#file.choose()
survey <- read.csv("/Users/navyaneelamegam/Desktop/Team7_survey_clean.csv",
                   fileEncoding = "UTF-8",
                   na.strings = c("", "NA"),
                   stringsAsFactors = FALSE)
dim(survey)        # expect 49 rows, 34 columns
## [1] 49 34
head(survey)
##   id           timestamp      consent enrolled age_eligible ai_use
## 1  1 2026-11-07 13:41:12 Yes, I agree      Yes          Yes      5
## 2  2 2026-11-07 13:41:15 Yes, I agree      Yes          Yes      4
## 3  3 2026-11-07 13:41:59 Yes, I agree      Yes          Yes      4
## 4  4 2026-11-07 13:44:04 Yes, I agree      Yes          Yes      4
## 5  5 2026-11-07 13:46:13 Yes, I agree      Yes          Yes      4
## 6  6 2026-11-07 13:55:38 Yes, I agree      Yes          Yes      4
##   ai_disclosure_freq ai_comfort ai_willing ai_holdback ai_judgment
## 1                  1          1          1           5           1
## 2                  2          3          4           3           1
## 3                  1          1          1           5           1
## 4                  1          2          1           1           4
## 5                  1          1          1           5           1
## 6                  3          3          4           2           1
##   ai_understanding ai_privacy ai_relief ai_uneasy ai_closure ai_lasting_relief
## 1                1          4         1         4          1                 1
## 2                2          5         4         4          4                 2
## 3                1          5         1         3          1                 2
## 4                1          5         2         4          1                 1
## 5                1          5         1         5          1                 1
## 6                1          3         3         3          2                 1
##   human_disclosure_freq human_comfort human_willing human_holdback
## 1                     5             5             5              4
## 2                     4             4             4              2
## 3                     4             5             5              1
## 4                     3             3             4              5
## 5                     5             5             5              2
## 6                     3             4             4              5
##   human_judgment human_understanding human_privacy human_relief human_uneasy
## 1              3                   4             3            4            2
## 2              2                   4             2            5            2
## 3              2                   5             2            5            1
## 4              4                   3             2            4            3
## 5              2                   3             3            5            2
## 6              3                   2             3            2            3
##   human_closure human_lasting_relief preferred_confidant
## 1             4                    4      A close friend
## 2             4                    5  A romantic partner
## 3             5                    5  A romantic partner
## 4             4                    3  A romantic partner
## 5             5                    5          Bsf and bf
## 6             2                    3      A close friend
##                                                                                                                                                         explanation
## 1                                                                                                                                                           Nothing
## 2                                                                                               Ai is always available, people need time to be available to respond
## 3                                                   Ai is a robot and they are just going to tell me what I want to hear. With a Perón it’s more personal and real.
## 4                                                             A chatbot doesnt have personal human experiences, so it can never actually know what im going through
## 5                                                                                                                                                              Both
## 6 I think its cause AI chatbots are more designed to appease you rather than people who just have their own thought or opinion that influence what they say to you.
##   age_group gender   year             area_study
## 1  22 to 24    Man Senior         Communications
## 2  20 to 21    Man Junior Architecture or design
## 3  20 to 21  Woman Junior      Arts and sciences
## 4  20 to 21    Man Junior      Arts and sciences
## 5  22 to 24  Woman Senior      Political Science
## 6  20 to 21  Woman Senior                   HDFS
str(survey)
