save_CAMs_as_pictures = FALSE
# consider_Protocol = FALSE # not needed at current stageData Preperation
Background Information
This is an R Markdown document. Instructions for writing these documents and background information can be found in the book written by Xie, Allaire, and Grolemund (2018) When you execute code within the document, the results appear beneath the code. This is an R Markdown document. Instructions for writing these documents and background information can be found in the book written by Xie, Allaire, and Grolemund (2018) When you execute code within the document, the results appear beneath the code. This file contains summary statistics, respectively the analysis step (confirmatory and exploratory analyses). Files are split into multiple subfiles like data processing and data analyses steps, which follows the classical data-analysis pipeline (see Peng and Matsui 2016; Wickham and Grolemund 2017).
Global variables
create raw data files
# sets the directory of location of this script as the current directory
# setwd(dirname(rstudioapi::getSourceEditorContext()$path))
### load packages
require(pacman)
p_load('tidyverse', 'jsonlite', 'magrittr',
'stargazer', 'psych', 'jtools', 'DT', 'igraph',
'writexl')
### load socio-demographic data
setwd("data_demographic")
prolific1 <- read.csv(file = "prolific_export_682f1c80a267ba868f8a1af8.csv", header = TRUE)
prolific2 <- read.csv(file = "prolific_export_68261e4765055a12fd0d2dd9.csv", header = TRUE)
prolific <- rbind(prolific1, prolific2)
### list data files
setwd("../data")
folders <- list.files(pattern = "^study_result.*")
### create data files - GERMANY
# get CAM data
writeLines("", "CAMdata.txt") # create file
text_connection <- file("CAMdata.txt", "a") # open connection to append
# get CAM data second
writeLines("", "secondCAMdata.txt") # create file
text_connection_second <- file("secondCAMdata.txt", "a") # open connection to append
# get pre CAM data
writeLines("", "preCAM.txt") # create file
text_connection_pre <- file("preCAM.txt", "a") # open connection to append
# get post CAM data
writeLines("", "postCAM.txt") # create file
text_connection_post <- file("postCAM.txt", "a") # open connection to append
# get post second CAM data
writeLines("", "secondPostCAM.txt") # create file
text_connection_postSecond <- file("secondPostCAM.txt", "a") # open connection to append
for(i in 1:length(folders)){
setwd(folders[i])
if(length(dir()) == 5){
# print(i)
# pre CAM data
setwd(dir()[1])
tmp <- jsonlite::fromJSON(txt = "data.txt")
tmp_id <- tmp$ID[!is.na(tmp$ID)]
writeLines(jsonlite::toJSON(x = tmp), text_connection_pre)
setwd("..")
# CAM data
setwd(dir()[2])
tmp <- jsonlite::fromJSON(txt = "data.txt")
if(tmp$creator != tmp_id){
warning("IDs (primary keys) not matching")
}
writeLines(jsonlite::toJSON(x = tmp), text_connection)
setwd("..")
# post CAM data
setwd(dir()[3])
tmp <- jsonlite::fromJSON(txt = "data.txt")
tmp$ID <- NA
tmp$ID[2] <- tmp_id
writeLines(jsonlite::toJSON(x = tmp), text_connection_post)
setwd("..")
# CAM data second
setwd(dir()[4])
tmp <- jsonlite::fromJSON(txt = "data.txt")
if(tmp$creator != tmp_id){
warning("IDs (primary keys) not matching")
}
# tmp$creator <- paste0(tmp$creator, "_t2")
writeLines(jsonlite::toJSON(x = tmp), text_connection_second)
setwd("..")
# post CAM data second
setwd(dir()[5])
tmp <- jsonlite::fromJSON(txt = "data.txt")
tmp$ID <- NA
tmp$ID[2] <- tmp_id
writeLines(jsonlite::toJSON(x = tmp), text_connection_postSecond)
setwd("..")
}
setwd("..")
}
close(text_connection) # close connection CAM
close(text_connection_pre) # close connection
close(text_connection_post) # close connection
close(text_connection_second) # close connection CAM
close(text_connection_postSecond) # close connection
### move files to output folder
# copy files (not overwritten)
tmp_file_from <- getwd()
setwd("../outputs")
file.copy(from = paste0(tmp_file_from, "/CAMdata.txt"), to = paste0(getwd(), "/CAMdata.txt"))[1] FALSEfile.copy(from = paste0(tmp_file_from, "/preCAM.txt"), to = paste0(getwd(), "/preCAM.txt"))[1] FALSEfile.copy(from = paste0(tmp_file_from, "/postCAM.txt"), to = paste0(getwd(), "/postCAM.txt"))[1] FALSEfile.copy(from = paste0(tmp_file_from, "/secondPostCAM.txt"), to = paste0(getwd(), "/secondPostCAM.txt"))[1] FALSEfile.copy(from = paste0(tmp_file_from, "/secondCAMdata.txt"), to = paste0(getwd(), "/secondCAMdata.txt"))[1] FALSE# remove files
file.remove(paste0(tmp_file_from, "/CAMdata.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/preCAM.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/postCAM.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/secondPostCAM.txt"))[1] TRUEfile.remove(paste0(tmp_file_from, "/secondCAMdata.txt"))[1] TRUE### load functions
# print(getwd())
setwd("../functions")
for(i in 1:length(dir())){
# print(dir()[i])
source(dir()[i], encoding = "utf-8")
}
setwd("../functions_CAMapp")
for(i in 1:length(dir())){
# print(dir()[i])
source(dir()[i], encoding = "utf-8")
}
rm(i)
### summary function
data_summary <- function(data, varname, groupnames){
require(plyr)
summary_func <- function(x, col){
c(mean = mean(x[[col]], na.rm=TRUE),
se = sd(x[[col]], na.rm=TRUE) / sqrt(length(x[[col]])))
}
data_sum<-ddply(data, groupnames, .fun=summary_func,
varname)
data_sum <- plyr::rename(data_sum, c("mean" = varname))
return(data_sum)
}
rm(tmp); rm(tmp_id); rm(folders); rm(tmp_file_from)
rm(prolific1); rm(prolific2)
rm(text_connection); rm(text_connection_post); rm(text_connection_postSecond); rm(text_connection_pre); rm(text_connection_second)merge CAM data sets
setwd("outputs")
# Read the contents of both files
cam_content <- readLines("CAMdata.txt")
second_cam_content <- readLines("secondCAMdata.txt")
# Create a new file and write combined contents
writeLines(c(cam_content, second_cam_content), "mergedCAMdata.txt")
rm(cam_content)
rm(second_cam_content)set up data.frame questionnaires
load data:
setwd("outputs")
# > pre study
suppressMessages(read_file('preCAM.txt') %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
# ... filter empty rows ...
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... parse JSON into a data.frame
map_dfr(fromJSON, flatten=TRUE)) -> dat_preCAM
# > post first CAM
suppressMessages(read_file('postCAM.txt') %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
# ... filter empty rows ...
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... parse JSON into a data.frame
map_dfr(fromJSON, flatten=TRUE)) -> dat_postCAM
# > post second CAM
suppressMessages(read_file('secondPostCAM.txt') %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
