Load and clean
data
new_path = "Qualitrics/FB Misinfo Stimuli Pilot_July 31, 2023_16.34.sav"
#old_path = "Qualitrics/FB Misinfo Stimuli Pilot_July 27, 2023_18.29.sav"
#old_data = read_sav(old_path) |> mutate(old_data = TRUE)
#new_data = read_sav(new_path) |> mutate(new_data = TRUE)
#dt = merge(old_data, new_data, all = TRUE) |>
# mutate(across(c(old_data, new_data), ~ifelse(is.na(.x), FALSE, .x)))
# Load data
data = read_sav(new_path) |>
rename(ProlificID = Q109) |>
filter(Finished == 1, !is.na(ProlificID)) |>
filter(
!(ResponseId %in% c("R_1hFLVlyOvoORO7X", "R_3erVa4BDzEtxiWS"))
)
cat("Number of finished participants:", data |> nrow(), "\n")
## Number of finished participants: 103
# Extract column labels
col_labels = lapply(data, function(x) attributes(x)$label)
col_labels = data.frame(
Variable = names(data),
Label = col_labels |> unlist() |> as.character()
) |> mutate(
q_number = str_extract(Variable, "\\d+"))
col_labels = col_labels |> mutate(
q_type = case_when(
str_detect(Label, "share") ~ "share",
str_detect(Label, "manipulative") ~ "manipulative",
str_detect(Label, "reliable") ~ "reliable",
str_detect(Label, "concerning") ~ "concerning",
str_detect(Label, "might see") ~ "might_see",
str_detect(Label, "easy to understand") ~ "easy_to_understand",
str_detect(Label, "feedback") ~ "feedback"
)
)
col_labels$q_type[is.na(col_labels$q_type)] = "other"
opinions = data[, (col_labels$Variable == "ResponseId") | (col_labels$q_type %in% c("share", "manipulative", "reliable", "misleading", "concerning", "might_see", "easy_to_understand"))]
# Convert labeled to numeric
opinions = opinions |> mutate_at(vars(-ResponseId), as.numeric)
# Pivot data
opinions = opinions |> pivot_longer(
cols = -ResponseId,
names_to = "Variable",
values_to = "opinion"
)
# Merge with labels
opinions = opinions |> left_join(col_labels |> select(Variable, q_type, q_number), by = "Variable")
# Group variables into posts
opinions = opinions |> arrange(ResponseId, q_number) |>
mutate(
post_number = case_when(
q_number %in% 255:260 ~ 1,
q_number %in% 493:498 ~ 2,
q_number %in% 507:512 ~ 3,
q_number %in% 521:526 ~ 4,
q_number %in% 535:540 ~ 5,
q_number %in% 549:554 ~ 6,
q_number %in% 563:568 ~ 7,
q_number %in% 577:582 ~ 8,
q_number %in% 591:596 ~ 9,
q_number %in% 605:610 ~ 10,
q_number %in% 619:624 ~ 11,
q_number %in% 633:638 ~ 12,
q_number %in% 647:652 ~ 13,
q_number %in% 661:666 ~ 14,
q_number %in% 675:680 ~ 15,
q_number %in% 689:694 ~ 16,
q_number %in% 703:708 ~ 17,
q_number %in% 717:722 ~ 18,
q_number %in% 731:736 ~ 19,
q_number %in% 745:750 ~ 20,
q_number %in% 759:764 ~ 21,
q_number %in% 773:778 ~ 22,
q_number %in% 787:792 ~ 23,
q_number %in% 801:806 ~ 24,
q_number %in% 815:820 ~ 25,
q_number %in% 829:834 ~ 26,
q_number %in% 843:848 ~ 27,
q_number %in% 857:862 ~ 28,
q_number %in% 871:876 ~ 29),
post_type = case_when(
post_number %in% 1:13 ~ "Non Misinfo",
post_number %in% 14:18 ~ "Discrediting",
post_number %in% 19:23 ~ "False Dichotomy",
post_number %in% 24:29 ~ "Emotional")
)
nice_labels = data.frame(
variable = c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"),
Variable = c("Manipulative", "Reliable", "Concerning", "Easy to Understand", "Might See", "Would Share")
)
post_types = opinions |> select(post_number, post_type) |> distinct()
# Select feedback variables
feedback = data[, (col_labels$Variable == "ResponseId") | (col_labels$q_type == "feedback")]
feedback = feedback |>
# Now pivot to long
pivot_longer(
cols = -ResponseId,
names_to = "question",
values_to = "feedback"
) |>
# Merge with labels
left_join(
data.frame(
post_number = 1:29,
question = names(feedback)[2:30]
)
)
valid_feedback = feedback |> filter(feedback != "", feedback != "no feed back", feedback != "na") |>
filter(str_length(feedback) > 6) |>
group_by(ResponseId) |>
mutate(n_valid_feedback = n()) |>
ungroup() |>
# Now merge post_type
left_join(post_types, by = "post_number")
valid_feedback |> select(ResponseId, post_number, feedback) |>
arrange(post_number) |>
write_csv("Qualitrics/valid_feedback.csv")
valid_feedback |> filter(n_valid_feedback == max(n_valid_feedback)) |>
distinct(ResponseId, n_valid_feedback) |>
left_join(data |> select(ResponseId, ProlificID)) |>
write_csv("Qualitrics/valid_feedback_ProlificIds.csv")
# Pivot data to wider by ResponseID+post_number
opinions = opinions |>
select(ResponseId, post_number, post_type, opinion, q_type) |>
pivot_wider(
id_cols = c(ResponseId, post_number, post_type),
names_from = q_type,
values_from = opinion
)
#recode variables
opinions = opinions |> mutate(
share = case_when(
share == 1 ~ 1,
share == 2 ~ 0,
),
reliable_orig = reliable,
reliable = case_when(
