This document runs a basic text analysis and sentiment analysis on four Bluesky post collections (two for each candidate in the California governor’s race) and shows how both change over time. All charts are interactive (Plotly).
Workflow
*2.csv files contain a few
invalid UTF-8 bytes, handled below)record
columnInstall once (not run when knitting):
install.packages(c("tidyverse", "tidytext", "plotly", "kableExtra", "cld2", "scales"))
library(tidyverse)
library(lubridate)
library(tidytext)
library(plotly)
library(kableExtra)
library(cld2) # language detection
library(scales)
tz_local <- "C:/Users/zxu3/Documents/R/bluesky" # time zone used to assign posts to days
election_day <- as.Date("2026-11-03") # vertical reference line on trend charts
min_posts_per_day <- 5 # hide days with fewer posts in trend charts
pal <- c(Becerra = "#2C7BB6", Hilton = "#D7191C")
files <- tribble(
~file, ~candidate, ~batch,
"post_Xavier.csv", "Becerra", "batch 1",
"post_Xavier2.csv", "Becerra", "batch 2",
"post_steve.csv", "Hilton", "batch 1",
"post_steve2.csv", "Hilton", "batch 2"
) %>%
mutate(path = file.path(params$data_dir, file))
# Words the Bing lexicon scores in ways that are misleading for political posts
# (e.g., "trump" is listed as positive, "lead" as positive). Edit freely.
sent_exclude <- c("trump", "like", "lead", "leads", "leading", "right", "well",
"work", "top", "won")
# Words that are uninformative here (candidate names, site boilerplate)
custom_stop <- tibble(word = c("steve", "hilton", "xavier", "becerra", "california",
"californians", "californian", "governor", "gov",
"gubernatorial", "race", "election", "candidate",
"bsky", "social", "amp", "nbsp", "publisher", "via"))
The CSVs were exported from R with nested fields flattened into text,
and the two *2.csv files contain a few invalid UTF-8 bytes.
read_bsky() drops the bad bytes before parsing.
read_bsky <- function(path) {
raw_txt <- rawToChar(readBin(path, "raw", file.size(path)))
Encoding(raw_txt) <- "UTF-8"
clean_txt <- iconv(raw_txt, from = "UTF-8", to = "UTF-8", sub = "") # drop invalid bytes
tmp <- tempfile(fileext = ".csv")
writeLines(clean_txt, tmp, useBytes = TRUE)
read_csv(tmp, col_types = cols(.default = col_character()), show_col_types = FALSE)
}
raw_posts <- files %>%
mutate(data = map(path, read_bsky)) %>%
select(-path) %>%
unnest(data) %>%
mutate(
created_utc = ymd_hms(indexed_at, tz = "UTC"),
created_local = with_tz(created_utc, tz_local),
day = as_date(created_local),
handle = str_split_fixed(author, "; ", 4)[, 2],
across(c(like_count, repost_count, reply_count, quote_count), as.integer)
)
raw_posts %>%
group_by(candidate, batch, file) %>%
summarise(rows = n(), unique_posts = n_distinct(uri),
first_day = min(day), last_day = max(day), .groups = "drop") %>%
kbl(caption = "Raw files") %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed"), full_width = FALSE)
| candidate | batch | file | rows | unique_posts | first_day | last_day |
|---|---|---|---|---|---|---|
| Becerra | batch 1 | post_Xavier.csv | 500 | 500 | 2026-10-15 | 2026-10-31 |
| Becerra | batch 2 | post_Xavier2.csv | 488 | 488 | 2026-10-22 | 2026-11-03 |
| Hilton | batch 1 | post_steve.csv | 500 | 500 | 2026-10-17 | 2026-10-31 |
| Hilton | batch 2 | post_steve2.csv | 486 | 486 | 2026-10-21 | 2026-11-03 |
The record column is a flattened string such as
app.bsky.feed.post; <date>; list(<embed>); list(<facets>); en; <post text>.
The helper below removes the type, date, nested list(...)
blocks and language code, leaving the text. Posts bridged from Mastodon
have a different order and are handled separately.