# ... filter empty rows ...
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... parse JSON into a data.frame
map_dfr(fromJSON, flatten=TRUE)) -> dat_secondPostCAMrename ID variable for data sets:
colnames(dat_preCAM)[colnames(dat_preCAM) == "ID"] <- "PROLIFIC_PID"
colnames(dat_postCAM)[colnames(dat_postCAM) == "ID"] <- "PROLIFIC_PID"
colnames(dat_secondPostCAM)[colnames(dat_secondPostCAM) == "ID"] <- "PROLIFIC_PID"add unique ID variable to match rows to participants, only keep complete data sets:
### create counter variable for both data sets
# pre study
dat_preCAM$ID <- NA
tmp_IDcounter <- 0
for(i in 1:nrow(dat_preCAM)){
if(!is.na(dat_preCAM$sender[i]) && dat_preCAM$sender[i] == "Greetings"){
# tmp <- dat_preCAM$prolific_pid[i]
tmp_IDcounter = tmp_IDcounter + 1
}
dat_preCAM$ID[i] <- tmp_IDcounter
}
# post study
dat_postCAM$ID <- NA
tmp_IDcounter <- 0
for(i in 1:nrow(dat_postCAM)){
if(!is.na(dat_postCAM$sender[i]) && dat_postCAM$sender[i] == "CAMfeedbackGeneral"){
# tmp <- dat_postCAM$prolific_pid[i]
tmp_IDcounter = tmp_IDcounter + 1
}
dat_postCAM$ID[i] <- tmp_IDcounter
}
# second post study
#> fix error in "sender variable"
for(i in 1:nrow(dat_secondPostCAM)){
if(is.na(dat_secondPostCAM$sender[i])){
if(!is.na(dat_secondPostCAM$sender[i+1])){
dat_secondPostCAM$sender[i] <- "adaptiveQuestion_Feedback"
}
}
}
dat_secondPostCAM$ID <- NA
tmp_IDcounter <- 0
for(i in 1:nrow(dat_secondPostCAM)){
if(!is.na(dat_secondPostCAM$sender[i]) && dat_secondPostCAM$sender[i] == "break500ms_2"){
# tmp <- dat_secondPostCAM$prolific_pid[i]
tmp_IDcounter = tmp_IDcounter + 1
}
dat_secondPostCAM$ID[i] <- tmp_IDcounter
}
### keep only complete data sets
# pre-study
# sort(table(dat_preCAM$ID))
sum(table(dat_preCAM$ID) != max(table(dat_preCAM$ID)))[1] 0sum(table(dat_preCAM$ID) == max(table(dat_preCAM$ID)))[1] 21dat_preCAM <- dat_preCAM[dat_preCAM$ID %in% names(table(dat_preCAM$ID))[table(dat_preCAM$ID) == max(table(dat_preCAM$ID))],]
# post-study
# sort(table(dat_postCAM$ID))
sum(table(dat_postCAM$ID) != max(table(dat_postCAM$ID)))[1] 2sum(table(dat_postCAM$ID) == max(table(dat_postCAM$ID)))[1] 20# dat_postCAM <- dat_postCAM[dat_postCAM$ID %in% names(table(dat_postCAM$ID))[table(dat_postCAM$ID) == max(table(dat_postCAM$ID))],]
dat_postCAM <- dat_postCAM[dat_postCAM$ID %in% names(table(dat_postCAM$ID))[table(dat_postCAM$ID) >= 4],]
# post-study second
# sort(table(dat_secondPostCAM$ID))
sum(table(dat_secondPostCAM$ID) != max(table(dat_secondPostCAM$ID)))[1] 0sum(table(dat_secondPostCAM$ID) == max(table(dat_secondPostCAM$ID)))[1] 21# dat_secondPostCAM <- dat_secondPostCAM[dat_secondPostCAM$ID %in% names(table(dat_secondPostCAM$ID))[table(dat_secondPostCAM$ID) == max(table(dat_secondPostCAM$ID))],]
dat_secondPostCAM <- dat_secondPostCAM[dat_secondPostCAM$ID %in% names(table(dat_secondPostCAM$ID))[table(dat_secondPostCAM$ID) >= 11],]
all(unique(dat_preCAM$ID) %in% unique(dat_postCAM$ID))[1] TRUEall(unique(dat_preCAM$ID) %in% unique(dat_secondPostCAM$ID))[1] TRUEquestionnaire pre-study (component 1)
colnames(dat_preCAM) [1] "sender" "sender_type"
[3] "sender_id" "6"
[5] "ended_on" "duration"
[7] "time_run" "time_render"
[9] "time_show" "time_end"
[11] "time_commit" "timestamp"
[13] "time_switch" "currentLocation"
[15] "choosenManipulationCheck" "IDtype"
[17] "PROLIFIC_PID" "para_countShowRights"
[19] "dummy_informedconsent" "commCheck"
[21] "sociodemo_age" "sociodemo_gender"
[23] "sociodemo_transport_mode" "sociodemo_transport_mode_other"
[25] "sociodemo_net_income" "meta.labjs_version"
[27] "meta.location" "meta.userAgent"
[29] "meta.platform" "meta.language"
[31] "meta.locale" "meta.timeZone"
[33] "meta.timezoneOffset" "meta.screen_width"
[35] "meta.screen_height" "meta.scroll_width"
[37] "meta.scroll_height" "meta.window_innerWidth"
[39] "meta.window_innerHeight" "meta.devicePixelRatio"
[41] "meta.labjs_build.flavor" "meta.labjs_build.commit"
[43] "para_defocuscount" "7"
[45] "ID" tmp_notNumeric <- str_subset(string = colnames(dat_preCAM), pattern = "^meta|^R")
tmp_notNumeric <- str_subset(string = tmp_notNumeric, pattern = "labjs|location", negate = TRUE)
vec_ques <- c("PROLIFIC_PID",
"currentLocation", "IDtype",
"choosenManipulationCheck",
"para_countShowRights",
"dummy_informedconsent",
"commCheck",
"sociodemo_age", "sociodemo_gender", "sociodemo_transport_mode", "sociodemo_transport_mode_other", "sociodemo_net_income",
tmp_notNumeric)
vec_notNumeric = c("PROLIFIC_PID", "currentLocation", "IDtype", "choosenManipulationCheck",
"sociodemo_gender", "sociodemo_transport_mode", "sociodemo_transport_mode_other", "sociodemo_net_income", tmp_notNumeric)
questionnaire_c1 <- questionnairetype(dataset = dat_preCAM,
listvars = vec_ques,
notNumeric = vec_notNumeric, verbose = FALSE)
questionnaire_c1$sociodemo_gender <- factor(questionnaire_c1$sociodemo_gender)
questionnaire_c1$sociodemo_net_income <- factor(questionnaire_c1$sociodemo_net_income)
questionnaire_c1$sociodemo_transport_mode <- factor(questionnaire_c1$sociodemo_transport_mode)
dim(questionnaire_c1)[1] 21 26colnames(questionnaire_c1) [1] "ID" "PROLIFIC_PID"
[3] "currentLocation" "IDtype"
[5] "choosenManipulationCheck" "para_countShowRights"
[7] "dummy_informedconsent" "commCheck"
[9] "sociodemo_age" "sociodemo_gender"
[11] "sociodemo_transport_mode" "sociodemo_transport_mode_other"
[13] "sociodemo_net_income" "meta.userAgent"
[15] "meta.platform" "meta.language"
[17] "meta.locale" "meta.timeZone"
[19] "meta.timezoneOffset" "meta.screen_width"
[21] "meta.screen_height" "meta.scroll_width"
[23] "meta.scroll_height" "meta.window_innerWidth"
[25] "meta.window_innerHeight" "meta.devicePixelRatio" questionnaire post-CAM (component 3)
colnames(dat_postCAM) [1] "sender" "sender_type"
[3] "sender_id" "ended_on"
[5] "duration" "time_run"
[7] "time_render" "time_show"
[9] "time_end" "time_commit"
[11] "timestamp" "time_switch"
[13] "feedCAM_repres" "feedCAM_technicalprobs"
[15] "feedCAM_technicalprobsText" "feedCAM_already"
[17] "feedCAM_alreadyText" "18"
[19] "PROLIFIC_PID" "law_positive_negative"
[21] "law_fairness" "law_effectiveness"
[23] "law_acceptability" "law_petition"
[25] "law_demonstration" "law_demonstration_against"
[27] "scenario_thoughts" "para_countShowScenario"
[29] "para_defocuscount" "19"
[31] "ID" vec_ques <- c("PROLIFIC_PID",
"feedCAM_repres",
"feedCAM_technicalprobs", "feedCAM_technicalprobsText",
"feedCAM_already", "feedCAM_alreadyText",
"scenario_thoughts", "para_countShowScenario")
vec_notNumeric = c("PROLIFIC_PID",
"feedCAM_technicalprobsText", "feedCAM_alreadyText", "scenario_thoughts")
questionnaire_c3 <- questionnairetype(dataset = dat_postCAM,
listvars = vec_ques,