## 'data.frame':    49 obs. of  34 variables:
##  $ id                   : int  1 2 3 4 5 6 7 8 9 10 ...
##  $ timestamp            : chr  "2026-11-07 13:41:12" "2026-11-07 13:41:15" "2026-11-07 13:41:59" "2026-11-07 13:44:04" ...
##  $ consent              : chr  "Yes, I agree" "Yes, I agree" "Yes, I agree" "Yes, I agree" ...
##  $ enrolled             : chr  "Yes" "Yes" "Yes" "Yes" ...
##  $ age_eligible         : chr  "Yes" "Yes" "Yes" "Yes" ...
##  $ ai_use               : int  5 4 4 4 4 4 5 1 5 1 ...
##  $ ai_disclosure_freq   : int  1 2 1 1 1 3 3 1 2 1 ...
##  $ ai_comfort           : int  1 3 1 2 1 3 3 1 2 1 ...
##  $ ai_willing           : int  1 4 1 1 1 4 4 1 2 1 ...
##  $ ai_holdback          : int  5 3 5 1 5 2 3 3 5 5 ...
##  $ ai_judgment          : int  1 1 1 4 1 1 1 3 5 1 ...
##  $ ai_understanding     : int  1 2 1 1 1 1 3 1 1 1 ...
##  $ ai_privacy           : int  4 5 5 5 5 3 3 5 5 5 ...
##  $ ai_relief            : int  1 4 1 2 1 3 4 1 1 1 ...
##  $ ai_uneasy            : int  4 4 3 4 5 3 2 5 3 5 ...
##  $ ai_closure           : int  1 4 1 1 1 2 4 1 1 1 ...
##  $ ai_lasting_relief    : int  1 2 2 1 1 1 4 1 1 1 ...
##  $ human_disclosure_freq: int  5 4 4 3 5 3 5 4 5 5 ...
##  $ human_comfort        : int  5 4 5 3 5 4 5 4 5 5 ...
##  $ human_willing        : int  5 4 5 4 5 4 5 4 5 5 ...
##  $ human_holdback       : int  4 2 1 5 2 5 3 2 3 1 ...
##  $ human_judgment       : int  3 2 2 4 2 3 4 1 5 2 ...
##  $ human_understanding  : int  4 4 5 3 3 2 4 4 5 5 ...
##  $ human_privacy        : int  3 2 2 2 3 3 2 1 5 1 ...
##  $ human_relief         : int  4 5 5 4 5 2 4 4 5 5 ...
##  $ human_uneasy         : int  2 2 1 3 2 3 2 1 3 1 ...
##  $ human_closure        : int  4 4 5 4 5 2 4 4 5 5 ...
##  $ human_lasting_relief : int  4 5 5 3 5 3 5 1 5 5 ...
##  $ preferred_confidant  : chr  "A close friend" "A romantic partner" "A romantic partner" "A romantic partner" ...
##  $ explanation          : chr  "Nothing" "Ai is always available, people need time to be available to respond" "Ai is a robot and they are just going to tell me what I want to hear. With a Perón it’s more personal and real." "A chatbot doesnt have personal human experiences, so it can never actually know what im going through" ...
##  $ age_group            : chr  "22 to 24" "20 to 21" "20 to 21" "20 to 21" ...
##  $ gender               : chr  "Man" "Man" "Woman" "Man" ...
##  $ year                 : chr  "Senior" "Junior" "Junior" "Junior" ...
##  $ area_study           : chr  "Communications" "Architecture or design" "Arts and sciences" "Arts and sciences" ...
colSums(is.na(survey))[colSums(is.na(survey)) > 0]
## explanation 
##           1
item_names  <- c("comfort", "willing", "holdback", "judgment", "understanding",
                 "privacy", "relief", "uneasy", "closure", "lasting_relief")
rating_cols <- c(paste0("ai_", item_names), paste0("human_", item_names))
sapply(survey[rating_cols], range) 
##      ai_comfort ai_willing ai_holdback ai_judgment ai_understanding ai_privacy
## [1,]          1          1           1           1                1          1
## [2,]          5          5           5           5                5          5
##      ai_relief ai_uneasy ai_closure ai_lasting_relief human_comfort
## [1,]         1         1          1                 1             1
## [2,]         4         5          5                 5             5
##      human_willing human_holdback human_judgment human_understanding
## [1,]             1              1              1                   1
## [2,]             5              5              5                   5
##      human_privacy human_relief human_uneasy human_closure human_lasting_relief
## [1,]             1            1            1             2                    1
## [2,]             5            5            5             5                    5
survey$gender              <- factor(survey$gender)
survey$area_study          <- factor(survey$area_study)
survey$preferred_confidant <- factor(survey$preferred_confidant)
survey$age_group <- factor(survey$age_group,
                           levels = c("18 to 19", "20 to 21", "22 to 24", "25 or older"),
                           ordered = TRUE)
survey$year <- factor(survey$year,
                      levels = c("Freshman", "Sophomore", "Junior", "Senior",
                                 "Graduate student", "BA degree", "Prefer not to say"))
table(survey$age_group)   # expect 13, 26, 7, 3
## 
##    18 to 19    20 to 21    22 to 24 25 or older 
##          13          26           7           3
survey$ai_holdback_r    <- 6 - survey$ai_holdback
survey$ai_uneasy_r      <- 6 - survey$ai_uneasy
survey$human_holdback_r <- 6 - survey$human_holdback
survey$human_uneasy_r   <- 6 - survey$human_uneasy
survey$ai_disclosure_score <- rowMeans(survey[, c("ai_comfort", "ai_willing", "ai_holdback_r")])
survey$ai_emotional_score  <- rowMeans(survey[, c("ai_relief", "ai_uneasy_r",
                                                  "ai_closure", "ai_lasting_relief")])
survey$human_disclosure_score <- rowMeans(survey[, c("human_comfort", "human_willing", "human_holdback_r")])
survey$human_emotional_score  <- rowMeans(survey[, c("human_relief", "human_uneasy_r",
                                                     "human_closure", "human_lasting_relief")])
cronbach_alpha <- function(items) {
  items <- na.omit(items)
  k <- ncol(items)
  (k / (k - 1)) * (1 - sum(apply(items, 2, var)) / var(rowSums(items)))
}

