Main File for t2 CAM study (USA, Germany samples)

Author

Julius Fenn, Christophe Becht

Notes

Remark: “dat” at first is the data set of N=150 americans who have the political affilication “Democrat”; in opposition to “dat_Republican”

prepare data

set up data.frame questionnaires

for Germany

setwd("outputs")
########################################
# Germany
########################################
# > pre study
suppressMessages(read_file('preCAM_Germany.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_Germany
# > post study
suppressMessages(read_file('postCAM_Germany.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_Germany


########################################
# create counter variable for both data sets
########################################
### pre study
dat_preCAM_Germany$ID <- NA
dat_preCAM_Germany$country <- NA

tmp_IDcounter <- 0
for(i in 1:nrow(dat_preCAM_Germany)){
  if(!is.na(dat_preCAM_Germany$sender[i]) && dat_preCAM_Germany$sender[i] == "Greetings"){
    # tmp <- dat_preCAM_Germany$prolific_pid[i]
    tmp_IDcounter = tmp_IDcounter + 1
    dat_preCAM_Germany$country[i] <- "Germany" ## add country
  }
  dat_preCAM_Germany$ID[i] <- tmp_IDcounter
}

### post study
dat_postCAM_Germany$ID <- NA
dat_postCAM_Germany$country <- NA

tmp_IDcounter <- 0
for(i in 1:nrow(dat_postCAM_Germany)){
  if(!is.na(dat_postCAM_Germany$sender[i]) && dat_postCAM_Germany$sender[i] == "CAMfeedbackGeneral"){
    # tmp <- dat_postCAM_Germany$prolific_pid[i]
    tmp_IDcounter = tmp_IDcounter + 1
    dat_postCAM_Germany$country[i] <- "Germany" ## add country
  }
  dat_postCAM_Germany$ID[i] <- tmp_IDcounter
}


########################################
# keep only complete data sets
########################################
### pre-study
sum(table(dat_preCAM_Germany$ID) != max(table(dat_preCAM_Germany$ID)))

[1] 0

sum(table(dat_preCAM_Germany$ID) == max(table(dat_preCAM_Germany$ID)))

[1] 75

dat_preCAM_Germany <- dat_preCAM_Germany[dat_preCAM_Germany$ID %in% names(table(dat_preCAM_Germany$ID))[table(dat_preCAM_Germany$ID) == max(table(dat_preCAM_Germany$ID))],]

### post-study
sum(table(dat_postCAM_Germany$ID) != max(table(dat_postCAM_Germany$ID)))

[1] 0

sum(table(dat_postCAM_Germany$ID) == max(table(dat_postCAM_Germany$ID)))

[1] 75

dat_postCAM_Germany <- dat_postCAM_Germany[dat_postCAM_Germany$ID %in% names(table(dat_postCAM_Germany$ID))[table(dat_postCAM_Germany$ID) == max(table(dat_postCAM_Germany$ID))],]


########################################
# json (from JATOS) to 2D data.frame
########################################
################################ pre-study
tmp_notNumeric <- str_subset(string = colnames(dat_preCAM_Germany), pattern = "^meta|^R")
tmp_notNumeric <- str_subset(string = tmp_notNumeric, pattern = "labjs|location", negate = TRUE)


vec_ques <- c("PROLIFIC_PID",
                "dummy_informedconsent",
                "commCheck",
                "country",  tmp_notNumeric)

vec_notNumeric = c("PROLIFIC_PID",
                   "country",
                   tmp_notNumeric)

questionnaire_preCAM_Germany <- questionnairetype(dataset = dat_preCAM_Germany, 
                                        listvars = vec_ques, 
                                        notNumeric = vec_notNumeric)


################################ post-study
tmp_numeric <- str_subset(string = colnames(dat_postCAM_Germany), pattern = "^Biospheric|^probabilityClimate|^concernClimate|^Risk|^policyItems|rlgdgr")


vec_ques <- c("PROLIFIC_PID",
                tmp_numeric,
                "education",
                "feedback_critic",
                "country")

vec_notNumeric = c("PROLIFIC_PID",
                   "education",
                   "feedback_critic",
                   "country")

questionnaire_postCAM_Germany <- questionnairetype(dataset = dat_postCAM_Germany, 
                                        listvars = vec_ques, 
                                        notNumeric = vec_notNumeric)


dim(questionnaire_preCAM_Germany)