notNumeric = vec_notNumeric, verbose = FALSE)
dim(questionnaire_c3)[1] 21 9colnames(questionnaire_c3)[1] "ID" "PROLIFIC_PID"
[3] "feedCAM_repres" "feedCAM_technicalprobs"
[5] "feedCAM_technicalprobsText" "feedCAM_already"
[7] "feedCAM_alreadyText" "scenario_thoughts"
[9] "para_countShowScenario" questionnaire post-second-CAM (component 5):
colnames(dat_secondPostCAM) [1] "sender" "sender_type"
[3] "sender_id" "ended_on"
[5] "duration" "time_run"
[7] "time_render" "time_show"
[9] "time_end" "time_commit"
[11] "timestamp" "time_switch"
[13] "changeCAM_valence" "14"
[15] "PROLIFIC_PID" "law_positive_negative"
[17] "law_fairness" "law_effectiveness"
[19] "law_acceptability" "law_petition"
[21] "law_demonstration" "law_demonstration_against"
[23] "ease_mindmap" "ease_scenario"
[25] "guttman-item" "not_needed"
[27] "guttman-response" "feedback_critic"
[29] "ID" vec_ques <- c("PROLIFIC_PID",
"changeCAM_valence",
"ease_mindmap", "ease_scenario", "feedback_critic")
vec_notNumeric = c("PROLIFIC_PID",
"changeCAM_valence",
"feedback_critic")
questionnaire_c5 <- questionnairetype(dataset = dat_secondPostCAM,
listvars = vec_ques,
notNumeric = vec_notNumeric, verbose = FALSE)
dim(questionnaire_c5)[1] 21 6colnames(questionnaire_c5)[1] "ID" "PROLIFIC_PID" "changeCAM_valence"
[4] "ease_mindmap" "ease_scenario" "feedback_critic" get ratings of law and guttman
# Pre-define the column names with rat_ pattern
law_cols <- sort(str_subset(string = colnames(dat_postCAM), pattern = "^law"))
guttman_cols <- sort(str_subset(string = colnames(dat_secondPostCAM), pattern = "^guttman"))
# to merge data sets
for(i in 1:length(guttman_cols)){
dat_postCAM[[guttman_cols[i]]] <- NA
}
# Create an empty list to store processed data
result_list <- list()
dat_merged <- rbind(dat_postCAM[, c("ID", "PROLIFIC_PID", "sender", law_cols, guttman_cols)], dat_secondPostCAM[, c("ID", "PROLIFIC_PID", "sender", law_cols, guttman_cols)])
# Loop over each unique ID
for (i in unique(dat_merged$ID)) {
tmp <- dat_merged[dat_merged$ID == i, c("PROLIFIC_PID", "sender", law_cols, guttman_cols)]
# Fill down PROLIFIC_PID if missing
tmp <- tmp %>%
fill(PROLIFIC_PID, .direction = "downup")
# Filter rows where all rat_ columns are not NA
tmp <- tmp %>%
filter(
if_any(all_of(law_cols), ~ !is.na(.)) | # at least one law_* value present OR
if_any(all_of(guttman_cols), ~ !is.na(.)) # at least one guttman_* value present
)
tmp$sender[is.na(tmp$sender)] <- paste0("GI_", tmp$`guttman-item`[!is.na(tmp$`guttman-item`)])
# Append to result list
result_list[[as.character(i)]] <- tmp
}
# Combine all into one dataframe
questionnaire_rating_long <- bind_rows(result_list)
questionnaire_rating_long$sender <- factor(questionnaire_rating_long$sender)
questionnaire_rating_long <- questionnaire_rating_long %>%
mutate(across(starts_with("law_"), as.numeric))
questionnaire_rating_long$law_mean <- rowMeans(x = questionnaire_rating_long[, str_subset(string = colnames(questionnaire_rating_long), pattern = "^law_")])
questionnaire_rating_long$naming <- NA
questionnaire_rating_long$naming[questionnaire_rating_long$sender == "policyRating_I"] <- "I"
questionnaire_rating_long$naming[questionnaire_rating_long$sender == "policyRating_I_Manipulation"] <- "Ib"
questionnaire_rating_long$naming[questionnaire_rating_long$sender == "policyRating_II"] <- "II"
# wide data set for law ratings
questionnaire_rating_wide_law <- questionnaire_rating_long[!is.na(questionnaire_rating_long$naming),] %>%
pivot_wider(
id_cols = c(PROLIFIC_PID, PROLIFIC_PID),
names_from = naming,
values_from = c(law_acceptability, law_demonstration, law_demonstration_against, law_effectiveness, law_fairness, law_petition, law_mean),
names_glue = "{.value}_{naming}"
)
# wide data set for guttman ratings
colnames(questionnaire_rating_long)[colnames(questionnaire_rating_long) == "guttman-item"] <- "item"
colnames(questionnaire_rating_long)[colnames(questionnaire_rating_long) == "guttman-response"] <- "response"
questionnaire_rating_wide_guttman <- questionnaire_rating_long[is.na(questionnaire_rating_long$naming),] %>%
pivot_wider(
id_cols = c(PROLIFIC_PID, PROLIFIC_PID),
names_from = item ,
values_from = c(response),
names_glue = "{.value}_{item }"
)merge all data sets
# Start with the first dataset
merged_data <- questionnaire_c1
# Left join the others one by one
merged_data <- merged_data %>%
left_join(questionnaire_c3, by = "PROLIFIC_PID") %>%
left_join(questionnaire_c5, by = "PROLIFIC_PID") %>%
left_join(questionnaire_rating_wide_law, by = "PROLIFIC_PID") %>%
left_join(questionnaire_rating_wide_guttman, by = "PROLIFIC_PID")
merged_data$ID.x <- NULL
merged_data$ID.y <- NULL
dim(merged_data)[1] 21 62colnames(merged_data) [1] "PROLIFIC_PID" "currentLocation"
[3] "IDtype" "choosenManipulationCheck"
[5] "para_countShowRights" "dummy_informedconsent"
[7] "commCheck" "sociodemo_age"
[9] "sociodemo_gender" "sociodemo_transport_mode"
[11] "sociodemo_transport_mode_other" "sociodemo_net_income"
[13] "meta.userAgent" "meta.platform"
[15] "meta.language" "meta.locale"
[17] "meta.timeZone" "meta.timezoneOffset"
[19] "meta.screen_width" "meta.screen_height"
[21] "meta.scroll_width" "meta.scroll_height"
[23] "meta.window_innerWidth" "meta.window_innerHeight"
[25] "meta.devicePixelRatio" "feedCAM_repres"
[27] "feedCAM_technicalprobs" "feedCAM_technicalprobsText"
[29] "feedCAM_already" "feedCAM_alreadyText"
[31] "scenario_thoughts" "para_countShowScenario"
[33] "ID" "changeCAM_valence"
[35] "ease_mindmap" "ease_scenario"
[37] "feedback_critic" "law_acceptability_I"
[39] "law_acceptability_Ib" "law_acceptability_II"
[41] "law_demonstration_I" "law_demonstration_Ib"
[43] "law_demonstration_II" "law_demonstration_against_I"
[45] "law_demonstration_against_Ib" "law_demonstration_against_II"
[47] "law_effectiveness_I" "law_effectiveness_Ib"
[49] "law_effectiveness_II" "law_fairness_I"
[51] "law_fairness_Ib" "law_fairness_II"
[53] "law_petition_I" "law_petition_Ib"
[55] "law_petition_II" "law_mean_I"
[57] "law_mean_Ib" "law_mean_II"
[59] "response_1" "response_4"
[61] "response_2" "response_3" ### add prolific data
prolific <- prolific[prolific$Participant.id %in% merged_data$PROLIFIC_PID,]
prolific <- prolific %>%
arrange(sapply(Participant.id, function(y) which(y == merged_data$PROLIFIC_PID)))
if(all(prolific$Participant.id == merged_data$PROLIFIC_PID)){
print("prolific data sucessfully added")
merged_data$socio_age <- prolific$Age
merged_data$socio_sex <- prolific$Sex
merged_data$socio_ethnicity <- prolific$Ethnicity.simplified
merged_data$socio_student <- prolific$Student.status
merged_data$socio_employment <- prolific$Employment.status
merged_data$socio_car <- prolific$Car.ownership