reliable_orig == 1 ~ 1,
reliable_orig == 2 ~ 2,
reliable_orig == 7 ~ 3,
reliable_orig == 3 ~ 4,
reliable_orig == 8 ~ 5,
reliable_orig == 9 ~ 6,
reliable_orig == 11 ~ 7,
),
might_see_orig = might_see,
might_see = case_when(
might_see_orig == 1 ~ 1,
might_see_orig == 4 ~ 0,
might_see_orig == 2 ~ 0.5,
might_see_orig == 3 ~ 0.5,
)
) |> select(-reliable_orig, -might_see_orig)
Analyze the data
Descriptive
statistics by post
# Calculate mean for each post and number of participants
sum_stats_post = opinions |>
group_by(post_number, post_type) |>
summarise(
across(c("share", "manipulative", "reliable", "concerning", "easy_to_understand", "might_see"), mean, na.r = TRUE),
n = n()
) |> #now round to 2 decimals
mutate(across(c("share", "manipulative", "reliable", "concerning", "easy_to_understand", "might_see"), round, 2)) |>
rename(
Manipulative = manipulative,
Reliable = reliable,
Concerning = concerning,
`Easy tounderstand` = easy_to_understand,
`Might see` = might_see
)
sum_stats_post |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
post_number
|
post_type
|
share
|
Manipulative
|
Reliable
|
Concerning
|
Easy tounderstand
|
Might see
|
n
|
|
1
|
Non Misinfo
|
0.27
|
4.15
|
3.17
|
5.51
|
5.83
|
0.44
|
103
|
|
2
|
Non Misinfo
|
0.58
|
2.89
|
4.76
|
5.32
|
6.26
|
0.74
|
103
|
|
3
|
Non Misinfo
|
0.31
|
3.16
|
3.72
|
4.89
|
6.12
|
0.54
|
103
|
|
4
|
Non Misinfo
|
0.31
|
3.73
|
3.60
|
4.85
|
6.32
|
0.49
|
103
|
|
5
|
Non Misinfo
|
0.43
|
3.57
|
3.79
|
5.12
|
6.30
|
0.57
|
103
|
|
6
|
Non Misinfo
|
0.60
|
3.13
|
4.77
|
4.80
|
6.26
|
0.72
|
103
|
|
7
|
Non Misinfo
|
0.33
|
2.66
|
3.76
|
3.18
|
5.59
|
0.44
|
103
|
|
8
|
Non Misinfo
|
0.70
|
2.59
|
5.17
|
4.85
|
6.41
|
0.77
|
103
|
|
9
|
Non Misinfo
|
0.56
|
3.60
|
5.10
|
5.29
|
6.41
|
0.67
|
103
|
|
10
|
Non Misinfo
|
0.50
|
3.12
|
4.65
|
4.91
|
6.41
|
0.62
|
103
|
|
11
|
Non Misinfo
|
0.55
|
3.22
|
4.48
|
5.53
|
6.30
|
0.66
|
103
|
|
12
|
Non Misinfo
|
0.26
|
3.11
|
3.13
|
2.66
|
6.12
|
0.65
|
103
|
|
13
|
Non Misinfo
|
0.31
|
3.85
|
3.52
|
5.32
|
5.80
|
0.54
|
103
|
|
14
|
Discrediting
|
0.50
|
4.02
|
4.35
|
5.17
|
6.44
|
0.69
|
103
|
|
15
|
Discrediting
|
0.23
|
3.97
|
3.13
|
4.66
|
4.63
|
0.43
|
103
|
|
16
|
Discrediting
|
0.12
|
5.38
|
2.28
|
4.90
|
5.82
|
0.43
|
103
|
|
17
|
Discrediting
|
0.32
|
4.42
|
3.78
|
5.49
|
6.16
|
0.67
|
103
|
|
18
|
Discrediting
|
0.60
|
3.38
|
5.39
|
5.22
|
6.66
|
0.86
|
103
|
|
19
|
False Dichotomy
|
0.28
|
3.14
|
3.36
|
3.19
|
5.64
|
0.69
|
103
|
|
20
|
False Dichotomy
|
0.16
|
5.56
|
2.71
|
4.46
|
6.34
|
0.72
|
103
|
|
21
|
False Dichotomy
|
0.31
|
5.68
|
3.83
|
5.25
|
6.06
|
0.70
|
103
|
|
22
|
False Dichotomy
|
0.12
|
5.35
|
2.59
|
5.35
|
5.55
|
0.61
|
103
|
|
23
|
False Dichotomy
|
0.46
|
3.88
|
4.15
|
5.79
|
6.29
|
0.67
|
103
|
|
24
|
Emotional
|
0.40
|
4.44
|
3.40
|
6.09
|
6.14
|
0.69
|
103
|
|
25
|
Emotional
|
0.45
|
2.96
|
4.51
|
6.45
|
6.24
|
0.78
|
103
|
|
26
|
Emotional
|
0.48
|
4.41
|
3.83
|
5.91
|
6.43
|
0.75
|
103
|
|
27
|
Emotional
|
0.13
|
5.91
|
2.46
|
5.13
|
6.18
|
0.64
|
103
|
|
28
|
Emotional
|
0.27
|
3.67
|
3.52
|
5.17
|
6.16
|
0.67
|
103
|
|
29
|
Emotional
|
0.47
|
4.04
|
4.47
|
5.59
|
6.49
|
0.74
|
103
|
Descriptive
statistics by post-type
opinions |>
select(post_type, all_of(c("share", "manipulative", "reliable", "concerning", "easy_to_understand", "might_see"))) |>
# now pivot long
pivot_longer(cols = -post_type, names_to = "variable", values_to = "opinion") |>
group_by(post_type, variable) |>
# Compute mean, standard deviation, number non-missing, q25 and q75
summarise(
mean = mean(opinion, na.rm = TRUE),
sd = sd(opinion, na.rm = TRUE),
n = n(),
q25 = quantile(opinion, probs = 0.25, na.rm = TRUE),
q75 = quantile(opinion, probs = 0.75, na.rm = TRUE)
) |> #now round to 2 decimals
mutate(across(c("mean", "sd", "q25", "q75"), round, 2)) |>
left_join(nice_labels, by.x = "variable") |>
select(
`Post Type` = post_type, Variable, `Mean` = mean, `SD` = sd, `N` = n, q25, q75
) |>
kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
Post Type
|
Variable
|
Mean
|
SD
|
N
|
q25
|
q75
|
|
Discrediting
|
Concerning
|
5.09
|
1.99
|
515
|
4.0
|
7.00
|
|
Discrediting
|
Easy to Understand
|
5.94
|
1.65
|
515
|
5.0
|
7.00
|
|
Discrediting
|
Manipulative
|
4.23
|
2.18
|
515
|
2.0
|
6.00
|
|
Discrediting
|
Might See
|
0.62
|
0.39
|
515
|
0.5
|
1.00
|
|
Discrediting
|
Reliable
|
3.78
|
2.04
|
515
|
2.0
|
5.00
|
|
Discrediting
|
Would Share
|
0.35
|
0.48
|
515
|
0.0
|
1.00
|
|
Emotional
|
Concerning
|
5.72
|
1.76
|
618
|
5.0
|
7.00
|
|
Emotional
|
Easy to Understand
|
6.27
|
1.27
|
618
|
6.0
|
7.00
|
|
Emotional
|
Manipulative
|
4.24
|
2.21
|
618
|
2.0
|
6.75
|
|
Emotional
|
Might See
|