# Remove a leading balanced "list( ... )" block, respecting quoted strings and escapes
strip_list_block <- function(s) {
pos <- gregexpr('[()"\\\\]', s, perl = TRUE)[[1]]
if (pos[1] == -1) return(s)
depth <- 0; in_str <- FALSE; skip_until <- 0
for (p in pos) {
if (p <= skip_until) next
ch <- substr(s, p, p)
if (ch == "\\") { skip_until <- p + 1; next }
if (in_str) { if (ch == '"') in_str <- FALSE; next }
if (ch == '"') { in_str <- TRUE; next }
if (ch == "(") depth <- depth + 1
if (ch == ")") {
depth <- depth - 1
if (depth == 0) return(substr(s, p + 1, nchar(s)))
}
}
s
}
extract_post_text <- function(rec) {
if (is.na(rec)) return(NA_character_)
date_rx <- "^\\d{4}-\\d{2}-\\d{2}T[^;]*?; "
lang_rx <- "^[a-z]{2,3}(?:-[A-Za-z0-9]+)?(?:; |$)"
x <- sub("^app\\.bsky\\.feed\\.post; ", "", rec)
if (grepl(date_rx, x, perl = TRUE)) {
x <- sub(date_rx, "", x, perl = TRUE)
for (i in 1:10) {
if (startsWith(x, "list(")) {
x <- sub("^; ", "", strip_list_block(x))
} else if (grepl(lang_rx, x, perl = TRUE)) {
x <- sub(lang_rx, "", x, perl = TRUE)
} else break
}
x
} else { # bridged posts: text; original url; date; ...
m <- regmatches(x, regexec("(?s)^(.*?); https?://[^;\\s]+; \\d{4}-\\d{2}-\\d{2}T[^;]*?; ",
x, perl = TRUE))[[1]]
if (length(m) > 1) m[2] else x
}
}
clean_post_text <- function(x) {
x %>%
str_replace_all("<[^>]+>", " ") %>% # html tags (bridged posts)
str_replace_all("&", "&") %>%
str_replace_all(" |"|'|<|>", " ") %>%
str_replace_all("[\u2018\u2019]", "'") %>% # curly apostrophes
str_replace_all("@[\\w.-]+", " ") %>% # @mentions
str_replace_all("https?://\\S+|www\\.\\S+", " ") %>% # urls
str_replace_all("\\b[\\w-]+(\\.[\\w-]+)*\\.(com|org|net|gov|edu|us|io|co|tv|news|live)\\b\\S*", " ") %>% # truncated links
str_replace_all("#", "") %>% # keep hashtag words
str_replace_all("[^\\p{L}\\p{N}\\s'-]", " ") %>% # emojis / punctuation
str_squish()
}
A post that appears in both candidates’ collections (it mentions
both) is kept once per candidate, and flagged with
in_both.
posts_0 <- raw_posts %>%
distinct(candidate, uri, .keep_all = TRUE) # batch 1 and batch 2 overlap
posts_1 <- posts_0 %>%
mutate(text_raw = map_chr(record, extract_post_text),
text = clean_post_text(text_raw)) %>%
filter(!is.na(text), nchar(text) > 0) # drops image-only / link-only posts
posts_2 <- posts_1 %>%
mutate(lang = detect_language(text)) %>%
filter(is.na(lang) | lang == "en") # keep English (and undetermined short posts)
posts <- posts_2 %>%
group_by(uri) %>% mutate(in_both = n_distinct(candidate) > 1) %>% ungroup() %>%
mutate(pid = paste(candidate, uri, sep = "|"))
tibble(
step = c("Raw rows", "Unique posts per candidate", "With usable text", "English / undetermined"),
posts = c(nrow(raw_posts), nrow(posts_0), nrow(posts_1), nrow(posts_2))
) %>%
kbl(caption = "Cleaning log") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)
| step | posts |
|---|---|
| Raw rows | 1974 |
| Unique posts per candidate | 1282 |
| With usable text | 1174 |
| English / undetermined | 1149 |
posts %>% select(candidate, day, handle, text) %>% head(10)
tokens_all <- posts %>%
select(pid, candidate, day, in_both, text) %>%
unnest_tokens(word, text) %>%
mutate(word = str_remove(word, "'s$")) %>%
filter(!str_detect(word, "^\\d+$"), nchar(word) > 1)
tokens <- tokens_all %>%
anti_join(stop_words, by = "word") %>%
anti_join(custom_stop, by = "word")
post_len <- tokens_all %>% count(pid, name = "n_words")
tibble(tokens_total = nrow(tokens_all), tokens_after_stopwords = nrow(tokens),
vocabulary = n_distinct(tokens$word))
posts %>%
left_join(post_len, by = "pid") %>%
plot_ly(x = ~n_words, color = ~candidate, colors = pal, type = "histogram",
opacity = 0.65, nbinsx = 40) %>%
layout(barmode = "overlay", title = "Words per post",
xaxis = list(title = "Words (after cleaning)"), yaxis = list(title = "Posts"))