alpha_table <- data.frame(
  scale = c("AI: willingness to disclose (3 items)",
            "AI: post-disclosure relief (4 items)",
            "Human: willingness to disclose (3 items)",
            "Human: post-disclosure relief (4 items)"),
  alpha = round(c(
    cronbach_alpha(survey[, c("ai_comfort", "ai_willing", "ai_holdback_r")]),
    cronbach_alpha(survey[, c("ai_relief", "ai_uneasy_r", "ai_closure", "ai_lasting_relief")]),
    cronbach_alpha(survey[, c("human_comfort", "human_willing", "human_holdback_r")]),
    cronbach_alpha(survey[, c("human_relief", "human_uneasy_r", "human_closure", "human_lasting_relief")])
  ), 2)
)
print(alpha_table)
##                                      scale alpha
## 1    AI: willingness to disclose (3 items)  0.60
## 2     AI: post-disclosure relief (4 items)  0.79
## 3 Human: willingness to disclose (3 items)  0.64
## 4  Human: post-disclosure relief (4 items)  0.75
round(sapply(survey[, c("ai_disclosure_score", "human_disclosure_score",
                        "ai_emotional_score", "human_emotional_score")],
             function(x) c(mean = mean(x), sd = sd(x))), 2)
##      ai_disclosure_score human_disclosure_score ai_emotional_score
## mean                2.34                   3.67               2.22
## sd                  0.99                   0.86               0.97
##      human_emotional_score
## mean                  3.84
## sd                    0.82
write.csv(survey, "Team7_ReplikaSurvey_ANALYSIS.csv", row.names = FALSE)
get_mode <- function(x) {
  counts <- table(na.omit(x))
  modes  <- as.numeric(names(counts)[counts == max(counts)])
  paste(round(modes, 2), collapse = " / ")
}
describe5 <- function(v) {
  x <- survey[[v]]
  data.frame(Variable = v,
             Mean   = round(mean(x), 2),
             Median = round(median(x), 2),
             Mode   = get_mode(x),
             Min    = round(min(x), 2),
             Max    = round(max(x), 2),
             Range  = round(max(x) - min(x), 2),   # range = max - min
             SD     = round(sd(x), 2))
}
make_table <- function(vars) do.call(rbind, lapply(vars, describe5))
freq_vars <- c("ai_use", "ai_disclosure_freq", "human_disclosure_freq")
table1 <- make_table(freq_vars)
table1
##                Variable Mean Median Mode Min Max Range   SD
## 1                ai_use 3.14      3    4   1   5     4 1.37
## 2    ai_disclosure_freq 2.00      2    1   1   5     4 1.15
## 3 human_disclosure_freq 3.51      4    4   1   5     4 1.23
item_names <- c("comfort", "willing", "holdback", "judgment", "understanding",
                "privacy", "relief", "uneasy", "closure", "lasting_relief")
item_vars <- as.vector(rbind(paste0("ai_", item_names), paste0("human_", item_names)))
table2 <- make_table(item_vars)
table2
##                Variable Mean Median  Mode Min Max Range   SD
## 1            ai_comfort 2.16      2     1   1   5     4 1.21
## 2         human_comfort 3.90      4     5   1   5     4 1.12
## 3            ai_willing 2.31      2     1   1   5     4 1.31
## 4         human_willing 4.02      4     5   1   5     4 1.01
## 5           ai_holdback 3.45      4     5   1   5     4 1.44
## 6        human_holdback 2.90      3     2   1   5     4 1.23
## 7           ai_judgment 2.00      1     1   1   5     4 1.29
## 8        human_judgment 3.06      3     4   1   5     4 1.14
## 9      ai_understanding 1.90      1     1   1   5     4 1.18
## 10  human_understanding 3.73      4     4   1   5     4 1.13
## 11           ai_privacy 3.92      4     5   1   5     4 1.29
## 12        human_privacy 2.43      2     2   1   5     4 1.40
## 13            ai_relief 2.06      2     1   1   4     3 1.13
## 14         human_relief 3.98      4     4   1   5     4 1.05
## 15            ai_uneasy 3.12      3 3 / 4   1   5     4 1.38
## 16         human_uneasy 2.37      2     2   1   5     4 1.18
## 17           ai_closure 2.00      1     1   1   5     4 1.26
## 18        human_closure 3.92      4     4   2   5     3 0.95
## 19    ai_lasting_relief 1.96      1     1   1   5     4 1.17
## 20 human_lasting_relief 3.84      4     5   1   5     4 1.14
score_vars <- c("ai_disclosure_score", "human_disclosure_score",
                "ai_emotional_score",  "human_emotional_score")