0.71
|
0.25
|
618
|
0.5
|
1.00
|
|
Emotional
|
Reliable
|
3.70
|
2.00
|
618
|
2.0
|
5.00
|
|
Emotional
|
Would Share
|
0.36
|
0.48
|
618
|
0.0
|
1.00
|
|
False Dichotomy
|
Concerning
|
4.81
|
2.16
|
515
|
3.0
|
7.00
|
|
False Dichotomy
|
Easy to Understand
|
5.98
|
1.66
|
515
|
5.0
|
7.00
|
|
False Dichotomy
|
Manipulative
|
4.72
|
2.18
|
515
|
3.0
|
7.00
|
|
False Dichotomy
|
Might See
|
0.68
|
0.24
|
515
|
0.5
|
1.00
|
|
False Dichotomy
|
Reliable
|
3.33
|
1.94
|
515
|
1.0
|
5.00
|
|
False Dichotomy
|
Would Share
|
0.26
|
0.44
|
515
|
0.0
|
1.00
|
|
Non Misinfo
|
Concerning
|
4.79
|
2.06
|
1339
|
3.0
|
7.00
|
|
Non Misinfo
|
Easy to Understand
|
6.16
|
1.31
|
1339
|
6.0
|
7.00
|
|
Non Misinfo
|
Manipulative
|
3.29
|
2.04
|
1339
|
1.0
|
5.00
|
|
Non Misinfo
|
Might See
|
0.60
|
0.38
|
1339
|
0.5
|
1.00
|
|
Non Misinfo
|
Reliable
|
4.12
|
1.91
|
1339
|
3.0
|
6.00
|
|
Non Misinfo
|
Would Share
|
0.44
|
0.50
|
1339
|
0.0
|
1.00
|
Distribution of Likert-Scale responses by outcome
bin_counts_post = opinions |>
group_by(post_number) |>
select(all_of(c("manipulative", "reliable", "concerning", "easy_to_understand"))) |> #now pivot to long
pivot_longer(cols = -post_number, names_to = "var", values_to = "opinion") |> #now count responses by post_number and var and opinion
group_by(post_number, var, opinion) |>
summarise(n = n()) |> #now pivot to wide
pivot_wider(names_from = opinion, values_from = n) |>
`colnames<-`(c("post_number", "variable", "1 -- not at all", "2", "3", "4", "5", "6", "7 -- very")) |>
ungroup() |>
left_join(nice_labels, by = "variable") |> # now replace NAs with 0
mutate_at(vars(-c("post_number", "variable", "Variable")), ~replace_na(., 0)) |>
left_join(post_types, by = "post_number") |> # now replace NAs with 0
select(`Post Number` = post_number, `Post Type` = post_type, all_of(c("Variable", "1 -- not at all", "2", "3", "4", "5", "6", "7 -- very")))
Manipulative
bin_counts_post |> filter(Variable == "Manipulative") |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>% scroll_box(height = "100%")
|
Post Number
|
Post Type
|
Variable
|
1 – not at all
|
2
|
3
|
4
|
5
|
6
|
7 – very
|
|
1
|
Non Misinfo
|
Manipulative
|
18
|
8
|
13
|
19
|
12
|
13
|
20
|
|
2
|
Non Misinfo
|
Manipulative
|
38
|
16
|
10
|
14
|
15
|
3
|
7
|
|
3
|
Non Misinfo
|
Manipulative
|
30
|
11
|
18
|
22
|
9
|
5
|
8
|
|
4
|
Non Misinfo
|
Manipulative
|
27
|
8
|
9
|
22
|
12
|
9
|
16
|
|
5
|
Non Misinfo
|
Manipulative
|
26
|
11
|
12
|
21
|
12
|
7
|
14
|
|
6
|
Non Misinfo
|
Manipulative
|
32
|
15
|
19
|
11
|
8
|
7
|
11
|
|
7
|
Non Misinfo
|
Manipulative
|
42
|
16
|
15
|
12
|
8
|
3
|
7
|
|
8
|
Non Misinfo
|
Manipulative
|
49
|
13
|
9
|
11
|
10
|
6
|
5
|
|
9
|
Non Misinfo
|
Manipulative
|
23
|
17
|
8
|
17
|
16
|
12
|
10
|
|
10
|
Non Misinfo
|
Manipulative
|
40
|
8
|
10
|
16
|
11
|
10
|
8
|
|
11
|
Non Misinfo
|
Manipulative
|
31
|
11
|
16
|
16
|
17
|
2
|
10
|
|
12
|
Non Misinfo
|
Manipulative
|
35
|
16
|
6
|
24
|
5
|
5
|
12
|
|
13
|
Non Misinfo
|
Manipulative
|
19
|
9
|
10
|
26
|
20
|
7
|
12
|
|
14
|
Discrediting
|
Manipulative
|
22
|
8
|
5
|
21
|
23
|
6
|
18
|
|
15
|
Discrediting
|
Manipulative
|
22
|
5
|
14
|
16
|
21
|
9
|
16
|
|
16
|
Discrediting
|
Manipulative
|
8
|
4
|
4
|
15
|
10
|
18
|
44
|
|
17
|
Discrediting
|
Manipulative
|
13
|
12
|
7
|
20
|
12
|
16
|
23
|
|
18
|
Discrediting
|
Manipulative
|
37
|
11
|
8
|
11
|
10
|
11
|
15
|
|
19
|
False Dichotomy
|
Manipulative
|
36
|
12
|
10
|
17
|
11
|
9
|
8
|
|
20
|
False Dichotomy
|
Manipulative
|
6
|
4
|
5
|
8
|
15
|
18
|
47
|
|
21
|
False Dichotomy
|
Manipulative
|
6
|
4
|
5
|
6
|
16
|
10
|
56
|
|
22
|
False Dichotomy
|
Manipulative
|
6
|
5
|
11
|
8
|
12
|
17
|
44
|
|
23
|
False Dichotomy
|
Manipulative
|
21
|
10
|
12
|
20
|
12
|
13
|
15
|
|
24
|
Emotional
|
Manipulative
|
16
|
7
|
7
|
22
|
12
|
15
|
24
|
|
25
|
Emotional
|
Manipulative
|
40
|
10
|
17
|
12
|
10
|
2
|
12
|
|
26
|
Emotional
|
Manipulative
|
16
|
11
|
6
|
19
|
12
|
11
|
28
|
|
27
|
Emotional
|
Manipulative
|
3
|
0
|
7
|
8
|
13
|
16
|
56
|
|
28
|
Emotional
|
Manipulative
|
25
|
11
|
10
|
17
|
19
|
9
|
12
|
|
29
|
Emotional
|
Manipulative
|
20
|
7
|
19
|
14
|
12
|
8
|
23
|
Reliable
bin_counts_post |> filter(Variable == "Reliable") |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>% scroll_box(height = "100%")
|
Post Number
|
Post Type
|
Variable
|
1 – not at all
|
2
|
3
|
4
|
5
|
6
|
7 – very
|
|
1
|
Non Misinfo
|
Reliable
|
25
|
16
|
19
|
24
|
7
|
3
|
9
|
|
2
|
Non Misinfo
|
Reliable
|
5
|
7
|
12
|
21
|
19
|
17
|
22
|
|
3
|
Non Misinfo
|
Reliable
|
17
|
13
|
13
|
25
|
17
|
10
|
8
|
|
4
|
Non Misinfo
|
Reliable
|
24
|
8
|
18
|
24
|
8
|
6
|
15
|
|
5
|
Non Misinfo
|
Reliable
