Draft: personalize these paragraphs after running the analysis and completing the review.
This newly designed lab gives me a useful way to connect data preparation, text analysis, sentiment analysis, and visualization in one reproducible report. Working with AI also shows why I need to describe my files and constraints clearly. My workbook contains a 100-row first scrape, a 15-row second sample, a third file with the same 100 post IDs as the first scrape, and supplied sentiment samples of 20 and 15 posts. Treating these as independent collections or counting the sentiment samples as additional posts would produce misleading results. The code below documents missing text, checks duplicates, and separates the source records from the analysis. I will use its checks to verify the results before interpreting them. A worked example of timestamp validation and a clearer distinction between a sample and total conversation volume would make this lab easier to follow.
Human judgment remains important when interpreting multilingual posts, product promotions, sarcasm, and comments about athletes rather than the brand itself. An English sentiment dictionary can label individual words without understanding the intended meaning or target of a post. For that reason, this analysis restricts dictionary scoring to posts marked as English, preserves unmatched posts as a separate category, and provides the existing manual labels for comparison. I will inspect the original wording and matched words before accepting any automated interpretation. The unequal sample sizes, missing language information, and relative timestamps also limit comparisons over time. AI can help organize the workflow and write code, but I remain responsible for checking assumptions, explaining disagreements, and making recommendations supported by the evidence.
This version includes a snapshot of the supplied workbook data inside
the file, so knitting does not depend on the workbook filename or its
folder. To refresh from a later workbook, set
params: workbook to its actual path; otherwise leave it
blank. Embedded data are visible in the source and the resulting HTML
includes tables of public post text, so review the report before
publishing.
This individual report uses the uploaded workbook to examine recurring words, engagement, and sentiment. The three supplied batches remain separate versions. Scrape 3 is not assumed to be a new collection session. The other workbook tabs contain copies or summaries of these records and are not additional independent observations.
All Posts sheet supplies the readable text and metrics;
Scrape 1 Raw supplies identifiers, language, and timestamp
metadata.The script does not claim that 100 versus 15 records means conversation volume fell. Search coverage, sampling methods, and time windows differ.
| Field | Value |
|---|---|
| Collection source | BlueFacts live Bluesky hashtag pages: #Nike and #sneakers |
| Source URL 1 | https://bluefacts.app/tag/nike |
| Source URL 2 | https://bluefacts.app/tag/sneakers |
| Collection date | October 26, 2026 |
| Important limitation | This is a smaller manually compiled public sample, not a full API export. Relative timestamps are preserved as displayed. Rows with counts shown as 0 reflect no visible engagement in the listing, not independently verified API counts. |
| batch | source_records |
|---|---|
| Scrape 1 | 100 |
| Scrape 2 | 15 |
| Scrape 3 | 100 |
ids1 <- unique(na.omit(batch1$post_id))
ids3 <- unique(na.omit(batch3$post_id))
overlap_check <- tibble(
measure = c("Scrape 3 distinct supplied IDs", "IDs also in Scrape 1", "IDs absent from Scrape 1"),
value = c(length(ids3), length(intersect(ids1, ids3)), length(setdiff(ids3, ids1))))
kable(overlap_check)
| measure | value |
|---|---|
| Scrape 3 distinct supplied IDs | 100 |
| IDs also in Scrape 1 | 100 |
| IDs absent from Scrape 1 | 0 |
metric_versions <- batch1 %>% select(post_id, likes_1 = likes, reposts_1 = reposts) %>%
inner_join(batch3 %>% select(post_id, likes_3 = likes, reposts_3 = reposts), by = "post_id") %>%
mutate(comparable = !is.na(likes_1) & !is.na(reposts_1) & !is.na(likes_3) & !is.na(reposts_3),
metrics_differ = comparable & (likes_1 != likes_3 | reposts_1 != reposts_3))
kable(tibble(shared_ids = nrow(metric_versions),
comparable_metrics = sum(metric_versions$comparable),
different_metric_values = sum(metric_versions$metrics_differ)))
| shared_ids | comparable_metrics | different_metric_values |
|---|---|---|
| 100 | 100 | 42 |
Scrape 3 is retained as requested so its supplied version can be inspected. Its shared post IDs are not new independent observations. Different metrics or restored text do not establish when or how a file was collected. Do not infer growth or a new collection session from the filename alone.