make_bar <- function(d, color, title) {
d <- d %>% mutate(term = fct_reorder(term, n))
plot_ly(d, x = ~n, y = ~term, type = "bar", orientation = "h",
marker = list(color = color),
hovertemplate = "%{y}: %{x}<extra></extra>") %>%
layout(title = title, xaxis = list(title = "Count"), yaxis = list(title = ""),
margin = list(l = 120))
}
top_words <- tokens %>%
count(candidate, word, sort = TRUE) %>%
group_by(candidate) %>% slice_max(n, n = 15, with_ties = FALSE) %>% ungroup() %>%
rename(term = word)
make_bar(filter(top_words, candidate == "Becerra"), pal[["Becerra"]], "Top words: Becerra posts")
make_bar(filter(top_words, candidate == "Hilton"), pal[["Hilton"]], "Top words: Hilton posts")
bigrams <- posts %>%
select(candidate, text) %>%
unnest_tokens(bigram, text, token = "ngrams", n = 2) %>%
filter(!is.na(bigram)) %>%
separate(bigram, c("w1", "w2"), sep = " ", remove = FALSE) %>%
filter(!w1 %in% stop_words$word, !w2 %in% stop_words$word,
!w1 %in% custom_stop$word, !w2 %in% custom_stop$word,
!str_detect(w1, "^\\d+$"), !str_detect(w2, "^\\d+$"))
top_bigrams <- bigrams %>%
count(candidate, bigram, sort = TRUE) %>%
group_by(candidate) %>% slice_max(n, n = 15, with_ties = FALSE) %>% ungroup() %>%
rename(term = bigram)
make_bar(filter(top_bigrams, candidate == "Becerra"), pal[["Becerra"]], "Top bigrams: Becerra posts")
make_bar(filter(top_bigrams, candidate == "Hilton"), pal[["Hilton"]], "Top bigrams: Hilton posts")
Which words are most characteristic of one candidate’s posts versus the other’s? Only posts that appear in one collection are used, and words need at least 10 uses. Positive values lean Becerra; negative values lean Hilton.
word_counts <- tokens %>%
filter(!in_both) %>%
count(candidate, word) %>%
pivot_wider(names_from = candidate, values_from = n, values_fill = 0)
tot_b <- sum(word_counts$Becerra)
tot_h <- sum(word_counts$Hilton)
word_odds <- word_counts %>%
filter(Becerra + Hilton >= 10) %>%
mutate(log_ratio = log2(((Becerra + 1) / (tot_b + 1)) / ((Hilton + 1) / (tot_h + 1))))
top_odds <- bind_rows(
slice_max(word_odds, log_ratio, n = 12, with_ties = FALSE) %>% mutate(favors = "Becerra"),
slice_min(word_odds, log_ratio, n = 12, with_ties = FALSE) %>% mutate(favors = "Hilton")
) %>% mutate(word = fct_reorder(word, log_ratio))
plot_ly(top_odds, x = ~log_ratio, y = ~word, color = ~favors, colors = pal,
type = "bar", orientation = "h") %>%
layout(title = "Most distinctive words", xaxis = list(title = "log2 odds ratio (Becerra / Hilton)"),
yaxis = list(title = ""), margin = list(l = 110))
posts %>%
count(candidate, handle, sort = TRUE) %>%
group_by(candidate) %>% slice_max(n, n = 8, with_ties = FALSE) %>% ungroup() %>%
kbl(col.names = c("Collection", "Account", "Posts")) %>%
kable_styling(bootstrap_options = c("striped", "hover", "condensed"), full_width = FALSE)
| Collection | Account | Posts |
|---|---|---|
| Becerra | andyheppelle.bsky.social | 74 |
| Becerra | bluegitana.bsky.social | 47 |
| Becerra | davidsicairos.bsky.social | 22 |
| Becerra | nypost.com | 17 |
| Becerra | plaintanjane.bsky.social | 13 |
| Becerra | bsfavourite.bsky.social | 8 |
| Becerra | pollresults.org | 8 |
| Becerra | sfpoliticsbriefly.bsky.social | 8 |
| Hilton | davidsicairos.bsky.social | 22 |
| Hilton | christopretensism.bsky.social | 16 |
| Hilton | judgement-bot.bsky.social | 15 |
| Hilton | bsfavourite.bsky.social | 13 |
| Hilton | nypost.com | 13 |
| Hilton | porcellato.bsky.social | 9 |
| Hilton | chicagonewsbench.bsky.social | 7 |
| Hilton | pollresults.org | 7 |
Sentiment is scored with the Bing lexicon (built
into tidytext, no download needed). For each post:
score = (# positive words) - (# negative words), and the
post is labeled Positive (> 0), Negative (< 0) or Neutral / none
(= 0). This is a simple word-count method: it does not detect negation
or sarcasm.