|
16
|
8
|
19
|
31
|
7
|
12
|
10
|
|
6
|
Non Misinfo
|
Reliable
|
8
|
4
|
8
|
25
|
19
|
17
|
22
|
|
7
|
Non Misinfo
|
Reliable
|
15
|
10
|
16
|
27
|
21
|
7
|
7
|
|
8
|
Non Misinfo
|
Reliable
|
5
|
0
|
9
|
18
|
29
|
11
|
31
|
|
9
|
Non Misinfo
|
Reliable
|
6
|
2
|
12
|
19
|
14
|
17
|
33
|
|
10
|
Non Misinfo
|
Reliable
|
7
|
6
|
9
|
26
|
20
|
16
|
19
|
|
11
|
Non Misinfo
|
Reliable
|
10
|
7
|
11
|
22
|
21
|
13
|
19
|
|
12
|
Non Misinfo
|
Reliable
|
27
|
19
|
13
|
20
|
10
|
10
|
4
|
|
13
|
Non Misinfo
|
Reliable
|
16
|
14
|
17
|
27
|
18
|
7
|
4
|
|
14
|
Discrediting
|
Reliable
|
10
|
7
|
15
|
26
|
14
|
12
|
19
|
|
15
|
Discrediting
|
Reliable
|
27
|
12
|
22
|
21
|
11
|
4
|
6
|
|
16
|
Discrediting
|
Reliable
|
53
|
11
|
14
|
13
|
7
|
4
|
1
|
|
17
|
Discrediting
|
Reliable
|
19
|
10
|
13
|
23
|
18
|
11
|
9
|
|
18
|
Discrediting
|
Reliable
|
1
|
6
|
7
|
16
|
20
|
14
|
39
|
|
19
|
False Dichotomy
|
Reliable
|
26
|
11
|
14
|
29
|
9
|
3
|
11
|
|
20
|
False Dichotomy
|
Reliable
|
35
|
18
|
17
|
19
|
6
|
5
|
3
|
|
21
|
False Dichotomy
|
Reliable
|
17
|
11
|
16
|
21
|
15
|
12
|
11
|
|
22
|
False Dichotomy
|
Reliable
|
46
|
13
|
14
|
13
|
6
|
6
|
5
|
|
23
|
False Dichotomy
|
Reliable
|
14
|
9
|
10
|
25
|
17
|
16
|
12
|
|
24
|
Emotional
|
Reliable
|
26
|
13
|
12
|
22
|
14
|
8
|
8
|
|
25
|
Emotional
|
Reliable
|
4
|
9
|
14
|
23
|
23
|
16
|
14
|
|
26
|
Emotional
|
Reliable
|
23
|
8
|
9
|
24
|
16
|
8
|
15
|
|
27
|
Emotional
|
Reliable
|
51
|
16
|
13
|
6
|
3
|
6
|
8
|
|
28
|
Emotional
|
Reliable
|
17
|
19
|
12
|
26
|
10
|
15
|
4
|
|
29
|
Emotional
|
Reliable
|
12
|
7
|
8
|
24
|
19
|
12
|
21
|
Concerning
bin_counts_post |> filter(Variable == "Concerning") |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>% scroll_box(height = "100%")
|
Post Number
|
Post Type
|
Variable
|
1 – not at all
|
2
|
3
|
4
|
5
|
6
|
7 – very
|
|
1
|
Non Misinfo
|
Concerning
|
7
|
1
|
5
|
9
|
22
|
15
|
44
|
|
2
|
Non Misinfo
|
Concerning
|
5
|
4
|
8
|
16
|
13
|
17
|
40
|
|
3
|
Non Misinfo
|
Concerning
|
8
|
2
|
13
|
13
|
26
|
16
|
25
|
|
4
|
Non Misinfo
|
Concerning
|
15
|
4
|
4
|
18
|
14
|
13
|
35
|
|
5
|
Non Misinfo
|
Concerning
|
8
|
4
|
8
|
17
|
17
|
9
|
40
|
|
6
|
Non Misinfo
|
Concerning
|
11
|
6
|
4
|
21
|
19
|
14
|
28
|
|
7
|
Non Misinfo
|
Concerning
|
28
|
21
|
13
|
11
|
14
|
7
|
9
|
|
8
|
Non Misinfo
|
Concerning
|
9
|
9
|
6
|
17
|
16
|
15
|
31
|
|
9
|
Non Misinfo
|
Concerning
|
7
|
5
|
4
|
13
|
19
|
16
|
39
|
|
10
|
Non Misinfo
|
Concerning
|
10
|
5
|
10
|
11
|
21
|
15
|
31
|
|
11
|
Non Misinfo
|
Concerning
|
4
|
3
|
6
|
11
|
17
|
21
|
41
|
|
12
|
Non Misinfo
|
Concerning
|
44
|
15
|
13
|
11
|
9
|
5
|
6
|
|
13
|
Non Misinfo
|
Concerning
|
5
|
5
|
6
|
15
|
14
|
21
|
37
|
|
14
|
Discrediting
|
Concerning
|
13
|
3
|
4
|
11
|
12
|
23
|
37
|
|
15
|
Discrediting
|
Concerning
|
12
|
4
|
6
|
29
|
13
|
12
|
27
|
|
16
|
Discrediting
|
Concerning
|
12
|
5
|
10
|
11
|
16
|
14
|
35
|
|
17
|
Discrediting
|
Concerning
|
6
|
4
|
3
|
10
|
22
|
14
|
44
|
|
18
|
Discrediting
|
Concerning
|
10
|
2
|
10
|
12
|
11
|
15
|
43
|
|
19
|
False Dichotomy
|
Concerning
|
32
|
15
|
11
|
18
|
9
|
9
|
9
|
|
20
|
False Dichotomy
|
Concerning
|
19
|
5
|
9
|
13
|
17
|
14
|
26
|
|
21
|
False Dichotomy
|
Concerning
|
7
|
6
|
7
|
10
|
17
|
16
|
40
|
|
22
|
False Dichotomy
|
Concerning
|
12
|
2
|
1
|
12
|
17
|
14
|
45
|
|
23
|
False Dichotomy
|
Concerning
|
6
|
0
|
7
|
5
|
12
|
22
|
51
|
|
24
|
Emotional
|
Concerning
|
4
|
0
|
1
|
6
|
15
|
18
|
59
|
|
25
|
Emotional
|
Concerning
|
2
|
1
|
1
|
4
|
3
|
18
|
74
|
|
26
|
Emotional
|
Concerning
|
4
|
4
|
2
|
7
|
11
|
17
|
58
|
|
27
|
Emotional
|
Concerning
|
14
|
3
|
9
|
7
|
12
|
13
|
45
|
|
28
|
Emotional
|
Concerning
|
9
|
2
|
7
|
14
|
19
|
16
|
36
|
|
29
|
Emotional
|
Concerning
|
6
|
4
|
1
|
10
|
15
|
25
|
42
|
Easy to
understand
bin_counts_post |> filter(Variable == "Easy to Understand") |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>% scroll_box(height = "100%")
|
Post Number
|
Post Type
|
Variable
|
1 – not at all
|
2
|
3
|
4
|
5
|
6
|
7 – very
|
|
1
|
Non Misinfo
|
Easy to Understand
|
3
|
1
|
7
|
9
|
13
|
16
|
54
|
|
2
|
Non Misinfo
|
Easy to Understand
|
1
|
1
|
4
|
4
|
10
|
17
|
66
|
|
3
|
Non Misinfo
|
Easy to Understand
|
1
|
2
|
2
|
4
|
19
|
17
|
58
|
|
4
|
Non Misinfo
|
Easy to Understand
|
0
|
1
|
3
|
6
|
9
|
17
|
67
|
|
5
|
Non Misinfo
|
Easy to Understand
|
1
|
1
|
2
|
5
|
10
|
18
|
66
|
|
6
|
Non Misinfo
|
Easy to Understand
|
2
|
2
|
1
|
5
|
10
|
15
|
68
|
|
7
|
Non Misinfo
|
Easy to Understand
|
3
|
2
|
9
|
8
|
18
|
21
|
42
|
|
8
|
Non Misinfo
|
Easy to Understand
|
0
|
1
|
4
|
4
|
5
|
18
|
71
|
|
9
|
Non Misinfo
|
Easy to Understand
|
1
|
1
|
1
|
3
|