merged_data$total_min_prolific <- prolific$Time.taken / 60
## all time outs to NA
# merged_data$total_min_prolific[merged_data$total_min_prolific > 1000] <- NA
## all expired data to NA
# merged_data[merged_data == "DATA_EXPIRED"] <- NA
merged_data$socio_age <- as.numeric(merged_data$socio_age)
}[1] "prolific data sucessfully added"Warning: NAs durch Umwandlung erzeugtsave all data sets
setwd("outputs/questionnaire")
# Save as .RData objects
save(questionnaire_c1, file = "questionnaire_c1.RData")
save(questionnaire_c3, file = "questionnaire_c3.RData")
save(questionnaire_c5, file = "questionnaire_c5.RData")
save(merged_data, file = "merged_data.RData")
save(questionnaire_rating_long, file = "questionnaire_rating_long.RData")
# Save as Excel files
write_xlsx(questionnaire_c1, "questionnaire_c1.xlsx")
write_xlsx(questionnaire_c3, "questionnaire_c3.xlsx")
write_xlsx(questionnaire_c5, "questionnaire_c5.xlsx")
write_xlsx(merged_data, "merged_data.xlsx")
write_xlsx(questionnaire_rating_long, "questionnaire_rating_long.xlsx")get reaction times for single components
Plot time taken (in minutes) by participants for single components of study:
dat_duration <- data.frame(duration = NA, sender = NA, ID = NA, PROLIFIC_PID = NA)
for(i in 1:length(unique(dat_secondPostCAM$ID))){
tmp_PID <- dat_secondPostCAM$PROLIFIC_PID[dat_secondPostCAM$ID == unique(dat_secondPostCAM$ID)[i] & !is.na(dat_secondPostCAM$PROLIFIC_PID)]
# pre CAM
tmp_preCAM <- data.frame(duration = dat_preCAM$duration[dat_preCAM$ID == unique(dat_preCAM$ID)[i]] / 1000,
sender = dat_preCAM$sender[dat_preCAM$ID == unique(dat_preCAM$ID)[i]])
tmp_preCAM <- tmp_preCAM[!is.na(tmp_preCAM$sender),]
# post CAM
tmp_postCAM <- data.frame(duration = dat_postCAM$duration[dat_postCAM$ID == unique(dat_postCAM$ID)[i]] / 1000,
sender = dat_postCAM$sender[dat_postCAM$ID == unique(dat_postCAM$ID)[i]])
tmp_postCAM <- tmp_postCAM[!is.na(tmp_postCAM$sender),]
# pre CAM
tmp_secondPostCAM <- data.frame(duration = dat_secondPostCAM$duration[dat_secondPostCAM$ID == unique(dat_secondPostCAM$ID)[i]] / 1000,
sender = dat_secondPostCAM$sender[dat_secondPostCAM$ID == unique(dat_secondPostCAM$ID)[i]])
tmp_secondPostCAM <- tmp_secondPostCAM[!is.na(tmp_secondPostCAM$sender),]
tmp <- rbind(tmp_preCAM, tmp_postCAM, tmp_secondPostCAM)
if(all(is.na(dat_duration))){
dat_duration <- data.frame(duration = tmp$duration,
sender = tmp$sender,
ID = rep(i, times=nrow(tmp)),
PROLIFIC_PID = rep(tmp_PID, times=nrow(tmp)))
}else{
dat_duration <- rbind(dat_duration, data.frame(duration = tmp$duration,
sender = tmp$sender,
ID = rep(i, times=nrow(tmp)),
PROLIFIC_PID = rep(tmp_PID, times=nrow(tmp))))
}
}
## remove empty sender
dat_duration <- dat_duration[!is.na(dat_duration$sender), ]
dat_duration <- dat_duration[!is.na(dat_duration$duration), ]
dat_duration$sender[dat_duration$sender == "done"] <- "CAM instructions"
## save as .xlsx
# write.xlsx2(x = dat_duration, file = "outputs/para_duration_singleComponents.xlsx")
#### plot
dat_duration$ID <- factor(dat_duration$ID)
p <- dat_duration %>%
ggplot(aes(x=sender, y=duration, color=PROLIFIC_PID)) +
geom_point() +
geom_jitter(width=0.15)+
theme(axis.text.x = element_text(angle = 90)) + theme(legend.position="none")
p
# Calculate the mean duration in seconds for each sender and sort by mean duration
tmp <- dat_duration %>%
group_by(sender) %>%
summarise(N = n(), mean_duration = mean(duration, na.rm = TRUE)) %>%
arrange(desc(mean_duration))
DT::datatable(tmp, options = list(pageLength = 5)) set up CAM data
pre CAM (component 2)
Load CAM data
setwd("outputs")
suppressMessages(read_file("CAMdata.txt") %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... filter empty rows ...
discard(function(x) x == '')) -> dat_CAM_pre
raw_CAM_pre <- list()
for(i in 1:length(dat_CAM_pre)){
raw_CAM_pre[[i]] <- jsonlite::fromJSON(txt = dat_CAM_pre[[i]])
}Create CAM files, draw CAMs and compute network indicators
### create CAM single files (nodes, connectors, merged)
CAMfiles_pre <- create_CAMfiles(datCAM = raw_CAM_pre, reDeleted = TRUE)Nodes and connectors, which were deleted by participants were removed.
# deleted nodes: 32
# deleted connectors: 18# remove testing data sets
nrow(CAMfiles_pre[[1]])[1] 306CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][nchar(CAMfiles_pre[[1]]$participantCAM) == 24,]
CAMfiles_pre[[2]] <- CAMfiles_pre[[2]][nchar(CAMfiles_pre[[2]]$participantCAM) == 24,]
CAMfiles_pre[[3]] <- CAMfiles_pre[[3]][nchar(CAMfiles_pre[[3]]$participantCAM.x) == 24,]
# number of CAMs collected
nrow(CAMfiles_pre[[1]])[1] 306# remove person who draw many empty concepts
# tmp_pid <- unique(CAMfiles_pre[[1]]$participantCAM[CAMfiles_pre[[1]]$CAM %in% c("a0c6edeb-267a-4f27-8199-79f896e033ce", "8d74f576-e617-4eb1-8ccf-93589ce6c65b")])
# print(tmp_pid)
## remove person from questionnaire data
# questionnaire <- questionnaire[!questionnaire$PROLIFIC_PID %in% tmp_pid,]
## remove person from CAM data
# table(CAMfiles_pre[[1]][CAMfiles_pre[[1]]$participantCAM %in% tmp_pid,]$text)
# CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][!CAMfiles_pre[[1]]$participantCAM %in% tmp_pid,]
# CAMfiles_pre[[2]] <- CAMfiles_pre[[2]][!CAMfiles_pre[[2]]$participantCAM %in% tmp_pid,]
# CAMfiles_pre[[3]] <- CAMfiles_pre[[3]][!CAMfiles_pre[[3]]$participantCAM.x %in% tmp_pid,]
# remove 7 empty concepts:
# CAMfiles_pre[[1]]$text[nchar(CAMfiles_pre[[1]]$text) < 2]
# tmp_ids <- CAMfiles_pre[[1]]$id[nchar(CAMfiles_pre[[1]]$text) < 2]
# table(CAMfiles_pre[[1]]$isActive[CAMfiles_pre[[1]]$id %in% tmp_ids])
# table(CAMfiles_pre[[1]]$participantCAM[CAMfiles_pre[[1]]$id %in% tmp_ids])
#
# CAMfiles_pre[[1]] <- CAMfiles_pre[[1]][!CAMfiles_pre[[1]]$id %in% tmp_ids,]
### draw CAMs
CAMdrawn_pre <- draw_CAM(dat_merged = CAMfiles_pre[[3]],
dat_nodes = CAMfiles_pre[[1]],ids_CAMs = "all",
plot_CAM = FALSE,
useCoordinates = TRUE,
relvertexsize = 3,
reledgesize = 1)processing 21 CAMs... Warning: `graph.data.frame()` was deprecated in igraph 2.0.0.
ℹ Please use `graph_from_data_frame()` instead.[1] "== participantCAM in drawnCAM"for(i in 1:length(CAMdrawn_pre)){
if(any(nchar(V(CAMdrawn_pre[[i]])$label) < 3)){
print(V(CAMdrawn_pre[[i]])$label)
}
}
### network indicators
tmp_microIndicator <- c("Auto", "Fahrrad", "ÖPNV")
networkIndicators_pre <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_pre,
micro_degree = tmp_microIndicator,
micro_valence = tmp_microIndicator,
micro_centr_clo = tmp_microIndicator,
micro_transitivity = tmp_microIndicator,
largestClique = FALSE)Warning: `graph.density()` was deprecated in igraph 2.0.0.
ℹ Please use `edge_density()` instead.Warning: The `types1` argument of `assortativity()` is deprecated as of igraph 1.6.0.