bing <- get_sentiments("bing") %>%
distinct(word, .keep_all = TRUE) %>%
filter(!word %in% sent_exclude)
post_sent <- tokens_all %>%
inner_join(bing, by = "word") %>%
count(pid, sentiment) %>%
pivot_wider(names_from = sentiment, values_from = n, values_fill = 0)
posts <- posts %>%
left_join(post_sent, by = "pid") %>%
mutate(
positive = replace_na(positive, 0L),
negative = replace_na(negative, 0L),
score = positive - negative,
label = case_when(score > 0 ~ "Positive", score < 0 ~ "Negative", TRUE ~ "Neutral / none"),
label = factor(label, levels = c("Negative", "Neutral / none", "Positive"))
)
posts %>%
group_by(candidate) %>%
summarise(posts = n(),
mean_score = round(mean(score), 3),
pct_positive = percent(mean(label == "Positive"), accuracy = 0.1),
pct_neutral = percent(mean(label == "Neutral / none"), accuracy = 0.1),
pct_negative = percent(mean(label == "Negative"), accuracy = 0.1)) %>%
kbl(caption = "Sentiment summary by candidate") %>%
kable_styling(bootstrap_options = c("striped", "hover"), full_width = FALSE)
| candidate | posts | mean_score | pct_positive | pct_neutral | pct_negative |
|---|---|---|---|---|---|
| Becerra | 576 | -0.201 | 19.1% | 45.0% | 35.9% |
| Hilton | 573 | -0.293 | 20.1% | 43.6% | 36.3% |
A quick significance check on posts that appear in only one collection (so the two groups do not share posts):
excl <- posts %>% filter(!in_both)
wilcox.test(score ~ candidate, data = excl)
##
## Wilcoxon rank sum test with continuity correction
##
## data: score by candidate
## W = 86266, p-value = 0.7148
## alternative hypothesis: true location shift is not equal to 0
posts %>%
mutate(score_clip = pmax(pmin(score, 5), -5)) %>%
plot_ly(x = ~score_clip, color = ~candidate, colors = pal, type = "histogram",
histnorm = "probability") %>%
layout(barmode = "group", title = "Distribution of post sentiment scores (clipped at ±5)",
xaxis = list(title = "Score (positive words - negative words)", dtick = 1),
yaxis = list(title = "Share of posts", tickformat = ".0%"))
sent_words <- tokens_all %>%
inner_join(bing, by = "word") %>%
count(candidate, word, sentiment) %>%
group_by(candidate, sentiment) %>% slice_max(n, n = 10, with_ties = FALSE) %>% ungroup()
make_sent_bar <- function(cand) {
d <- sent_words %>%
filter(candidate == cand) %>%
mutate(n_signed = if_else(sentiment == "negative", -n, n),
word = fct_reorder(word, n_signed))
plot_ly(d, x = ~n_signed, y = ~word, color = ~sentiment,
colors = c(negative = "#D95F02", positive = "#1B9E77"),
type = "bar", orientation = "h", text = ~n, hoverinfo = "text+y") %>%
layout(title = paste("Top sentiment words:", cand),
xaxis = list(title = "\u2190 negative words | positive words \u2192 (count)"),
yaxis = list(title = ""), margin = list(l = 110))
}
make_sent_bar("Becerra")
make_sent_bar("Hilton")
Days are defined in C:/Users/zxu3/Documents/R/bluesky time. Days with fewer than 5 posts are hidden from the sentiment charts because their averages are unreliable. The dotted vertical line marks Election Day.