8
|
21
|
68
|
|
10
|
Non Misinfo
|
Easy to Understand
|
0
|
1
|
2
|
3
|
11
|
17
|
69
|
|
11
|
Non Misinfo
|
Easy to Understand
|
2
|
0
|
1
|
4
|
11
|
22
|
63
|
|
12
|
Non Misinfo
|
Easy to Understand
|
2
|
3
|
1
|
6
|
12
|
18
|
61
|
|
13
|
Non Misinfo
|
Easy to Understand
|
2
|
0
|
7
|
11
|
17
|
17
|
49
|
|
14
|
Discrediting
|
Easy to Understand
|
2
|
0
|
2
|
3
|
8
|
13
|
75
|
|
15
|
Discrediting
|
Easy to Understand
|
14
|
6
|
13
|
12
|
14
|
14
|
30
|
|
16
|
Discrediting
|
Easy to Understand
|
4
|
4
|
3
|
11
|
8
|
17
|
56
|
|
17
|
Discrediting
|
Easy to Understand
|
1
|
3
|
4
|
2
|
11
|
22
|
60
|
|
18
|
Discrediting
|
Easy to Understand
|
0
|
0
|
0
|
1
|
10
|
12
|
80
|
|
19
|
False Dichotomy
|
Easy to Understand
|
9
|
0
|
5
|
10
|
11
|
14
|
54
|
|
20
|
False Dichotomy
|
Easy to Understand
|
2
|
0
|
3
|
4
|
9
|
14
|
71
|
|
21
|
False Dichotomy
|
Easy to Understand
|
6
|
3
|
1
|
5
|
6
|
15
|
67
|
|
22
|
False Dichotomy
|
Easy to Understand
|
6
|
7
|
3
|
8
|
15
|
12
|
52
|
|
23
|
False Dichotomy
|
Easy to Understand
|
2
|
2
|
2
|
1
|
13
|
14
|
69
|
|
24
|
Emotional
|
Easy to Understand
|
3
|
2
|
2
|
5
|
8
|
22
|
61
|
|
25
|
Emotional
|
Easy to Understand
|
3
|
0
|
3
|
3
|
10
|
19
|
65
|
|
26
|
Emotional
|
Easy to Understand
|
2
|
0
|
0
|
6
|
7
|
15
|
73
|
|
27
|
Emotional
|
Easy to Understand
|
3
|
1
|
2
|
4
|
12
|
17
|
64
|
|
28
|
Emotional
|
Easy to Understand
|
2
|
0
|
1
|
4
|
21
|
17
|
58
|
|
29
|
Emotional
|
Easy to Understand
|
1
|
0
|
2
|
1
|
10
|
16
|
73
|
Distribution of
Likert-Scale responses by post-type
bin_counts = opinions |>
group_by(post_type) |>
select(all_of(c("manipulative", "reliable", "concerning", "easy_to_understand"))) |> #now pivot to long
pivot_longer(cols = -post_type, names_to = "var", values_to = "opinion") |> #now count responses by post_type and var and opinion
group_by(post_type, var, opinion) |>
summarise(n = n()) |> #now pivot to wide
pivot_wider(names_from = opinion, values_from = n) |>
`colnames<-`(c("Post Type", "variable", "1 -- not at all", "2", "3", "4", "5", "6", "7 -- very")) |>
ungroup() |>
left_join(nice_labels, by = "variable") |>
select(all_of(c("Post Type", "Variable", "1 -- not at all", "2", "3", "4", "5", "6", "7 -- very")))
bin_counts |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
Post Type
|
Variable
|
1 – not at all
|
2
|
3
|
4
|
5
|
6
|
7 – very
|
|
Discrediting
|
Concerning
|
53
|
18
|
33
|
73
|
74
|
78
|
186
|
|
Discrediting
|
Easy to Understand
|
21
|
13
|
22
|
29
|
51
|
78
|
301
|
|
Discrediting
|
Manipulative
|
102
|
40
|
38
|
83
|
76
|
60
|
116
|
|
Discrediting
|
Reliable
|
110
|
46
|
71
|
99
|
70
|
45
|
74
|
|
Emotional
|
Concerning
|
39
|
14
|
21
|
48
|
75
|
107
|
314
|
|
Emotional
|
Easy to Understand
|
14
|
3
|
10
|
23
|
68
|
106
|
394
|
|
Emotional
|
Manipulative
|
120
|
46
|
66
|
92
|
78
|
61
|
155
|
|
Emotional
|
Reliable
|
133
|
72
|
68
|
125
|
85
|
65
|
70
|
|
False Dichotomy
|
Concerning
|
76
|
28
|
35
|
58
|
72
|
75
|
171
|
|
False Dichotomy
|
Easy to Understand
|
25
|
12
|
14
|
28
|
54
|
69
|
313
|
|
False Dichotomy
|
Manipulative
|
75
|
35
|
43
|
59
|
66
|
67
|
170
|
|
False Dichotomy
|
Reliable
|
138
|
62
|
71
|
107
|
53
|
42
|
42
|
|
Non Misinfo
|
Concerning
|
161
|
84
|
100
|
183
|
221
|
184
|
406
|
|
Non Misinfo
|
Easy to Understand
|
18
|
16
|
44
|
72
|
153
|
234
|
802
|
|
Non Misinfo
|
Manipulative
|
410
|
159
|
155
|
231
|
155
|
89
|
140
|
|
Non Misinfo
|
Reliable
|
181
|
114
|
176
|
309
|
210
|
146
|
203
|
Corelations between
variables
# Calculate bivariate correlations and present as a heatmap using ggplot
# Rename variables to more readable names
opinions |>
select(
manipulative, reliable, concerning, easy_to_understand, might_see, share
) |>
na.omit() |>
cor(use = "pairwise.complete.obs") |>
as.data.frame() |>
rename(
Manipulative = manipulative,
Reliable = reliable,
Concerning = concerning,
`Easy tounderstand` = easy_to_understand,
`Might see` = might_see
) |>
rownames_to_column("var1") |>
pivot_longer(cols = -var1, names_to = "var2", values_to = "cor") |>
ggplot(aes(x = var1, y = var2, fill = cor)) +
geom_tile() +
geom_text(aes(label = round(cor, 2)), size = 3) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0) +
theme_minimal() +
theme(axis.text.x = element_text(angle = 90, vjust = 0.5, hjust = 1)) +
labs(x = "", y = "", title = "Correlations between variables")

Some
observations
- Manipulative posts are harder to understand and more concerning but
(understandably) seen as less reliable and, less likely to be seen on
one’s timeline and less likely to be shared
- Sharing intention most correlated with reliability and likelihood of
seeing the post on one’s timeline.