ℹ Please use the `values` argument instead.Warning: `assortativity.degree()` was deprecated in igraph 2.0.0.
ℹ Please use `assortativity_degree()` instead.### wordlist
CAMwordlist_pre <- create_wordlist(
dat_nodes = CAMfiles_pre[[1]],
dat_merged = CAMfiles_pre[[3]],
useSummarized = TRUE,
order = "frequency",
splitByValence = FALSE,
comments = TRUE,
raterSubsetWords = NULL,
rater = FALSE
)[1] "create_wordlist - use raw words"
[1] 0
[1] 306
[1] "temporarily suffixes are added, because not all words have been summarized"
processing 21 CAMs...
[1] "== participantCAM in drawnCAM"if(all(nchar(CAMwordlist_pre$Words) > 2)){
print("sucessfully removed empty words")
}[1] "sucessfully removed empty words"DT::datatable(CAMwordlist_pre, options = list(pageLength = 5)) save CAMs as .json files, and as .png (igraph)
if(save_CAMs_as_pictures){
setwd("outputs")
setwd("savedCAMs_pre")
setwd("png")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .png files have been deleted')
}
### if no participant ID was provided replace by randomly generated CAM ID
if(all(CAMfiles_pre[[3]]$participantCAM.x == "noID")){
CAMfiles_pre[[3]]$participantCAM.x <- CAMfiles_pre[[3]]$CAM.x
}
### save as .json files, and as .png (igraph)
ids_CAMs <- unique(CAMfiles_pre[[3]]$participantCAM.x); length(ids_CAMs)
for(i in 1:length(ids_CAMs)){
save_graphic(filename = paste0("CAM", "_t1_", ids_CAMs[i])) # paste0(ids_CAMs[i]))
CAM_igraph <- CAMdrawn_pre[[c(1:length(CAMdrawn_pre))[
names(CAMdrawn_pre) == paste0(unique(CAMfiles_pre[[3]]$participantCAM.x)[i])]]]
plot(CAM_igraph, edge.arrow.size = .7,
layout=layout_nicely, vertex.frame.color="black", asp = .5, margin = -0.1,
vertex.size = 10, vertex.label.cex = .9)
dev.off()
}
setwd("../json")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .json files have been deleted')
}
for(i in 1:length(raw_CAM_pre)){
if(!is_empty(raw_CAM_pre[[i]]$nodes)){
if(nrow(raw_CAM_pre[[i]]$nodes) > 5){
write(toJSON(raw_CAM_pre[[i]], encoding = "UTF-8"),
paste0(raw_CAM_pre[[i]]$creator, ".json"))
}
}
}
}post CAM (component 4)
Load CAM data
setwd("outputs")
suppressMessages(read_file("secondCAMdata.txt") %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... filter empty rows ...
discard(function(x) x == '')) -> dat_CAM_post
raw_CAM_post <- list()
for(i in 1:length(dat_CAM_post)){
raw_CAM_post[[i]] <- jsonlite::fromJSON(txt = dat_CAM_post[[i]])
}Create CAM files, draw CAMs and compute network indicators
### create CAM single files (nodes, connectors, merged)
CAMfiles_post <- create_CAMfiles(datCAM = raw_CAM_post, reDeleted = TRUE)Nodes and connectors, which were deleted by participants were removed.
# deleted nodes: 24
# deleted connectors: 17# remove testing data sets
nrow(CAMfiles_post[[1]])[1] 368CAMfiles_post[[1]] <- CAMfiles_post[[1]][nchar(CAMfiles_post[[1]]$participantCAM) >= 24,]
CAMfiles_post[[2]] <- CAMfiles_post[[2]][nchar(CAMfiles_post[[2]]$participantCAM) >= 24,]
CAMfiles_post[[3]] <- CAMfiles_post[[3]][nchar(CAMfiles_post[[3]]$participantCAM.x) >= 24,]
# number of CAMs collected
nrow(CAMfiles_post[[1]])[1] 368# remove person who draw many empty concepts
# tmp_pid <- unique(CAMfiles_post[[1]]$participantCAM[CAMfiles_post[[1]]$CAM %in% c("a0c6edeb-267a-4f27-8199-79f896e033ce", "8d74f576-e617-4eb1-8ccf-93589ce6c65b")])
# print(tmp_pid)
## removed person already from questionnaire data
# ## remove person from CAM data
# table(CAMfiles_post[[1]][CAMfiles_post[[1]]$participantCAM %in% tmp_pid,]$text)
# CAMfiles_post[[1]] <- CAMfiles_post[[1]][!CAMfiles_post[[1]]$participantCAM %in% tmp_pid,]
# CAMfiles_post[[2]] <- CAMfiles_post[[2]][!CAMfiles_post[[2]]$participantCAM %in% tmp_pid,]
# CAMfiles_post[[3]] <- CAMfiles_post[[3]][!CAMfiles_post[[3]]$participantCAM.x %in% tmp_pid,]
#
#
# # removed 4 empty concepts:
# CAMfiles_post[[1]]$text[nchar(CAMfiles_post[[1]]$text) < 2 & CAMfiles_post[[1]]$text != "f"]
# tmp_ids <- CAMfiles_post[[1]]$id[nchar(CAMfiles_post[[1]]$text) < 2 & CAMfiles_post[[1]]$text != "f"]
# table(CAMfiles_post[[1]]$isActive[CAMfiles_post[[1]]$id %in% tmp_ids])
# table(CAMfiles_post[[1]]$participantCAM[CAMfiles_post[[1]]$id %in% tmp_ids])
#
#
# CAMfiles_post[[1]] <- CAMfiles_post[[1]][!CAMfiles_post[[1]]$id %in% tmp_ids,]
### draw CAMs
CAMdrawn_post <- draw_CAM(dat_merged = CAMfiles_post[[3]],
dat_nodes = CAMfiles_post[[1]],ids_CAMs = "all",
plot_CAM = FALSE,
useCoordinates = TRUE,
relvertexsize = 3,
reledgesize = 1)processing 21 CAMs...
[1] "== participantCAM in drawnCAM"### network indicators
tmp_microIndicator <- c("Auto", "Fahrrad", "ÖPNV")
networkIndicators_post <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_post,
micro_degree = tmp_microIndicator,
micro_valence = tmp_microIndicator,
micro_centr_clo = tmp_microIndicator,
micro_transitivity = tmp_microIndicator,
largestClique = FALSE)
# wordlist
CAMwordlist_post <- create_wordlist(
dat_nodes = CAMfiles_post[[1]],
dat_merged = CAMfiles_post[[3]],
order = "frequency",
splitByValence = FALSE,
comments = TRUE,
raterSubsetWords = NULL,
rater = FALSE
)[1] "create_wordlist - use raw words"
[1] 0
[1] 368
[1] "temporarily suffixes are added, because not all words have been summarized"
processing 21 CAMs...
[1] "== participantCAM in drawnCAM"if(all(nchar(CAMwordlist_post$Words) > 2)){
print("sucessfully removed empty words")
}else{
CAMwordlist_post$Words[nchar(CAMwordlist_post$Words) < 2]
}[1] ""DT::datatable(CAMwordlist_post, options = list(pageLength = 5)) save CAMs as .json files, and as .png (igraph)
if(save_CAMs_as_pictures){
setwd("outputs")
setwd("savedCAMs_post")
setwd("png")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .png files have been deleted')
}
### if no participant ID was provided replace by randomly generated CAM ID
if(all(CAMfiles_post[[3]]$participantCAM.x == "noID")){
CAMfiles_post[[3]]$participantCAM.x <- CAMfiles_post[[3]]$CAM.x
}
### save as .json files, and as .png (igraph)
ids_CAMs <- unique(CAMfiles_post[[3]]$participantCAM.x); length(ids_CAMs)
for(i in 1:length(ids_CAMs)){
save_graphic(filename = paste0("CAM", "_t2_", ids_CAMs[i])) # paste0(ids_CAMs[i]))
CAM_igraph <- CAMdrawn_post[[c(1:length(CAMdrawn_post))[
names(CAMdrawn_post) == paste0(unique(CAMfiles_post[[3]]$participantCAM.x)[i])]]]
plot(CAM_igraph, edge.arrow.size = .7,
layout=layout_nicely, vertex.frame.color="black", asp = .5, margin = -0.1,
vertex.size = 10, vertex.label.cex = .9)
dev.off()
}
setwd("../json")
### remove all files if there are any
if(length(list.files()) >= 1){
file.remove(list.files())
cat('\n!