table3 <- make_table(score_vars)
table3
##                 Variable Mean Median     Mode  Min  Max Range   SD
## 1    ai_disclosure_score 2.34   2.33     2.33 1.00 4.33  3.33 0.99
## 2 human_disclosure_score 3.67   4.00 4 / 4.33 1.67 5.00  3.33 0.86
## 3     ai_emotional_score 2.22   2.00        1 1.00 4.50  3.50 0.97
## 4  human_emotional_score 3.84   4.00        4 2.00 5.00  3.00 0.82
cat_table <- function(v) {
  t <- table(survey[[v]])
  data.frame(Variable = v, Category = names(t), n = as.integer(t),
             Percent = round(100 * as.numeric(t) / sum(t), 1))
}
cat_vars <- c("gender", "age_group", "year", "area_study", "preferred_confidant")
table4 <- do.call(rbind, lapply(cat_vars, cat_table))
table4
##               Variable                        Category  n Percent
## 1               gender                             Man 18    36.7
## 2               gender                      Non-binary  2     4.1
## 3               gender               Prefer not to say  5    10.2
## 4               gender                           Woman 24    49.0
## 5            age_group                        18 to 19 13    26.5
## 6            age_group                        20 to 21 26    53.1
## 7            age_group                        22 to 24  7    14.3
## 8            age_group                     25 or older  3     6.1
## 9                 year                        Freshman  5    10.2
## 10                year                       Sophomore 10    20.4
## 11                year                          Junior 14    28.6
## 12                year                          Senior 14    28.6
## 13                year                Graduate student  2     4.1
## 14                year                       BA degree  1     2.0
## 15                year               Prefer not to say  3     6.1
## 16          area_study          Architecture or design  4     8.2
## 17          area_study               Arts and sciences 13    26.5
## 18          area_study          Business or management  8    16.3
## 19          area_study                  Communications  4     8.2
## 20          area_study                       Education  1     2.0
## 21          area_study Engineering or computer science  5    10.2
## 22          area_study                            HDFS  1     2.0
## 23          area_study                      Healthcare  1     2.0
## 24          area_study     Information studies or data  5    10.2
## 25          area_study         International relations  1     2.0
## 26          area_study               Political Science  3     6.1
## 27          area_study               Prefer not to say  3     6.1
## 28 preferred_confidant                  A close friend 14    28.6
## 29 preferred_confidant        A counselor or therapist  2     4.1
## 30 preferred_confidant                 A family member  8    16.3
## 31 preferred_confidant              A romantic partner 15    30.6
## 32 preferred_confidant                   An AI chatbot  3     6.1
## 33 preferred_confidant                      Bsf and bf  1     2.0
## 34 preferred_confidant                             Dog  1     2.0
## 35 preferred_confidant                          No one  4     8.2
## 36 preferred_confidant                        The LORD  1     2.0
sum(!is.na(survey$explanation))  
## [1] 48
measures <- c("disclosure_score", "emotional_score", "judgment", "understanding",
              "privacy", "relief", "closure", "lasting_relief")
means_mat <- rbind(
  "AI chatbot"            = sapply(paste0("ai_",    measures), function(v) mean(survey[[v]])),
  "Close friend/family"   = sapply(paste0("human_", measures), function(v) mean(survey[[v]]))
)
colnames(means_mat) <- c("Disclosure\nscore", "Relief\nscore", "Fear of\njudgment",
                         "Feeling\nunderstood", "Privacy\nconcern", "Immediate\nrelief",
                         "Closure", "Lasting\nrelief")
barplot(means_mat, beside = TRUE, ylim = c(0, 5.5), col = c("grey70", "grey25"),
        ylab = "Mean rating (1 = strongly disagree, 5 = strongly agree)",
        main = "Mean ratings by confidant (N = 49)", cex.names = 0.75,
        legend.text = TRUE, args.legend = list(x = "top", horiz = TRUE, bty = "n"))