election_shape <- list(list(type = "line", x0 = as.character(election_day),
x1 = as.character(election_day), xref = "x",
y0 = 0, y1 = 1, yref = "paper",
line = list(color = "gray40", dash = "dot")))
election_note <- list(list(x = as.character(election_day), y = 1, yref = "paper",
text = "Election Day", showarrow = FALSE,
xanchor = "left", font = list(color = "gray40")))
daily <- posts %>%
group_by(candidate, day) %>%
summarise(n = n(),
mean_score = mean(score),
se = sd(score) / sqrt(n()),
pct_pos = mean(label == "Positive"),
pct_neg = mean(label == "Negative"),
.groups = "drop") %>%
mutate(lo = mean_score - 1.96 * se, hi = mean_score + 1.96 * se)
daily_ok <- daily %>% filter(n >= min_posts_per_day)
# 3-day rolling mean of post scores (pools posts from the day and the two days before)
roll <- posts %>%
group_by(candidate) %>%
group_modify(function(.x, .y) {
days <- sort(unique(.x$day))
tibble(day = days,
roll_mean = map_dbl(days, function(d) mean(.x$score[.x$day >= d - 2 & .x$day <= d])))
}) %>% ungroup() %>%
semi_join(daily_ok, by = c("candidate", "day"))
Volume reflects what was collected (each collection holds at most about 500 posts), so treat it as a rough indicator of activity rather than an exact count.
plot_ly(daily, x = ~day, y = ~n, color = ~candidate, colors = pal,
type = "scatter", mode = "lines+markers") %>%
layout(title = "Posts per day", xaxis = list(title = ""), yaxis = list(title = "Posts"),
shapes = election_shape, annotations = election_note, hovermode = "x unified")
Solid line = daily mean score with a 95% confidence band; dotted line = 3-day rolling mean.
plot_ly(daily_ok, x = ~day, color = ~candidate, colors = pal) %>%
add_ribbons(ymin = ~lo, ymax = ~hi, alpha = 0.15, line = list(width = 0),
showlegend = FALSE, hoverinfo = "none") %>%
add_trace(y = ~mean_score, type = "scatter", mode = "lines+markers") %>%
add_lines(data = roll, x = ~day, y = ~roll_mean, color = ~candidate,
line = list(dash = "dot", width = 2), showlegend = FALSE) %>%
layout(title = "Mean post sentiment score by day",
xaxis = list(title = ""), yaxis = list(title = "Mean score (pos - neg words)"),
shapes = election_shape, annotations = election_note, hovermode = "x unified")
Each cell shows how often a word appears per 1,000 words on that day, for each candidate’s 15 most frequent words.
term_heatmap <- function(cand, n_terms = 15, color = "Blues") {
d0 <- tokens %>% filter(candidate == cand)
top_terms <- d0 %>% count(word, sort = TRUE) %>% slice_head(n = n_terms) %>% pull(word)
day_totals <- d0 %>% count(day, name = "total")
d <- d0 %>%
filter(word %in% top_terms) %>%
count(day, word) %>%
left_join(day_totals, by = "day") %>%
mutate(per_1k = n / total * 1000) %>%
complete(day = seq(min(d0$day), max(d0$day), by = "day"),
word = top_terms, fill = list(per_1k = 0)) %>%
select(word, day, per_1k) %>%
pivot_wider(names_from = day, values_from = per_1k, values_fill = 0) %>%
arrange(match(word, rev(top_terms))) # most frequent word ends up on top
plot_ly(x = names(d)[-1], y = d$word, z = as.matrix(d[, -1]),
type = "heatmap", colors = color,
hovertemplate = "%{y}<br>%{x}: %{z:.1f} per 1k words<extra></extra>") %>%
layout(title = paste("Top terms by day:", cand),
xaxis = list(title = ""),
yaxis = list(title = "", categoryorder = "array", categoryarray = d$word))
}
term_heatmap("Becerra", color = "Blues")
term_heatmap("Hilton", color = "Reds")
Share of each day’s posts that mention a keyword (prefix match, so
tax also matches taxes). Edit
keywords to follow any topics you like.