all former .json files have been deleted')
}
for(i in 1:length(raw_CAM_post)){
if(!is_empty(raw_CAM_post[[i]]$nodes)){
if(nrow(raw_CAM_post[[i]]$nodes) > 5){
write(toJSON(raw_CAM_post[[i]], encoding = "UTF-8"),
paste0(raw_CAM_post[[i]]$creator, ".json"))
}
}
}
}merge CAM data
Load CAM data
setwd("outputs")
suppressMessages(read_file("mergedCAMdata.txt") %>%
# ... split it into lines ...
str_split('\n') %>% first() %>%
discard(function(x) x == '') %>%
discard(function(x) x == '\r') %>%
# ... filter empty rows ...
discard(function(x) x == '')) -> dat_CAM_combined
raw_CAM_combined <- list()
for(i in 1:length(dat_CAM_combined)){
raw_CAM_combined[[i]] <- jsonlite::fromJSON(txt = dat_CAM_combined[[i]])
}
length(raw_CAM_combined)[1] 42Create CAM files, draw CAMs and compute network indicators
### create CAM single files (nodes, connectors, merged)
CAMfiles_combined <- create_CAMfiles(datCAM = raw_CAM_combined, reDeleted = TRUE)Nodes and connectors, which were deleted by participants were removed.
# deleted nodes: 56
# deleted connectors: 35# remove testing data sets
nrow(CAMfiles_combined[[1]])[1] 674CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][nchar(CAMfiles_combined[[1]]$participantCAM) >= 24,]
CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][nchar(CAMfiles_combined[[2]]$participantCAM) >= 24,]
CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][nchar(CAMfiles_combined[[3]]$participantCAM.x) >= 24,]
nrow(CAMfiles_combined[[1]])[1] 674# remove person who draw many empty concepts
# tmp_pid <- unique(CAMfiles_combined[[1]]$participantCAM[CAMfiles_combined[[1]]$CAM %in% c("a0c6edeb-267a-4f27-8199-79f896e033ce", "8d74f576-e617-4eb1-8ccf-93589ce6c65b")])
# print(tmp_pid)
## removed person already from questionnaire data
## remove person from CAM data
# table(CAMfiles_combined[[1]][CAMfiles_combined[[1]]$participantCAM %in% tmp_pid,]$text)
# CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][!CAMfiles_combined[[1]]$participantCAM %in% tmp_pid,]
# CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][!CAMfiles_combined[[2]]$participantCAM %in% tmp_pid,]
# CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][!CAMfiles_combined[[3]]$participantCAM.x %in% tmp_pid,]
length(unique(CAMfiles_combined[[1]]$CAM))[1] 42# remove empty concepts:
# CAMfiles_combined[[1]]$text[nchar(CAMfiles_combined[[1]]$text) < 2 & CAMfiles_combined[[1]]$text != "f"]
# tmp_ids <- CAMfiles_combined[[1]]$id[nchar(CAMfiles_combined[[1]]$text) < 2 & CAMfiles_combined[[1]]$text != "f"]
# table(CAMfiles_combined[[1]]$isActive[CAMfiles_combined[[1]]$id %in% tmp_ids])
# table(CAMfiles_combined[[1]]$participantCAM[CAMfiles_combined[[1]]$id %in% tmp_ids])
#
# CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][!CAMfiles_combined[[1]]$id %in% tmp_ids,]
### add protocol #
# if(consider_Protocol){
# setwd("outputs/01_dataPreperation")
#
# text <- readLines("protocol_after_word2vec.txt", warn = FALSE)
# text <- readLines(textConnection(text, encoding="UTF-8"), encoding="UTF-8")
#
# if (testIfJson(file = text)) {
# protocol <- rjson::fromJSON(file = "protocol_after_word2vec.txt")
#
# ## no CAM deleted
# # CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][CAMfiles_combined[[1]]$CAM %in% protocol$currentCAMs,]
# # CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][CAMfiles_combined[[2]]$CAM %in% protocol$currentCAMs,]
# # CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][CAMfiles_combined[[3]]$CAM.x %in% protocol$currentCAMs,]
#
#
# tmp_out <- overwriteTextNodes(protocolDat = protocol,
# nodesDat = CAMfiles_combined[[1]])
# CAMfiles_combined[[1]] <- tmp_out[[1]]
# # tmp_out[[2]]
#
# } else{
# print("Invalid protocol uploaded")
# }
# }
# vec_CAMs <- c(); h = 1
# for(c in unique(CAMfiles_combined[[1]]$CAM)){
# tmp <- CAMfiles_combined[[1]][CAMfiles_combined[[1]]$CAM %in% c,]
#
# if(!(any(c("Rettungsroboter", "sozialer Assistenzroboter") %in% tmp$text) & all(c("Vorteile", "Nachteile") %in% tmp$text))){
# print(c)
# print(tmp$text)
# vec_CAMs[h] <- c
# h = h + 1
# # plot(CAMdrawn_combined[[c]])
# }
# }
## fix manually
# single pre defined concepts were falsely written
## Soziale Assistenzroboter to sozialer Assistenzroboter
# CAMfiles_combined[[1]]$CAM[CAMfiles_combined[[1]]$participantCAM %in% "5debfbcc3a11682f0fae8b29" & CAMfiles_combined[[1]]$text == "Soziale Assistenzroboter"]
# vec_CAMs <- vec_CAMs[!vec_CAMs %in% CAMfiles_combined[[1]]$CAM[CAMfiles_combined[[1]]$participantCAM %in% "5debfbcc3a11682f0fae8b29" & CAMfiles_combined[[1]]$text == "Soziale Assistenzroboter"]]
#
# CAMfiles_combined[[1]]$text[CAMfiles_combined[[1]]$participantCAM %in% "5debfbcc3a11682f0fae8b29" & CAMfiles_combined[[1]]$text == "Soziale Assistenzroboter"] <- "Soziale Assistenzroboter"
# CAMfiles_combined[[1]]$text_summarized[CAMfiles_combined[[1]]$participantCAM %in% "5debfbcc3a11682f0fae8b29" & CAMfiles_combined[[1]]$text == "Soziale Assistenzroboter"] <- "Soziale Assistenzroboter_positive"
#
# ## Roboter to sozialer Rettungsroboter
# CAMfiles_combined[[1]]$CAM[CAMfiles_combined[[1]]$participantCAM %in% "5ba00acff337030001de805d" & CAMfiles_combined[[1]]$text == "Roboter"]
# vec_CAMs <- vec_CAMs[!vec_CAMs %in% CAMfiles_combined[[1]]$CAM[CAMfiles_combined[[1]]$participantCAM %in% "5ba00acff337030001de805d" & CAMfiles_combined[[1]]$text == "Roboter"]]
#
# CAMfiles_combined[[1]]$text[CAMfiles_combined[[1]]$participantCAM %in% "5ba00acff337030001de805d" & CAMfiles_combined[[1]]$text == "Roboter"] <- "Rettungsroboter"
# CAMfiles_combined[[1]]$text_summarized[CAMfiles_combined[[1]]$participantCAM %in% "5ba00acff337030001de805d" & CAMfiles_combined[[1]]$text == "Rettungsroboter"] <- "Rettungsroboter_neutral"
## remove 5 persons because of technical issues
# vec_Pids <- unique(CAMfiles_combined[[1]]$participantCAM[CAMfiles_combined[[1]]$CAM %in% vec_CAMs])
# vec_Pids
#
# # remove CAMs
# CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][!CAMfiles_combined[[1]]$participantCAM %in% vec_Pids,]
# CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][!CAMfiles_combined[[2]]$participantCAM %in% vec_Pids,]
# CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][!CAMfiles_combined[[3]]$participantCAM.x %in% vec_Pids,]
# remove questionnaires
# questionnaire <- questionnaire[!questionnaire$PROLIFIC_PID %in% vec_Pids,]
# remove person "6560e6f734ae18bd18474cc9" -> only draw pre-defined concepts
# for(c in unique(CAMfiles_combined[[1]]$participantCAM)){
# tmp <- CAMfiles_combined[[1]][CAMfiles_combined[[1]]$participantCAM %in% c,]
#
# if(sum(tmp$text %in% c("Vorteile", "Nachteile")) != 4){
# print(c)
# print(sum(tmp$text %in% c("Vorteile", "Nachteile")))
# print(tmp$text)
# }
# }
## removed person from questionnaire data
# questionnaire <- questionnaire[!questionnaire$PROLIFIC_PID %in% "6560e6f734ae18bd18474cc9",]
#
# ## remove person from CAM data
# CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][!CAMfiles_combined[[1]]$participantCAM %in% "6560e6f734ae18bd18474cc9",]
# CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][!CAMfiles_combined[[2]]$participantCAM %in% "6560e6f734ae18bd18474cc9",]
# CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][!CAMfiles_combined[[3]]$participantCAM.x %in% "6560e6f734ae18bd18474cc9",]
# remove person "65304e8a630196510c79f7df" -> draw multiple times concept "leer"
# for(c in unique(CAMfiles_combined[[1]]$CAM)){
# tmp <- CAMfiles_combined[[1]][CAMfiles_combined[[1]]$CAM == c,]
#
# if(any(table(tmp$text) >= 3)){
# print(c)
# print(sort(table(tmp$text)))
# }
# }
#
# # remove person who draw many empty concepts
# tmp_pid <- unique(CAMfiles_combined[[1]]$participantCAM[CAMfiles_combined[[1]]$CAM %in% c("503b3517-b003-48e5-b121-f48c9a64ecb6", "39e7d213-1276-4da8-99ea-5a13487874e7")])
# print(tmp_pid)
#
# ## remove person from questionnaire data
# questionnaire <- questionnaire[!questionnaire$PROLIFIC_PID %in% tmp_pid,]
#
# ## remove person from CAM data
# CAMfiles_combined[[1]] <- CAMfiles_combined[[1]][!CAMfiles_combined[[1]]$participantCAM %in% tmp_pid,]
# CAMfiles_combined[[2]] <- CAMfiles_combined[[2]][!CAMfiles_combined[[2]]$participantCAM %in% tmp_pid,]
# CAMfiles_combined[[3]] <- CAMfiles_combined[[3]][!CAMfiles_combined[[3]]$participantCAM.x %in% tmp_pid,]
### draw CAMs
CAMdrawn_combined <- draw_CAM(dat_merged = CAMfiles_combined[[3]],
dat_nodes = CAMfiles_combined[[1]],ids_CAMs = "all",
plot_CAM = FALSE,
useCoordinates = TRUE,
relvertexsize = 3,
reledgesize = 1)processing 42 CAMs...