[1] 75 18

dim(questionnaire_postCAM_Germany)

[1] 75 25

questionnaire_Germany <- left_join(questionnaire_preCAM_Germany, questionnaire_postCAM_Germany, by="ID") # !!!
dim(questionnaire_Germany)

[1] 75 42

for USA

setwd("outputs")
########################################
# Germany
########################################
# > pre study
suppressMessages(read_file('preCAM_USA.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_USA
# > post study
suppressMessages(read_file('postCAM_USA.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_USA


########################################
# create counter variable for both data sets
########################################
### pre study
dat_preCAM_USA$ID <- NA
dat_preCAM_USA$country <- NA

tmp_IDcounter <- 0
for(i in 1:nrow(dat_preCAM_USA)){
  if(!is.na(dat_preCAM_USA$sender[i]) && dat_preCAM_USA$sender[i] == "Greetings"){
    # tmp <- dat_preCAM_USA$prolific_pid[i]
    tmp_IDcounter = tmp_IDcounter + 1
    dat_preCAM_USA$country[i] <- "Germany" ## add country
  }
  dat_preCAM_USA$ID[i] <- tmp_IDcounter
}

### post study
dat_postCAM_USA$ID <- NA
dat_postCAM_USA$country <- NA

tmp_IDcounter <- 0
for(i in 1:nrow(dat_postCAM_USA)){
  if(!is.na(dat_postCAM_USA$sender[i]) && dat_postCAM_USA$sender[i] == "CAMfeedbackGeneral"){
    # tmp <- dat_postCAM_USA$prolific_pid[i]
    tmp_IDcounter = tmp_IDcounter + 1
    dat_postCAM_USA$country[i] <- "Germany" ## add country
  }
  dat_postCAM_USA$ID[i] <- tmp_IDcounter
}


########################################
# keep only complete data sets
########################################
### pre-study
sum(table(dat_preCAM_USA$ID) != max(table(dat_preCAM_USA$ID)))

[1] 0

sum(table(dat_preCAM_USA$ID) == max(table(dat_preCAM_USA$ID)))

[1] 49

dat_preCAM_USA <- dat_preCAM_USA[dat_preCAM_USA$ID %in% names(table(dat_preCAM_USA$ID))[table(dat_preCAM_USA$ID) == max(table(dat_preCAM_USA$ID))],]

### post-study
sum(table(dat_postCAM_USA$ID) != max(table(dat_postCAM_USA$ID)))

[1] 1

sum(table(dat_postCAM_USA$ID) == max(table(dat_postCAM_USA$ID)))

[1] 48

dat_postCAM_USA <- dat_postCAM_USA[dat_postCAM_USA$ID %in% names(table(dat_postCAM_USA$ID))[table(dat_postCAM_USA$ID) == max(table(dat_postCAM_USA$ID))],]


########################################
# json (from JATOS) to 2D data.frame
########################################
################################ pre-study
tmp_notNumeric <- str_subset(string = colnames(dat_preCAM_USA), pattern = "^meta|^R")
tmp_notNumeric <- str_subset(string = tmp_notNumeric, pattern = "labjs|location", negate = TRUE)


vec_ques <- c("PROLIFIC_PID",
                "dummy_informedconsent",
                "commCheck",
                "country",  tmp_notNumeric)

vec_notNumeric = c("PROLIFIC_PID",
                   "country",
                   tmp_notNumeric)

questionnaire_preCAM_USA <- questionnairetype(dataset = dat_preCAM_USA, 
                                        listvars = vec_ques, 
                                        notNumeric = vec_notNumeric)


################################ post-study
tmp_numeric <- str_subset(string = colnames(dat_postCAM_USA), pattern = "^Biospheric|^probabilityClimate|^concernClimate|^Risk|^policyItems|rlgdgr")


vec_ques <- c("PROLIFIC_PID",
                tmp_numeric,
                "education",
                "feedback_critic",
                "country")

vec_notNumeric = c("PROLIFIC_PID",
                   "education",
                   "feedback_critic",
                   "country")

questionnaire_postCAM_USA <- questionnairetype(dataset = dat_postCAM_USA, 
                                        listvars = vec_ques, 
                                        notNumeric = vec_notNumeric)


dim(questionnaire_preCAM_USA)