Covariate heatmap
by post type
mean_diffs = opinions |>
select(post_type, all_of(c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"))) |> #now pivot to long
pivot_longer(cols = -post_type, names_to = "variable", values_to = "opinion") |>
# calculate grand means by variable and by variable-post_type
group_by(variable) |>
mutate(grand_mean = mean(opinion, na.rm = TRUE)) |>
group_by(variable, post_type) |>
mutate(
group_mean = mean(opinion, na.rm = TRUE),
group_se = sd(opinion, na.rm = TRUE)/sqrt(n())
) |>
# group diferences from grand mean
mutate(group_diff = group_mean - grand_mean) |>
# now pivot to wide
distinct(
variable, post_type, group_diff, group_se
)
# Plot heatmap with SDs in parentheses below
library(ggtext)
mean_diffs |>
ggplot(aes(x = post_type, y = variable)) +
geom_tile(aes(fill = group_diff), color = "white") +
geom_text(aes(label = paste0(round(group_diff, 2), "\n(", round(group_se, 2), ")")),
vjust =0,
colour = "black",
size = 2,
lineheight = 0.9) +
labs(title = "Opinions Heatmap",
x = "Post Type",
y = "Variable") +
theme_minimal() +
theme(axis.text.x = element_text(angle = 45, hjust = 1),
plot.title = element_text(hjust = 0.5)) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0)

ggsave("opinions_heatmap.png", width = 10, height = 10, units = "in")
Coviariate heatmap by post (within post type)
Non-misinfo
opinions |>
filter(post_type == "Non Misinfo") |>
select(post_number, all_of(c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"))) |> #now pivot to long
pivot_longer(cols = -post_number, names_to = "variable", values_to = "opinion") |>
group_by(variable) |>
mutate(grand_mean = mean(opinion, na.rm = TRUE)) |>
group_by(variable, post_number) |>
mutate(
group_mean = mean(opinion, na.rm = TRUE),
group_diff = group_mean - grand_mean,
group_se = sd(opinion, na.rm = TRUE)/sqrt(n())
) |>
distinct(variable, post_number, group_diff, group_se) |>
ggplot(aes(y = variable, x = post_number, fill = group_diff)) +
geom_tile() +
geom_text(aes(label = paste0(round(group_diff, 2), " \n (", round(group_se, 2), ")")),
vjust =0,
colour = "black",
size = 2,
lineheight = 0.9) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0) +
theme_minimal() +
theme(axis.text.x = element_text(vjust = 0.5, hjust = 1)) +
labs(y = "Feeling", x = "Question Number", title = "Differences from Post-Type group mean by post number, Non-Misinfo")

ggsave("opinions_heatmap.png", width = 15, height = 10, units = "in")
Discrediting
opinions |>
filter(post_type == "Non Misinfo") |>
select(post_number, all_of(c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"))) |> #now pivot to long
pivot_longer(cols = -post_number, names_to = "variable", values_to = "opinion") |>
group_by(variable) |>
mutate(grand_mean = mean(opinion, na.rm = TRUE)) |>
group_by(variable, post_number) |>
mutate(
group_mean = mean(opinion, na.rm = TRUE),
group_diff = group_mean - grand_mean,
group_se = sd(opinion, na.rm = TRUE)/sqrt(n())
) |>
distinct(variable, post_number, group_diff, group_se) |>
ggplot(aes(y = variable, x = post_number, fill = group_diff)) +
geom_tile() +
geom_text(aes(label = paste0(round(group_diff, 2), " \n (", round(group_se, 2), ")")),
vjust = 0,
colour = "black",
size = 2,
lineheight = 0.9) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0) +
theme_minimal() +
theme(axis.text.x = element_text(vjust = 0.5, hjust = 1)) +
labs(y = "Feeling", x = "Question Number", title = "Differences from Post-Type group mean by post number, Discrediting")

False
Dichotomy
opinions |>
filter(post_type == "Non Misinfo") |>
select(post_number, all_of(c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"))) |> #now pivot to long
pivot_longer(cols = -post_number, names_to = "variable", values_to = "opinion") |>
group_by(variable) |>
mutate(grand_mean = mean(opinion, na.rm = TRUE)) |>
group_by(variable, post_number) |>
mutate(
group_mean = mean(opinion, na.rm = TRUE),
group_diff = group_mean - grand_mean,
group_se = sd(opinion, na.rm = TRUE)/sqrt(n())
) |>
distinct(variable, post_number, group_diff, group_se) |>
ggplot(aes(y = variable, x = post_number, fill = group_diff)) +
geom_tile() +
geom_text(aes(label = paste0(round(group_diff, 2), "\n (", round(group_se, 2), ")")),
vjust = 0,
colour = "black",
size = 2,
lineheight = 0.9) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0) +
theme_minimal() +
theme(axis.text.x = element_text(vjust = 0.5, hjust = 1)) +
labs(y = "Feeling", x = "Question Number", title = "Differences from Post-Type group mean by post number, False Dichotomy")

Emotional
opinions |>
filter(post_type == "Non Misinfo") |>
select(post_number, all_of(c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see", "share"))) |> #now pivot to long
pivot_longer(cols = -post_number, names_to = "variable", values_to = "opinion") |>
group_by(variable) |>
mutate(grand_mean = mean(opinion, na.rm = TRUE)) |>
group_by(variable, post_number) |>
mutate(
group_mean = mean(opinion, na.rm = TRUE),
group_diff = group_mean - grand_mean,
group_se = sd(opinion, na.rm = TRUE)/sqrt(n()),
) |>
distinct(variable, post_number, group_diff, group_se) |>
ggplot(aes(y = variable, x = post_number, fill = group_diff)) +
geom_tile() +
geom_text(aes(label = paste0(round(group_diff, 2), "\n (", round(group_se, 2), ")")),
vjust = 0,
colour = "black",
size = 2,
lineheight = 0.9) +
scale_fill_gradient2(low = "blue", mid = "white", high = "red", midpoint = 0) +
theme_minimal() +
theme(axis.text.x = element_text(vjust = 0.5, hjust = 1)) +
labs(y = "Feeling", x = "Question Number", title = "Differences from Post-Type group mean by post number, Emotional")

Regressions
Regressions of
intention to share on other variables
# Run regressions of each variables individually on share and all jointly
library(fixest)
mods = list()
for(var in c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see")){
mods[[var]] = feols(as.formula(paste0("share ~ ", var)), data = opinions)
}
mods[["Manipulative_&_Reliable"]] = feols(share ~ manipulative + reliable, data = opinions)
mods[["all"]] = feols(share ~ manipulative + reliable + concerning + easy_to_understand + might_see, data = opinions)
#rename mods in list to (1), (2), etc
names(mods) = paste0("(", 1:length(mods), ")")
etable(mods, cluster = "ResponseId", digits = 3,
headers = rep("Share?", length(mods)),
depvar = FALSE,
drop = "Constant",
dict = c(
manipulative = "Manipulative?",
reliable = "Reliable?",
concerning = "Concerning?",
easy_to_understand = "Easy to understand?",
might_see = "Might see?"