keywords <- c("poll", "debate", "trump", "newsom", "housing", "homeless", "gas", "tax")
kw_daily <- map_dfr(keywords, function(k) {
posts %>%
group_by(candidate, day) %>%
summarise(keyword = k, n_posts = n(),
hits = sum(str_detect(str_to_lower(text), paste0("\\b", k))),
.groups = "drop")
}) %>%
mutate(pct = hits / n_posts) %>%
filter(n_posts >= min_posts_per_day)
kw_plot <- function(cand) {
kw_daily %>%
filter(candidate == cand) %>%
plot_ly(x = ~day, y = ~pct, color = ~keyword, type = "scatter", mode = "lines+markers") %>%
layout(title = paste("Keyword share of posts:", cand),
xaxis = list(title = ""), yaxis = list(title = "% of posts", tickformat = ".0%"),
shapes = election_shape, annotations = election_note, hovermode = "x unified")
}
kw_plot("Becerra")
kw_plot("Hilton")
in_both); the head-to-head tests
exclude them.sent_exclude and custom_stop in the Settings
section, and consider adding a second lexicon or a transformer model for
a robustness check.cld2 removes clearly
non-English posts; very short posts with no detected language are
kept.indexed_at
(when Bluesky indexed the post, in UTC) and are converted to
C:/Users/zxu3/Documents/R/bluesky.sessionInfo()
## R version 4.3.2 (2023-10-31 ucrt)
## Platform: x86_64-w64-mingw32/x64 (64-bit)
## Running under: Windows 11 x64 (build 22631)
##
## Matrix products: default
##
##
## locale:
## [1] LC_COLLATE=English_United States.utf8
## [2] LC_CTYPE=English_United States.utf8
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.utf8
##
## time zone: America/Los_Angeles
## tzcode source: internal
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] scales_1.4.0 cld2_1.2.6 kableExtra_1.4.0 plotly_4.12.1
## [5] tidytext_0.4.1 lubridate_1.9.5 forcats_1.0.1 stringr_1.6.0
## [9] dplyr_1.1.4 purrr_1.2.2 readr_2.2.0 tidyr_1.3.2
## [13] tibble_3.3.0 ggplot2_4.0.3 tidyverse_2.0.0
##
## loaded via a namespace (and not attached):
## [1] gtable_0.3.6 xfun_0.60 bslib_0.12.0 htmlwidgets_1.6.4
## [5] lattice_0.22-9 tzdb_0.5.0 vctrs_0.6.5 tools_4.3.2
## [9] crosstalk_1.2.1 generics_0.1.4 parallel_4.3.2 janeaustenr_1.0.0
## [13] pkgconfig_2.0.3 tokenizers_0.3.0 Matrix_1.6-1.1 data.table_1.17.8
## [17] RColorBrewer_1.1-3 S7_0.2.2 lifecycle_1.0.5 compiler_4.3.2
## [21] farver_2.1.2 textshaping_1.0.5 SnowballC_0.7.1 htmltools_0.5.9
## [25] sass_0.4.9 yaml_2.3.10 pillar_1.11.1 crayon_1.5.3
## [29] jquerylib_0.1.4 cachem_1.1.0 tidyselect_1.2.1 digest_0.6.39
## [33] stringi_1.8.9 fastmap_1.2.0 grid_4.3.2 cli_3.6.5
## [37] magrittr_2.0.4 dichromat_2.0-0.1 withr_3.0.3 bit64_4.8.4
## [41] timechange_0.4.0 rmarkdown_2.31 httr_1.4.8 bit_4.6.0
## [45] otel_0.2.0 hms_1.1.4 evaluate_1.0.5 knitr_1.51
## [49] viridisLite_0.4.3 rlang_1.1.6 Rcpp_1.1.0 glue_1.8.0
## [53] xml2_1.5.2 svglite_2.2.2 rstudioapi_0.19.0 vroom_1.7.1
## [57] jsonlite_2.0.0 R6_2.6.1 systemfonts_1.3.2
Jimmy Zhenning Xu, Ph.D. | github.com/utjimmyx