[1] "== ids_CAMs in drawnCAM"### network indicators
tmp_microIndicator <- c("Rettungsroboter", "sozialer Assistenzroboter", "Vorteile", "Nachteile")
networkIndicators_combined <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_combined,
micro_degree = tmp_microIndicator,
micro_valence = tmp_microIndicator,
micro_centr_clo = tmp_microIndicator,
micro_transitivity = tmp_microIndicator,
largestClique = FALSE)
# wordlist
CAMwordlist_combined <- create_wordlist(
dat_nodes = CAMfiles_combined[[1]],
dat_merged = CAMfiles_combined[[3]],
order = "frequency",
splitByValence = FALSE,
comments = TRUE,
raterSubsetWords = NULL,
rater = FALSE
)[1] "create_wordlist - use raw words"
[1] 0
[1] 674
[1] "temporarily suffixes are added, because not all words have been summarized"
processing 42 CAMs...
[1] "== ids_CAMs in drawnCAM"if(all(nchar(CAMwordlist_combined$Words) > 2)){
print("sucessfully removed empty words")
}else{
CAMwordlist_combined$Words[nchar(CAMwordlist_combined$Words) < 2]
}[1] ""DT::datatable(CAMwordlist_combined, options = list(pageLength = 5)) identify types of changes (delta CAM)
# backupIDs_post <- CAMfiles_post[[1]]$participantCAM
# CAMfiles_post[[1]]$participantCAM <- str_remove_all(string = CAMfiles_post[[1]]$participantCAM, pattern = "_t2$")
### set A, B, C, D types
if (all(unique(CAMfiles_pre[[1]]$participantCAM) == unique(CAMfiles_post[[1]]$participantCAM))) {
vec_type <- c()
error <- 0
verbose = FALSE
##
list_newWords_text <- list()
list_newWords_value <- list()
list_ids <- list()
h = 1
for (i in 1:length(unique(CAMfiles_pre[[1]]$participantCAM))) {
praeCAM <-
CAMfiles_pre[[1]][CAMfiles_pre[[1]]$participantCAM == unique(CAMfiles_pre[[1]]$participantCAM)[i],]
postCAM <-
CAMfiles_post[[1]][CAMfiles_post[[1]]$participantCAM == unique(CAMfiles_post[[1]]$participantCAM)[i],]
## to test:
# praeCAM$text %in% postCAM$text
# postCAM$text %in% praeCAM$text
# length(praeCAM$text)
# length(postCAM$text)
# praeCAM$text
# postCAM$text
## Typ A
if (all(postCAM$text %in% praeCAM$text) &
length(postCAM$text) < length(praeCAM$text)) {
vec_type[i] <- "A"
if (verbose) {
cat("\n i:", i, "type:", vec_type[i], "\n")
}
error = error + 1
}
## Typ B
if (all(praeCAM$text %in% postCAM$text) &
length(postCAM$text) > length(praeCAM$text)) {
vec_type[i] <- "B"
if (verbose) {
cat("\n i:", i, "type:", vec_type[i], "\n")
}
error = error + 1
## get words and values
list_newWords_text[[h]] <-
postCAM$text[!postCAM$text %in% praeCAM$text]
list_newWords_value[[h]] <-
postCAM$value[!postCAM$text %in% praeCAM$text]
list_ids[[h]] <- postCAM$id[!postCAM$text %in% praeCAM$text]
h = h + 1
}
## Typ C
if (all(praeCAM$text %in% postCAM$text) &
all(postCAM$text %in% praeCAM$text)) {
vec_type[i] <- "C"
if (verbose) {
cat("\n i:", i, "type:", vec_type[i], "\n")