)
) |> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
|
|
|
|
|
|
|
|
|
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
|
|
|
|
|
|
|
|
|
|
Manipulative?
|
-0.069*** (0.006)
|
|
|
|
|
-0.031*** (0.005)
|
-0.033*** (0.005)
|
|
Reliable?
|
|
0.132*** (0.006)
|
|
|
|
0.119*** (0.007)
|
0.098*** (0.007)
|
|
Concerning?
|
|
|
0.044*** (0.007)
|
|
|
|
0.021*** (0.004)
|
|
Easy to understand?
|
|
|
|
0.066*** (0.008)
|
|
|
0.005 (0.007)
|
|
Might see?
|
|
|
|
|
0.520*** (0.040)
|
|
0.318*** (0.036)
|
|
___________________
|
_________________
|
________________
|
________________
|
________________
|
________________
|
_________________
|
_________________
|
|
S.E.: Clustered
|
by: ResponseId
|
by: ResponseId
|
by: ResponseId
|
by: ResponseId
|
by: ResponseId
|
by: ResponseId
|
by: ResponseId
|
|
Observations
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
|
R2
|
0.09817
|
0.28704
|
0.03354
|
0.03794
|
0.13391
|
0.30400
|
0.36260
|
|
Adj. R2
|
0.09787
|
0.28680
|
0.03322
|
0.03762
|
0.13362
|
0.30354
|
0.36154
|
Leave-one-out
regressions
Now regress the intention to share on leave-one-out (LOO) means of
each variable by post number. This is to see to what extent, say, more
reliable posts are shared more widely. This specification lessens the
experimenter’s demand concerns.
# Compute the leave-one-out means by question of each variable
opinions = opinions |>
group_by(post_number) |>
mutate(
manipulative_loo = (sum(manipulative) - manipulative) / (n() - 1),
reliable_loo = (sum(reliable) - reliable) / (n() - 1),
concerning_loo = (sum(concerning) - concerning) / (n() - 1),
easy_to_understand_loo = (sum(easy_to_understand) - easy_to_understand) / (n() - 1),
might_see_loo = (sum(might_see) - might_see) / (n() - 1)
)
# Run regressions of each variables individually on share and all jointly
mods = list()
for(var in c("manipulative_loo", "reliable_loo", "concerning_loo", "easy_to_understand_loo", "might_see_loo")){
mods[[var]] = feols(as.formula(paste0("share ~ ", var)), data = opinions)
}
mods[["Manipulative_&_Reliable"]] = feols(share ~ manipulative_loo + reliable_loo, data = opinions)
mods[["all"]] = feols(share ~ manipulative_loo + reliable_loo + concerning_loo + easy_to_understand_loo + might_see_loo, data = opinions)
#rename mods in list to (1), (2), etc
names(mods) = paste0("(", 1:length(mods), ")")
etable(mods, cluster = "post_number", digits = 3,
headers = rep("Share?", length(mods)),
depvar = FALSE,
drop = "Constant",
dict = c(
manipulative_loo = "Manipulative LOO?",
reliable_loo = "Reliable LOO?",
concerning_loo = "Concerning LOO?",
easy_to_understand_loo = "Easy to understand LOO?",
might_see_loo = "Might see LOO?"
)
)|> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
|
|
|
|
|
|
|
|
|
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
|
|
|
|
|
|
|
|
|
|
Manipulative LOO?
|
-0.108*** (0.023)
|
|
|
|
|
-0.008 (0.011)
|
-0.025 (0.017)
|
|
Reliable LOO?
|
|
0.178*** (0.010)
|
|
|
|
0.172*** (0.012)
|
0.146*** (0.023)
|
|
Concerning LOO?
|
|
|
0.050*** (0.013)
|
|
|
|
0.015 (0.015)
|
|
Easy to understand LOO?
|
|
|
|
0.221** (0.073)
|
|
|
0.031 (0.019)
|
|
Might see LOO?
|
|
|
|
|
0.747*** (0.157)
|
|
0.026 (0.104)
|
|
_______________________
|
_________________
|
________________
|
________________
|
_______________
|
________________
|
________________
|
________________
|
|
S.E.: Clustered
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
|
Observations
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
|
R2
|
0.04142
|
0.08846
|
0.00694
|
0.03179
|
0.03007
|
0.08858
|
0.08947
|
|
Adj. R2
|
0.04109
|
0.08815
|
0.00661
|
0.03146
|
0.02974
|
0.08797
|
0.08794
|
Regressions with
both LOO and original variables
mods = list()
for(var in c("manipulative", "reliable", "concerning", "easy_to_understand", "might_see")){
mods[[var]] = feols(as.formula(paste0("share ~ ", var, " + ", var, "_loo")), data = opinions)
}
mods[["Manipulative_&_Reliable"]] = feols(share ~ manipulative + reliable + manipulative_loo + reliable_loo, data = opinions)
mods[[paste0("all")]] = feols(share ~ manipulative + reliable + concerning + easy_to_understand + might_see + manipulative_loo + reliable_loo + concerning_loo + easy_to_understand_loo + might_see_loo, data = opinions)
#rename mods in list to (1), (2), etc
names(mods) = paste0("(", 1:length(mods), ")")
etable(mods, cluster = "post_number", digits = 3,
headers = rep("Share?", length(mods)),
depvar = FALSE,
drop = "Constant",
dict = c(
manipulative = "Manipulative?",
reliable = "Reliable?",
concerning = "Concerning?",
easy_to_understand = "Easy to understand?",
might_see = "Might see?",
manipulative_loo = "Manipulative LOO?",
reliable_loo = "Reliable LOO?",
concerning_loo = "Concerning LOO?",
easy_to_understand_loo = "Easy to understand LOO?",
might_see_loo = "Might see LOO?"
