01] |
# Believeability and sharebility difference in both groups Ent and Political
all_t_test_results <- nice_t_test(data = pol_ent_combined_df,
response = names(pol_ent_combined_df)[11:16],
group = "video_subject",
warning = FALSE)
all_t_test_results## Dependent Variable t df p d CI_lower
## 1 share_numerical 0.298313 1458.335 7.655068e-01 0.01535485 -0.084907136
## 2 believe_numerical -1.689773 1514.636 9.127719e-02 -0.08628552 -0.186575961
## 3 impt_numerical -12.252968 1523.432 5.468686e-33 -0.62439667 -0.726962658
## 4 interest_numerical -12.252968 1523.432 5.468686e-33 -0.62439667 -0.726962658
## 5 familiar_numerical -3.224132 1489.584 1.290932e-03 -0.16531622 -0.265717858
## 6 novel_numerical 2.018744 1458.294 4.369654e-02 0.10390986 0.003567536
## CI_upper
## 1 0.11561182
## 2 0.01403300
## 3 -0.52163610
## 4 -0.52163610
## 5 -0.06486087
## 6 0.20421835all_t_test_table <- nice_table(all_t_test_results)
all_t_test_tableDependent Variable | t | df | p | d | 95% CI |
|---|---|---|---|---|---|
share_numerical | 0.30 | 1,458.33 | .766 | 0.02 | [-0.08, 0.12] |
believe_numerical | -1.69 | 1,514.64 | .091 | -0.09 | [-0.19, 0.01] |
impt_numerical | -12.25 | 1,523.43 | < .001 | -0.62 | [-0.73, -0.52] |
interest_numerical | -12.25 | 1,523.43 | < .001 | -0.62 | [-0.73, -0.52] |
familiar_numerical | -3.22 | 1,489.58 | .001 | -0.17 | [-0.27, -0.06] |
novel_numerical | 2.02 | 1,458.29 | .044 | 0.10 | [0.00, 0.20] |
ggplot(pol_ent_combined_df,aes(x=video_subject, y=share_numerical, color=video_subject)) +
geom_boxplot(width=0.5,lwd=1)+
labs(subtitle="Sharing diferences in the Treatment groups based on the Subject of video")
ggplot(pol_ent_combined_df,aes(x=video_subject, y=interest_numerical, color=video_subject)) +
geom_boxplot(width=0.5,lwd=1)+
labs(subtitle="Video interest in the Treatment groups based on the Subject of video")
ggplot(pol_ent_combined_df,aes(x=video_subject, y=familiar_numerical, color=video_subject)) +
geom_boxplot(width=0.5,lwd=1)+
labs(subtitle="Video familiarity diferences in the Treatment groups based on the Subject of video")
##understanding the likelihood of believing and the truth (discernment)
#understanding the likelihood of believing and the truth (discernment)
#Those who could not detect deepfakes
could_not_identify_DF1<- pol_ent_combined_df |> filter (fake == "DF", believe_numerical == 1)
could_not_identify_DF2<- pol_ent_combined_df |> filter (fake == "DF", believe_numerical == 2)
wrong_beleive_DF<-rbind(could_not_identify_DF1,could_not_identify_DF2) |> mutate (detect="DF_Wrong") #192
#Those who could not detect real
could_not_identify_R1<- pol_ent_combined_df |> filter (fake == "R", believe_numerical == 4)
could_not_identify_R2<- pol_ent_combined_df |> filter (fake == "R", believe_numerical == 5)
wrong_beleive_R<-rbind(could_not_identify_R1,could_not_identify_R2) |> mutate (detect="R_Wrong") #115
#Those who were uncertain of deepfakes or real
uncertain_to_belive_DF<- pol_ent_combined_df |> filter (fake == "DF", believe_numerical == 3)
uncertain_to_belive_F<- pol_ent_combined_df |> filter (fake == "R", believe_numerical == 3)
uncertain_DF_or_R<-rbind(uncertain_to_belive_DF,uncertain_to_belive_F) |> mutate (detect="R_DF_Uncertain") #201
#Those who got it right to detect deepfakes
identified_correctly_DF1<-pol_ent_combined_df |> filter (fake == "DF", believe_numerical == 4)
identified_correctly_DF2<-pol_ent_combined_df |> filter (fake == "DF", believe_numerical == 5)
correct_belive_DF<-rbind(identified_correctly_DF1,identified_correctly_DF2) |> mutate (detect="DF_Right") #491
#Those who got it right to detect real videos
identified_correctly_R1<-pol_ent_combined_df |> filter (fake == "R", believe_numerical == 1)
identified_correctly_R2<-pol_ent_combined_df |> filter (fake == "R", believe_numerical == 2)
correct_belive_R<-rbind(identified_correctly_R1,identified_correctly_R2)|> mutate (detect="R_Right") #557
#Those who detect DF and R right
correct_R_DF <-rbind(correct_belive_DF,correct_belive_R)
#All of the belives combined to table
All_believes <-rbind(correct_belive_R,
correct_belive_DF,
wrong_beleive_R,
wrong_beleive_DF,
uncertain_DF_or_R)
ggplot(All_believes, aes(x=detect, fill= detect)) +
geom_bar() 