}
error = error + 1
}
## Typ D
# smaller > pr? UE post, post UE pr?
if (sum(praeCAM$text %in% postCAM$text) < length(praeCAM$text) &
sum(postCAM$text %in% praeCAM$text) < length(postCAM$text)) {
vec_type[i] <- "D"
if (verbose) {
cat("\n i:", i, "type:", vec_type[i], "\n")
}
error = error + 1
}
if (error > 1) {
print("ERROR in (not exclusive logical condition)", i)
stop("check your data and adjust this function")
}
error = 0
}
}
table(vec_type)vec_type
B C D
11 3 7 barplot(table(vec_type))
example for newly added words:
barplot(table(unlist(list_newWords_value)))
# sort(table(unlist(list_newWords_text)))
### add data
# nrow(questionnaire); length(vec_type)
# questionnaire$typeChange <- vec_type
dat_newWords <- data.frame(id = unlist(list_ids),
text = unlist(list_newWords_text),
value = unlist(list_newWords_value))
DT::datatable(dat_newWords, options = list(pageLength = 5))merge and save all data
setwd("outputs/CAMs")
if(all(unique(CAMfiles_pre[[1]]$participantCAM) == networkIndicators_pre$participantCAM)){
print("pre CAM ID can be set")
networkIndicators_pre$CAM_ID <- unique(CAMfiles_pre[[1]]$CAM)
}[1] "pre CAM ID can be set"# CAMfiles_post[[1]]$participantCAM <- backupIDs_post
if(all(unique(CAMfiles_post[[1]]$participantCAM) == networkIndicators_post$participantCAM)){
print("post CAM ID can be set")
networkIndicators_post$CAM_ID <- unique(CAMfiles_post[[1]]$CAM)
}[1] "post CAM ID can be set"### remove all previously removed participants
length(unique(CAMfiles_combined[[1]]$participantCAM))[1] 21nrow(networkIndicators_pre)[1] 21nrow(networkIndicators_post)[1] 21nrow(merged_data)[1] 21networkIndicators_pre <-
networkIndicators_pre[networkIndicators_pre$participantCAM %in% CAMfiles_combined[[1]]$participantCAM,]
networkIndicators_post <-
networkIndicators_post[networkIndicators_post$participantCAM %in% CAMfiles_combined[[1]]$participantCAM,]
nrow(networkIndicators_pre)[1] 21nrow(networkIndicators_post)[1] 21### match data
if (all(merged_data$PROLIFIC_PID == networkIndicators_pre$participantCAM) &
all(networkIndicators_pre$participantCAM == networkIndicators_post$participantCAM) &
all(unique(CAMfiles_combined[[1]]$participantCAM) == networkIndicators_post$participantCAM)) {
print("all data can be matched row by row")
# fix IDs
networkIndicators_pre$participantCAM <- paste0(networkIndicators_pre$participantCAM, "_pre")
networkIndicators_post$participantCAM <- paste0(networkIndicators_post$participantCAM, "_post")
# save questionnaire
merged_data$participantCAMpre <- networkIndicators_pre$participantCAM
merged_data$participantCAMpost <- networkIndicators_post$participantCAM
## save as .xlsx file
xlsx::write.xlsx2(x = merged_data, file = "merged_data_final.xlsx")
## save as R object
saveRDS(merged_data, file = "merged_data_final.rds")
# save network indicators pre
## save as .xlsx file
xlsx::write.xlsx2(x = networkIndicators_pre, file = "networkIndicators_pre_final.xlsx")
## save as R object
saveRDS(networkIndicators_pre, file = "networkIndicators_pre_final.rds")
# save network indicators post
## save as .xlsx file
xlsx::write.xlsx2(x = networkIndicators_post, file = "networkIndicators_post_final.xlsx")
## save as R object
saveRDS(networkIndicators_post, file = "networkIndicators_post_final.rds")
# save CAMfiles pre
saveRDS(CAMfiles_pre, file = "CAMfiles_pre_final.rds")
# save CAMfiles post
saveRDS(CAMfiles_post, file = "CAMfiles_post_final.rds")
# save CAMfiles combined and clean
saveRDS(CAMfiles_combined, file = "CAMfiles_combined_final.rds")
# save CAMfiles combined and clean
# saveRDS(CAMfiles_combined_translated, file = "CAMfiles_combined_final_translated.rds")
# save questionnaire combined with CAMs
colnames(networkIndicators_pre) <- paste0(colnames(networkIndicators_pre), "_pre")
colnames(networkIndicators_post) <- paste0(colnames(networkIndicators_post), "_post")
merged_dataCAMs <- cbind(merged_data, networkIndicators_pre, networkIndicators_post)
dim(merged_dataCAMs)
## save as .xlsx file
xlsx::write.xlsx2(x = merged_dataCAMs, file = "merged_dataCAMs_final.xlsx")
## save as R object
saveRDS(merged_dataCAMs, file = "merged_dataCAMs_final.rds")
}[1] "all data can be matched row by row"create data frames of concepts constant (C), deleted (D), new (N)
dat_pre_out <- data.frame()
dat_post_out <- data.frame()
for (i in 1:nrow(merged_dataCAMs)) {
tmp_pre <-
CAMfiles_combined[[1]][CAMfiles_combined[[1]]$CAM %in% merged_dataCAMs$CAM_ID_pre[i],]
tmp_post <-
CAMfiles_combined[[1]][CAMfiles_combined[[1]]$CAM %in% merged_dataCAMs$CAM_ID_post[i],]
## get date of concepts drawn by data collection tool (no interaction by user) - heuristic !!!:
date_tmp <-
tmp_post$date[tmp_post$date - min(tmp_post$date) <= .5] # less than half a second
dat_pre <-
tmp_pre[, c("participantCAM",
"id" ,
"text",
"value",
"comment",
"date",
"x_pos",
"y_pos")]
dat_post <-
tmp_post[, c("participantCAM",
"id" ,
"text",
"value",
"comment",
"date",
"x_pos",
"y_pos")]
## set variables:
if (nrow(dat_pre) >= 1) {
## indicate type of concept:
dat_pre$typeConcept <- NA
checkOldDeleted <- FALSE
}
if (nrow(dat_post) >= 1) {
dat_post$originalConcept_date <- dat_post$date %in% date_tmp
## check if positions have changed - heuristic !!!:
dat_post$originalConcept_position <- FALSE
## indicate if position was changed
dat_post$changedPosition <- FALSE
## indicate if valence was changed
dat_post$changedValence <- FALSE
## indicate type of concept:
dat_post$typeConcept <- NA
checkNewAdded <- FALSE
}
## loop through if both data sets exists
if (nrow(dat_pre) >= 1 && nrow(dat_post) >= 1) {
#> through dat_pre
for (p in 1:nrow(dat_pre)) {
## check positon:
pos_tmp <- dat_pre[p, c("x_pos", "y_pos")]
matching_id <-
dat_post[dat_post$x_pos == pos_tmp$x_pos &
dat_post$y_pos == pos_tmp$y_pos, "id"]
dat_post$originalConcept_position[dat_post$id == matching_id] <-
TRUE
## check valence
value_tmp <-
dat_post$value[dat_post$text %in% dat_pre$text[p]]
if (length(value_tmp) != 0) {
if (dat_pre$value[p] != value_tmp[1]) {
dat_post$changedValence[dat_post$text %in% dat_pre$text[p]] <- TRUE
}
}
## indicate type of concept:
if (dat_pre$text[p] %in% dat_post$text) {
dat_pre$typeConcept[p] <- "constant"
} else{
dat_pre$typeConcept[p] <- "deleted"
# cat("\n deleted concepts:\n", "in i:", i, ", c:", c, "p:", p, "\n")
checkOldDeleted <- TRUE
}
}
#> through dat_post
for (q in 1:nrow(dat_post)) {
## indicate type of concept:
if (dat_post$text[q] %in% dat_pre$text) {
dat_post$typeConcept[q] <- "constant"
} else{
dat_post$typeConcept[q] <- "new"
# cat("\n new concepts:\n", "in i:", i, ", c:", c, "p:", p, "\n")
checkNewAdded <- TRUE
}
## indicate if concept changed positon
if (dat_post$originalConcept_date[q] &&
!dat_post$originalConcept_position[q]) {
dat_post$changedPosition[q] <- TRUE
}
}
if (all(checkOldDeleted, checkNewAdded)) {
# cat("\n deleted concepts, new concepts:\n", "in i:", i, ", c:", c, "p:", p, "\n")
}
}
## indicate type of concept:
if (nrow(dat_post) == 0) {
dat_pre$typeConcept <- "deleted"
}
if (nrow(dat_pre) == 0) {
dat_post$typeConcept <- "new"
}
if (any(is.na(dat_post$typeConcept))) {
cat("\n NA typeConcept:\n", "in i:", i, ", c:", c, "p:", p, "\n")
stop()
}
dat_pre_out <- rbind(dat_pre_out, dat_pre)
dat_post_out <- rbind(dat_post_out, dat_post)
}# check if I missed any typeConcept
sum(is.na(dat_pre_out$typeConcept))[1] 0sum(is.na(dat_post_out$typeConcept))[1] 0# check if any data set was multiple times added
sum(table(dat_pre_out$id) >= 2)[1] 0sum(table(dat_post_out$id) >= 2)[1] 0# number of entries
nrow(dat_pre_out)[1] 306nrow(dat_post_out)[1] 368# nrow(dat_post_out) - 535 + 68
# types
table(dat_pre_out$typeConcept)
constant deleted
296 10 table(dat_post_out$typeConcept)
constant new
297 71 table(dat_post_out$changedPosition)
FALSE TRUE
306 62 table(dat_post_out$changedValence)
FALSE TRUE
343 25 setwd("outputs/CAM_concepts")
xlsx::write.xlsx2(x = dat_pre_out, file = "concepts_preIntervention.xlsx")
xlsx::write.xlsx2(x = dat_post_out, file = "concepts_postIntervention.xlsx")References
Peng, Roger D., and Elizabeth Matsui. 2016. The Art of Data Science: A Guide for Anyone Who Works with Data. Lulu.com. https://bookdown.org/rdpeng/artofdatascience/.
Wickham, Hadley, and Garrett Grolemund. 2017. R for Data Science: Import, Tidy, Transform, Visualize, and Model Data. "O’Reilly Media, Inc.". https://r4ds.had.co.nz/.
Xie, Yihui, J. J. Allaire, and Garrett Grolemund. 2018. R Markdown: The Definitive Guide. New York: Chapman; Hall/CRC. https://doi.org/10.1201/9781138359444.