Blank text and spreadsheet-error strings cannot support text analysis. Exclude them from the analytic dataset and export them for inspection. Missing metrics remain missing rather than becoming zero. Duplicate removal is confined to each batch: use a post URI when available, otherwise normalized handle plus text. This fallback cannot prove that two similar posts are identical.
flagged <- combined_raw %>%
mutate(
text_clean = normalize_text(text_original),
text_invalid = text_clean == "" |
text_clean %in% c("#NAME?", "#REF!", "#VALUE!", "#N/A", "NA"),
content_key = paste(handle, str_to_lower(text_clean), sep = " :: "),
dedup_key = if_else(!is.na(post_id) & post_id != "", post_id, content_key),
encoding_flag = str_detect(text_clean, "\u00c3|\u00c2|\u00e2\u20ac|\ufffd")
)
valid_before_dedup <- flagged %>% filter(!text_invalid)
clean <- valid_before_dedup %>% distinct(batch, dedup_key, .keep_all = TRUE) %>%
mutate(engagement = if_else(is.na(likes) | is.na(reposts), NA_real_, likes + reposts))
audit <- flagged %>% group_by(batch) %>%
summarise(source_records = n(), unusable_text = sum(text_invalid), .groups = "drop") %>%
left_join(clean %>% count(batch, name = "retained"), by = "batch") %>%
mutate(retained = replace_na(retained, 0L),
duplicates_removed = source_records - unusable_text - retained)
kable(audit, caption = "Source-to-analysis reconciliation")
| batch | source_records | unusable_text | retained | duplicates_removed |
|---|---|---|---|---|
| Scrape 1 | 100 | 4 | 96 | 0 |
| Scrape 2 | 15 | 0 | 15 | 0 |
| Scrape 3 | 100 | 3 | 97 | 0 |
write_csv(flagged %>% filter(text_invalid), file.path(output_dir, "excluded_text_records.csv"))
write_csv(clean, file.path(output_dir, "clean_posts.csv"))
kable(clean %>% group_by(batch) %>% summarise(
missing_likes = sum(is.na(likes)), missing_reposts = sum(is.na(reposts)),
text_encoding_flags = sum(encoding_flag), .groups = "drop"))
| batch | missing_likes | missing_reposts | text_encoding_flags |
|---|---|---|---|
| Scrape 1 | 0 | 0 | 0 |
| Scrape 2 | 0 | 0 | 0 |
| Scrape 3 | 0 | 0 | 0 |
Encoding flags are review prompts, not automatic proof of corruption. Original text is retained, and the script does not guess replacements for damaged text.
sample_summary <- clean %>% group_by(batch) %>% summarise(
retained_posts = n(),
distinct_nonblank_handles = n_distinct(handle[handle != ""]),
valid_post_dates = sum(!is.na(posted_at)),
complete_engagement_rows = sum(!is.na(engagement)),
known_engagement_total = if (all(is.na(engagement))) NA_real_ else sum(engagement, na.rm = TRUE),
mean_known_engagement = if (all(is.na(engagement))) NA_real_ else mean(engagement, na.rm = TRUE),
.groups = "drop")
kable(sample_summary, digits = 2)
| batch | retained_posts | distinct_nonblank_handles | valid_post_dates | complete_engagement_rows | known_engagement_total | mean_known_engagement |
|---|---|---|---|---|---|---|
| Scrape 1 | 96 | 54 | 96 | 96 | 79 | 0.82 |
| Scrape 2 | 15 | 8 | 0 | 15 | 46 | 3.07 |
| Scrape 3 | 97 | 55 | 97 | 97 | 79 | 0.81 |
date_coverage <- clean %>% group_by(batch) %>% summarise(
earliest_utc = if (all(is.na(posted_at))) NA_character_ else
format(min(posted_at, na.rm = TRUE), tz = "UTC", usetz = TRUE),
latest_utc = if (all(is.na(posted_at))) NA_character_ else
format(max(posted_at, na.rm = TRUE), tz = "UTC", usetz = TRUE),
.groups = "drop")
kable(date_coverage)
| batch | earliest_utc | latest_utc |
|---|---|---|
| Scrape 1 | 2026-10-22 18:15:20 UTC | 2026-10-22 22:30:14 UTC |
| Scrape 2 | NA | NA |
| Scrape 3 | 2026-10-22 18:15:20 UTC | 2026-10-22 22:30:14 UTC |
Totals describe the retained sample; missing metrics make them partial. Relative times in Scrape 2 remain as supplied. The collection date is not substituted for the date of every post. A comparison of weekly trends requires multiple comparable time windows and reliable timestamps, which this workbook does not establish.