[1] 49 18

dim(questionnaire_postCAM_USA)

[1] 48 25

questionnaire_USA <- left_join(questionnaire_preCAM_USA, questionnaire_postCAM_USA, by="ID") # !!!
dim(questionnaire_USA)

[1] 49 42

check current data for conspiracy / country group

questionnaire_t1 <- read.xlsx2(file = "data/questionnaire_final.xlsx", sheetIndex = 1)

########################################
# Germany
########################################
tmp_dat <- questionnaire_t1[questionnaire_t1$PROLIFIC_PID %in% questionnaire_Germany$PROLIFIC_PID,]
table(tmp_dat$country)


Germany 
     75

table(tmp_dat$classes_conspiracy) # 3 = high, 1 = low


 1  3 
35 40

########################################
# USA
########################################
tmp_dat <- questionnaire_t1[questionnaire_t1$PROLIFIC_PID %in% questionnaire_USA$PROLIFIC_PID,]
table(tmp_dat$country)


USA 
 49

table(tmp_dat$classes_conspiracy) # 3 = high, 1 = low


 1  3 
26 23

set up CAM data

for Germany

Load CAM data

setwd("outputs")
suppressMessages(read_file("CAMdata_Germany.txt") %>%
  # ... split it into lines ...
  str_split('\n') %>% first() %>%
                   # ... filter empty rows ...
                   discard(function(x) x == '') %>%
                   discard(function(x) x == '\r')) -> dat_CAM_Germany


raw_CAM_Germany <- list()
for(i in 1:length(dat_CAM_Germany)){
  raw_CAM_Germany[[i]] <- jsonlite::fromJSON(txt = dat_CAM_Germany[[i]])
}

Create CAM files, draw CAMs and compute network indicators

########################################
# create CAM single files (nodes, connectors, merged)
########################################
CAMfiles_Germany <- create_CAMfiles(datCAM = raw_CAM_Germany, reDeleted = TRUE)

Nodes and connectors, which were deleted by participants were removed. 
 # deleted nodes:  127 
 # deleted connectors:  57

########################################
# draw CAMs
########################################
CAMdrawn_Germany <- draw_CAM(dat_merged = CAMfiles_Germany[[3]],
                     dat_nodes = CAMfiles_Germany[[1]],ids_CAMs = "all",
                     plot_CAM = FALSE,
                     useCoordinates = TRUE,
                     relvertexsize = 3,
                     reledgesize = 1)

processing 75 CAMs... 
[1] "== ids_CAMs in drawnCAM"

########################################
# draw CAMs
########################################
tmp_microIndicator <- c("Klimawandel")
networkIndicators_Germany <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_Germany, 
                                           micro_degree = tmp_microIndicator, 
                                           micro_valence = tmp_microIndicator, 
                                           micro_centr_clo = tmp_microIndicator, 
                                           micro_transitivity = tmp_microIndicator, 
                                           largestClique = FALSE)


########################################
# wordlists
########################################
CAMwordlist_Germany <- create_wordlist(
  dat_nodes =  CAMfiles_Germany[[1]],
  dat_merged =  CAMfiles_Germany[[3]],
  order = "frequency",
  splitByValence = FALSE,
  comments = TRUE,
  raterSubsetWords = NULL,
  rater = FALSE
)

processing 75 CAMs... 
[1] "== ids_CAMs in drawnCAM"

DT::datatable(CAMwordlist_Germany, options = list(pageLength = 5))

save CAMs as .json files, and as .png (igraph)

save_CAMs_as_pictures = FALSE

if(save_CAMs_as_pictures){
  setwd("outputs")

setwd("savedCAMs_Germany")
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_Germany[[3]]$participantCAM.x == "noID")){
  CAMfiles_Germany[[3]]$participantCAM.x <- CAMfiles_Germany[[3]]$CAM.x
}