boxplot(survey[, score_vars], ylim = c(1, 5),
        names = c("AI\ndisclosure", "Friend/family\ndisclosure", "AI\nrelief", "Friend/family\nrelief"),
        ylab = "Scale score (1-5)", main = "Distribution of scale scores (N = 49)",
        col = c("grey70", "grey25", "grey70", "grey25"))

PART 3

paired_test <- function(var, label, alt = "greater") {
  human <- survey[[paste0("human_", var)]]
  ai    <- survey[[paste0("ai_",    var)]]
  diff  <- human - ai

  tt <- t.test(human, ai, paired = TRUE, alternative = alt)  
  ci <- t.test(human, ai, paired = TRUE)$conf.int            
  wt <- suppressWarnings(wilcox.test(human, ai, paired = TRUE,
                                     alternative = alt, exact = FALSE))  

  data.frame(Test       = label,
             Tail       = ifelse(alt == "greater", "one-tailed", "two-tailed"),
             Mean_AI    = round(mean(ai), 2),
             Mean_Human = round(mean(human), 2),
             Mean_diff  = round(mean(diff), 2),
             CI_low     = round(ci[1], 2),
             CI_high    = round(ci[2], 2),
             t          = round(unname(tt$statistic), 2),
             df         = unname(tt$parameter),
             p          = tt$p.value,
             Cohens_d   = round(mean(diff) / sd(diff), 2),   # d for paired data (Cohen's dz)
             Wilcoxon_p = wt$p.value,
             Shapiro_p  = round(shapiro.test(diff)$p.value, 3))  # normality of the differences
}

results <- rbind(
  paired_test("disclosure_score", "H1: Willingness to disclose (score)"),
  paired_test("judgment",         "H2: Fear of judgment"),
  paired_test("understanding",    "H3: Perceived understanding"),
  paired_test("closure",          "H4a: Closure"),
  paired_test("lasting_relief",   "H4a: Lasting relief"),
  paired_test("relief",           "H4b: Immediate relief",            alt = "two.sided"),
  paired_test("emotional_score",  "Supplementary: Relief (score)",    alt = "two.sided"),
  paired_test("privacy",          "Supplementary: Privacy concern",   alt = "two.sided")
)


results$p_holm <- p.adjust(results$p, method = "holm")

fmt_p <- function(p) ifelse(p < .001, "< .001", sprintf("%.3f", p))
report <- results
report$p          <- fmt_p(results$p)
report$p_holm     <- fmt_p(results$p_holm)
report$Wilcoxon_p <- fmt_p(results$Wilcoxon_p)
report
##                                  Test       Tail Mean_AI Mean_Human Mean_diff
## 1 H1: Willingness to disclose (score) one-tailed    2.34       3.67      1.33
## 2                H2: Fear of judgment one-tailed    2.00       3.06      1.06
## 3         H3: Perceived understanding one-tailed    1.90       3.73      1.84
## 4                        H4a: Closure one-tailed    2.00       3.92      1.92
## 5                 H4a: Lasting relief one-tailed    1.96       3.84      1.88
## 6               H4b: Immediate relief two-tailed    2.06       3.98      1.92
## 7       Supplementary: Relief (score) two-tailed    2.22       3.84      1.62
## 8      Supplementary: Privacy concern two-tailed    3.92       2.43     -1.49
##   CI_low CI_high     t df      p Cohens_d Wilcoxon_p Shapiro_p p_holm
## 1   0.91    1.75  6.37 48 < .001     0.91     < .001     0.708 < .001
## 2   0.60    1.52  4.61 48 < .001     0.66     < .001     0.007 < .001
## 3   1.33    2.35  7.26 48 < .001     1.04     < .001     0.001 < .001
## 4   1.45    2.38  8.30 48 < .001     1.19     < .001     0.001 < .001
## 5   1.38    2.37  7.61 48 < .001     1.09     < .001     0.001 < .001
## 6   1.45    2.39  8.23 48 < .001     1.18     < .001     0.003 < .001
## 7   1.23    2.00  8.47 48 < .001     1.21     < .001     0.418 < .001
## 8  -1.98   -1.00 -6.14 48 < .001    -0.88     < .001     0.002 < .001