ggplot(All_believes, aes(x=detect, fill= detect)) +
geom_bar() +
facet_wrap(~video_subject, nrow=2)
ggplot(All_believes, aes(x=detect, fill= detect)) +
geom_bar() +
facet_wrap(~video_subject, nrow=2)
ggplot(All_believes,aes(x=detect, y=share_numerical, color=detect)) +
geom_boxplot(width=0.5,lwd=1)+
labs(subtitle="Sharing diferences in the Treatment groups based on the Subject of video")
Mediation analysis between sharing intention and beliveing in Entertainment videos
Is there a mediation effect of believing for sharing intention for Deepfakes and Real videos of Entertainment
#Entertainment dataset (treatment) with belive score and share score
#view (ent_beliveble_vs_sharability_df )
head (ent_beliveble_vs_sharability_df)## # A tibble: 6 × 16
## ResponseId fake video condition SHARE BELIEVE IMPT NOVEL INTEREST FAMILIAR
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 R_3Jh3kj1y3… R 3E Treatment very… unlike… impo… not … not int… very fa…
## 2 R_3Jh3kj1y3… R 9E Treatment slig… very u… impo… neit… interes… familiar
## 3 R_3Jh3kj1y3… R 11E Treatment mode… unlike… impo… neit… not int… familiar
## 4 R_3Jh3kj1y3… R 18P Treatment very… neithe… neit… not … not at … not at …
## 5 R_3Jh3kj1y3… R 20E Treatment slig… very u… impo… neit… interes… very fa…
## 6 R_3Jh3kj1y3… R 22E Treatment very… unlike… impo… not … not int… familiar
## # ℹ 6 more variables: share_numerical <dbl>, believe_numerical <dbl>,
## # impt_numerical <dbl>, interest_numerical <dbl>, familiar_numerical <dbl>,
## # novel_numerical <dbl>Mediation_df<-ent_beliveble_vs_sharability_df |>
select (fake,video, share_numerical, believe_numerical)
head (Mediation_df)## # A tibble: 6 × 4
## fake video share_numerical believe_numerical
## <chr> <chr> <dbl> <dbl>
## 1 R 3E 1 2
## 2 R 9E 4 1
## 3 R 11E 2 2
## 4 R 18P 1 3
## 5 R 20E 3 1
## 6 R 22E 1 2Step 1- the total effect
#dependant variable is sharing intention independant is the categorical variable fake (R or DF)
video_type_effect<-lm(share_numerical~fake,Mediation_df)
summary(video_type_effect)##
## Call:
## lm(formula = share_numerical ~ fake, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.9026 -0.9026 -0.5667 0.4333 4.4333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.56667 0.06377 24.566 < 2e-16 ***
## fakeR 0.33590 0.09019 3.724 0.00021 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.259 on 778 degrees of freedom
## Multiple R-squared: 0.01752, Adjusted R-squared: 0.01625
## F-statistic: 13.87 on 1 and 778 DF, p-value: 0.00021The result of predictor is very significant to the dependant variable. Which means there is a significant change in the change of R to DF makes to the sharing intention. The coefficiant is
Step 2- The effect of the IV onto the mediator.
#Mediator is the dependant variable and IV is our Real or DF video
mediator_effect <-lm(believe_numerical~fake, Mediation_df)
summary(mediator_effect)##
## Call:
## lm(formula = believe_numerical ~ fake, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4410 -1.1667 -0.1667 0.8333 2.8333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.44103 0.06221 55.31 <2e-16 ***
## fakeR -1.27436 0.08798 -14.48 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.229 on 778 degrees of freedom
## Multiple R-squared: 0.2124, Adjusted R-squared: 0.2114
## F-statistic: 209.8 on 1 and 778 DF, p-value: < 2.2e-16Step 3 The effect of the mediator on the dependent variable
sharaing_effect=lm(share_numerical~fake+believe_numerical,Mediation_df)
summary(sharaing_effect)##
## Call:
## lm(formula = share_numerical ~ fake + believe_numerical, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.9583 -0.8269 -0.5399 0.3645 4.5079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.73115 0.14157 12.228 < 2e-16 ***
## fakeR 0.27498 0.10158 2.707 0.00694 **
## believe_numerical -0.04780 0.03674 -1.301 0.19358
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.259 on 777 degrees of freedom
## Multiple R-squared: 0.01965, Adjusted R-squared: 0.01713
## F-statistic: 7.788 on 2 and 777 DF, p-value: 0.0004479Conclusion
This concludes that the believing nudge as a mediator is not significant. So -0.04780 coefficient is not supporting the effect of sharing behaviors.