### save as .json files, and as .png (igraph)
ids_CAMs <- unique(CAMfiles_Germany[[3]]$participantCAM.x); length(ids_CAMs)


for(i in 1:length(ids_CAMs)){
  save_graphic(filename = paste0(ids_CAMs[i]))
  CAM_igraph <- CAMdrawn_Germany[[c(1:length(CAMdrawn_Germany))[
    names(CAMdrawn_Germany) == paste0(unique(CAMfiles_Germany[[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_Germany)){
  if(!is_empty(raw_CAM_Germany[[i]]$nodes)){
    if(nrow(raw_CAM_Germany[[i]]$nodes) > 5){
      write(toJSON(raw_CAM_Germany[[i]], encoding = "UTF-8"),
            paste0(raw_CAM_Germany[[i]]$idCAM, ".json"))
    }
  }
}
}

for USA

setwd("outputs")
suppressMessages(read_file("CAMdata_USA.txt") %>%
  # ... split it into lines ...
  str_split('\n') %>% first() %>%
                   # ... filter empty rows ...
                   discard(function(x) x == '') %>%
                   discard(function(x) x == '\r')) -> dat_CAM_USA

raw_CAM_USA <- list()
for(i in 1:length(dat_CAM_USA)){
  raw_CAM_USA[[i]] <- jsonlite::fromJSON(txt = dat_CAM_USA[[i]])
}

Create CAM files, draw CAMs and compute network indicators

########################################
# create CAM single files (nodes, connectors, merged)
########################################
CAMfiles_USA <- create_CAMfiles(datCAM = raw_CAM_USA, reDeleted = TRUE)

Nodes and connectors, which were deleted by participants were removed. 
 # deleted nodes:  73 
 # deleted connectors:  22

########################################
# draw CAMs
########################################
CAMdrawn_USA <- draw_CAM(dat_merged = CAMfiles_USA[[3]],
                     dat_nodes = CAMfiles_USA[[1]],ids_CAMs = "all",
                     plot_CAM = FALSE,
                     useCoordinates = TRUE,
                     relvertexsize = 3,
                     reledgesize = 1)

processing 49 CAMs... 
[1] "== ids_CAMs in drawnCAM"

########################################
# draw CAMs
########################################
tmp_microIndicator <- c("Climate Change")
networkIndicators_USA <- compute_indicatorsCAM(drawn_CAM = CAMdrawn_USA, 
                                           micro_degree = tmp_microIndicator, 
                                           micro_valence = tmp_microIndicator, 
                                           micro_centr_clo = tmp_microIndicator, 
                                           micro_transitivity = tmp_microIndicator, 
                                           largestClique = FALSE)

########################################
# wordlists
########################################
CAMwordlist_USA <- create_wordlist(
  dat_nodes =  CAMfiles_USA[[1]],
  dat_merged =  CAMfiles_USA[[3]],
  order = "frequency",
  splitByValence = FALSE,
  comments = TRUE,
  raterSubsetWords = NULL,
  rater = FALSE
)

processing 49 CAMs... 
[1] "== ids_CAMs in drawnCAM"

DT::datatable(CAMwordlist_USA, options = list(pageLength = 5))

save CAMs as .json files, and as .png (igraph)

save_CAMs_as_pictures = FALSE

if(save_CAMs_as_pictures){
  setwd("outputs")

setwd("savedCAMs_USA")
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_USA[[3]]$participantCAM.x == "noID")){
  CAMfiles_USA[[3]]$participantCAM.x <- CAMfiles_USA[[3]]$CAM.x
}

### save as .json files, and as .png (igraph)
ids_CAMs <- unique(CAMfiles_USA[[3]]$participantCAM.x); length(ids_CAMs)


for(i in 1:length(ids_CAMs)){
  save_graphic(filename = paste0(ids_CAMs[i]))
  CAM_igraph <- CAMdrawn_USA[[c(1:length(CAMdrawn_USA))[
    names(CAMdrawn_USA) == paste0(unique(CAMfiles_USA[[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_USA)){
  if(!is_empty(raw_CAM_USA[[i]]$nodes)){
    if(nrow(raw_CAM_USA[[i]]$nodes) > 5){
      write(toJSON(raw_CAM_USA[[i]], encoding = "UTF-8"),
            paste0(raw_CAM_USA[[i]]$idCAM, ".json"))
    }
  }
}
}