)
)|> kable() |> kable_styling(bootstrap_options = c("striped", "hover")) %>%
scroll_box(height = "100%")
|
|
|
|
|
|
|
|
|
|
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
Share?
|
|
|
|
|
|
|
|
|
|
|
Manipulative?
|
-0.061*** (0.005)
|
|
|
|
|
-0.030*** (0.004)
|
-0.030*** (0.003)
|
|
Manipulative LOO?
|
-0.050* (0.023)
|
|
|
|
|
0.024* (0.011)
|
0.005 (0.018)
|
|
Reliable?
|
|
0.122*** (0.006)
|
|
|
|
0.112*** (0.005)
|
0.094*** (0.005)
|
|
Reliable LOO?
|
|
0.062*** (0.012)
|
|
|
|
0.067*** (0.013)
|
0.056* (0.024)
|
|
Concerning?
|
|
|
0.042*** (0.007)
|
|
|
|
0.021*** (0.003)
|
|
Concerning LOO?
|
|
|
0.010 (0.014)
|
|
|
|
-0.005 (0.016)
|
|
Easy to understand?
|
|
|
|
0.054*** (0.007)
|
|
|
0.005 (0.004)
|
|
Easy to understand LOO?
|
|
|
|
0.173* (0.076)
|
|
|
0.022 (0.019)
|
|
Might see?
|
|
|
|
|
0.490*** (0.031)
|
|
0.327*** (0.028)
|
|
Might see LOO?
|
|
|
|
|
0.297. (0.165)
|
|
-0.271* (0.115)
|
|
_______________________
|
_________________
|
________________
|
________________
|
________________
|
________________
|
_________________
|
_________________
|
|
S.E.: Clustered
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
by: post_number
|
|
Observations
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
2,987
|
|
R2
|
0.10563
|
0.29622
|
0.03379
|
0.05636
|
0.13822
|
0.31102
|
0.36749
|
|
Adj. R2
|
0.10503
|
0.29575
|
0.03314
|
0.05572
|
0.13764
|
0.31010
|
0.36537
|
Takeaways
- Stated reliability and post being similar to something one might see
on their timelines have strong (and positive) associations with the
intentions to share
- The remaining variables (easy to understand, manipulative,
concerning) have much weaker correlations with the intention to
share.
- Manipulativeness is the only variable with a negative association
with the intention to share.
Textual feedback
Takeaways: 1. A lot of people say they agree with true posts but some
say that they know nothing about given topics and it would not draw
their attention 2. On misinfo posts a lot of people comment as: “fake
news”, “lie” “crazy” 3. Some people agree with some misinfo posts:
“Media lies!”, “Interesting and good question”, “The post raises
eyebrows about the reliability of nutritionists.”, “it is sad but it
truth” 4. On style: “I like this post because its to the point.”
“arrogant pster”, “sad; but vague and unhelpful too”, “Humorous
post.”
Specific Posts:
- Post 18 (deemed very reliable) – “facts -poliiticians do not care”,
“politicians are the biggest criminals”, “Unfortunately, a large number
of the politicians never deliver their promised projects. It happens all
over the world!” – Notice these comments are not about reliability of
the post but just people agreeing with the sentiment of the post
- Post 27 (deemed very maniulative and unreliable) – “This could be
propaganda.”, “I learnt something new.”, “Antibiotics work wonders”,
“antibiotics are safe” – People mention that the post is manipulative
but also just express the opinion that they disagree with the substance
(i.e. they don’t think antibiotics are toxic)
- Post 23 (very reliable and concerning) – “There is truth in this
post” “This is just someone venting about lack of help for low income
countries but not harmful.”, “the figure makes me trust the post”, “With
statistical posts, proof should be provided. That said, if I were to
believe the post’s claim, I would get angry on behalf of low-income
nations.”, “nothing new, the rich will always come first” – Some people
took the number for granted but a lot question the figure and would like
to see a source. Still, it seems like a well-written post with a number
in it seems more reliable.
Word
Clouds
Non-misinfo
# Tokenize feedback
tokens <- valid_feedback %>%
filter(post_type == "Non Misinfo") %>%
select(feedback) %>%
unnest_tokens(word, feedback) |>
anti_join(stop_words)
# Count word occurrences and select top 100
word_counts <- tokens %>%
count(word, sort = TRUE)|>
filter(word!= "post") |>
slice(1:50)
# Create word cloud
wordcloud::wordcloud(words = word_counts$word, freq = word_counts$n, max.words = 50,
random.order = FALSE, rot.per = 0.35, colors = brewer.pal(8, "Dark2"))

Discrediting
# Tokenize feedback
tokens <- valid_feedback %>%
filter(post_type == "Discrediting") %>%
select(feedback) %>%
unnest_tokens(word, feedback) |>
anti_join(stop_words)
# Count word occurrences and select top 100
word_counts <- tokens %>%
count(word, sort = TRUE)|>
filter(word!= "post") |>
slice(1:50)
# Create word cloud
wordcloud::wordcloud(words = word_counts$word, freq = word_counts$n, max.words = 50,
random.order = FALSE, rot.per = 0.35, colors = brewer.pal(8, "Dark2"))

Emotional
# Tokenize feedback
tokens <- valid_feedback %>%
filter(post_type == "Emotional") %>%
select(feedback) %>%
unnest_tokens(word, feedback) |>
anti_join(stop_words)
# Count word occurrences and select top 100
word_counts <- tokens %>%
count(word, sort = TRUE) |>
filter(word!= "post")|>
slice(1:50)
# Create word cloud
wordcloud::wordcloud(words = word_counts$word, freq = word_counts$n, max.words = 50,
random.order = FALSE, rot.per = 0.35, colors = brewer.pal(8, "Dark2"))

False
Dichotomy
# Tokenize feedback
tokens <- valid_feedback %>%
filter(post_type == "False Dichotomy") %>%
select(feedback) %>%
unnest_tokens(word, feedback) |>
anti_join(stop_words)
# Count word occurrences and select top 100
word_counts <- tokens %>%
count(word, sort = TRUE) |>
filter(word!= "post") |>
slice(1:50)
# Create word cloud
wordcloud::wordcloud(words = word_counts$word, freq = word_counts$n, max.words = 50,
random.order = FALSE, rot.per = 0.35, colors = brewer.pal(8, "Dark2"))