Mediation analysis between sharing intention and beliveing in Political videos
Is there a mediation effect of believing for sharing intention for Deepfakes and Real videos of Political
#Entertainment dataset (treatment) with belive score and share score
#view (ent_beliveble_vs_sharability_df )
head (pol_beliveble_vs_sharability_df)## # A tibble: 6 × 16
## ResponseId fake video condition SHARE BELIEVE IMPT NOVEL INTEREST FAMILIAR
## <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr> <chr>
## 1 R_oXNZs9xxI… R 1P Treatment very… neithe… impo… not … neither… very fa…
## 2 R_oXNZs9xxI… R 5P Treatment very… very u… very… not … not int… very fa…
## 3 R_oXNZs9xxI… R 7P Treatment very… very u… very… not … neither… very fa…
## 4 R_oXNZs9xxI… R 17P Treatment mode… unlike… impo… not … interes… not fam…
## 5 R_oXNZs9xxI… R 21P Treatment mode… very u… very… neit… interes… very fa…
## 6 R_oXNZs9xxI… R 23P Treatment very… unlike… impo… not … not int… very fa…
## # ℹ 6 more variables: share_numerical <dbl>, believe_numerical <dbl>,
## # impt_numerical <dbl>, interest_numerical <dbl>, familiar_numerical <dbl>,
## # novel_numerical <dbl>Pol_mediation_df<-pol_beliveble_vs_sharability_df |>
dplyr::select (fake,video, share_numerical, believe_numerical)
head (Pol_mediation_df)## # A tibble: 6 × 4
## fake video share_numerical believe_numerical
## <chr> <chr> <dbl> <dbl>
## 1 R 1P 1 3
## 2 R 5P 1 1
## 3 R 7P 1 1
## 4 R 17P 2 2
## 5 R 21P 2 1
## 6 R 23P 1 2Step 1- the total effect
pol_video_type_effect<-lm(share_numerical~fake,Mediation_df)
summary(pol_video_type_effect)##
## Call:
## lm(formula = share_numerical ~ fake, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.9026 -0.9026 -0.5667 0.4333 4.4333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.56667 0.06377 24.566 < 2e-16 ***
## fakeR 0.33590 0.09019 3.724 0.00021 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.259 on 778 degrees of freedom
## Multiple R-squared: 0.01752, Adjusted R-squared: 0.01625
## F-statistic: 13.87 on 1 and 778 DF, p-value: 0.00021Step 2- The effect of the IV onto the mediator
pol_mediator_effect <-lm(believe_numerical~fake, Mediation_df)
summary(pol_mediator_effect)##
## Call:
## lm(formula = believe_numerical ~ fake, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -2.4410 -1.1667 -0.1667 0.8333 2.8333
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 3.44103 0.06221 55.31 <2e-16 ***
## fakeR -1.27436 0.08798 -14.48 <2e-16 ***
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.229 on 778 degrees of freedom
## Multiple R-squared: 0.2124, Adjusted R-squared: 0.2114
## F-statistic: 209.8 on 1 and 778 DF, p-value: < 2.2e-16Step 3 The effect of the mediator on the dependent variable
pol_sharaing_effect=lm(share_numerical~fake+believe_numerical,Mediation_df)
summary(pol_sharaing_effect)##
## Call:
## lm(formula = share_numerical ~ fake + believe_numerical, data = Mediation_df)
##
## Residuals:
## Min 1Q Median 3Q Max
## -0.9583 -0.8269 -0.5399 0.3645 4.5079
##
## Coefficients:
## Estimate Std. Error t value Pr(>|t|)
## (Intercept) 1.73115 0.14157 12.228 < 2e-16 ***
## fakeR 0.27498 0.10158 2.707 0.00694 **
## believe_numerical -0.04780 0.03674 -1.301 0.19358
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
##
## Residual standard error: 1.259 on 777 degrees of freedom
## Multiple R-squared: 0.01965, Adjusted R-squared: 0.01713
## F-statistic: 7.788 on 2 and 777 DF, p-value: 0.0004479