plotly::plot_ly(audit, x = ~batch, y = ~retained, type = "bar",
marker = list(color = "#245B89"),
hovertemplate = "%{x}<br>Retained sample records: %{y}<extra></extra>") %>%
plotly::layout(title = "Retained records by sample (not total platform volume)",
xaxis = list(title = "Sample"), yaxis = list(title = "Retained records"))
weekly_observed <- clean %>% filter(!is.na(posted_at)) %>%
mutate(week_start_utc = as.Date(floor_date(posted_at, "week", week_start = 1))) %>%
count(batch, week_start_utc, name = "dated_records")
kable(weekly_observed, caption = "Observed dated records by Monday-start week; missing dates excluded")
| batch | week_start_utc | dated_records |
|---|---|---|
| Scrape 1 | 2026-10-19 | 96 |
| Scrape 3 | 2026-10-19 | 97 |
top_posts <- clean %>% filter(!is.na(engagement)) %>%
group_by(batch) %>% arrange(desc(engagement), record_id, .by_group = TRUE) %>%
slice_head(n = 5) %>% ungroup() %>%
select(batch, record_id, handle, text_clean, likes, reposts, engagement)
kable(top_posts, caption = "Top five retained records per sample; ties ordered by record ID")
| batch | record_id | handle | text_clean | likes | reposts | engagement |
|---|---|---|---|---|---|---|
| Scrape 1 | Scrape1-row2 | realmadrid-fans.bsky.social | ✠One to watch: Spotless: Barcelona unveils special WHITE boots for El Clasico Agree or disagree? #RealMadrid #HalaMadrid #ElClasico | 25 | 1 | 26 |
| Scrape 1 | Scrape1-row3 | fcbarcelona-news.bsky.social | ✠One to watch: Spotless: Barcelona unveils special WHITE boots for El Clasico Agree or disagree? #FCBarcelona #Barca #ElClasico | 4 | 1 | 5 |
| Scrape 1 | Scrape1-row4 | swooshsupply.bsky.social | Nike SBâs skate-ready Air Force 1 returns in a clean color combination of Cool Grey and Court Green, releasing next Tuesday, October 27. | 4 | 1 | 5 |
| Scrape 1 | Scrape1-row5 | hnkbae.bsky.social | Ah, sim, meus queridos Nike, Adidas e⊠| 4 | 0 | 4 |
| Scrape 1 | Scrape1-row6 | goods.wouldcop.com | Nike Tech Fleece (M), L â $11 all-in. The lowest of 1224 current size-L listings in the same condition on the same site (oldest listed ~28 months ago). (sized from a single reference garment) | 4 | 0 | 4 |
| Scrape 2 | Scrape2-row7 | butterflygirl24.bsky.social | Nikeâs apology for the Converse Ad. There wasnât any information of disciplinary action towards those responsible for the ad. The apology is not an apology if itâs empty words w no acknowledgment of the harm of racism. So how will Nike n Converse Do Better? #nike | 30 | 7 | 37 |
| Scrape 2 | Scrape2-row8 | solefeen.bsky.social | Jalen Brunson x Nike Kobe 3 Low Protro âAranciaâ Availability: December 11th, 2026. Retail Price: $190 USD. #Nike #Kobe3 #JalenBrunson #Sneakers | 5 | 3 | 8 |
| Scrape 2 | Scrape2-row2 | jbjaso3.bsky.social | Nike Crater Impact âBlack Off Noirâ #WDYWT #KOTD #Sneakers #Sneakerhead #Nike | 1 | 0 | 1 |
| Scrape 2 | Scrape2-row10 | vibecircuit.bsky.social | .SWOOSH x Nike Air Max 1 âLow Polyâ: Future tech meets retro aesthetic, and it actually works. #nike #airmax1 #sneakers #sneakerhead #kicks | 0 | 0 | 0 |
| Scrape 2 | Scrape2-row11 | toppnews.bsky.social | News post linking Nike with Paris and London and an external Financial Times article. #Nike | 0 | 0 | 0 |
| Scrape 3 | Scrape3-row71 | roryblank.bsky.social | I mean I donât know that Travis Knight, Nike scion, is hurting for money, but Laika movies are extremely time and labor intensive endeavors and they spent \(100 million dollars making a stop motion movie, and by they, I mean also he's the producer and head of the company that produced it. | 25| 1| 26| |Scrape 3 |Scrape3-row58 |ricardooliveria2.bsky.social |đ„ TĂȘnis Nike Mc Trainer 3 đš De R\) 599 por R$ 289 đïž Use o Cupom: MODA2310 đ https://meli.la/2qL9VCU #amazon #Afazenda #Jonatas #desconto #promo | 4 | 0 | 4 |
| Scrape 3 | Scrape3-row60 | promoatomicas.bsky.social | đ„ TĂȘnis Nike Mc Trainer 3 đš De R$ 599 por R$ 289 đïž Use o Cupom: MODA2310 đ https://meli.la/2qL9VCU #mercadolivre #amazon #Afazenda #oferta #blackfriday | 4 | 0 | 4 |
| Scrape 3 | Scrape3-row84 | ricardooliveria2.bsky.social | đ„ TĂȘnis Nike Uplift Sc Masculino đš R$ 266 đïž Cupom: MODA2310 đ https://meli.la/1PZ54Me #Revelando #amazon #SDV #desconto #oferta | 4 | 0 | 4 |
| Scrape 3 | Scrape3-row86 | promoatomicas.bsky.social | đ„ TĂȘnis Nike Uplift Sc Masculino đš R$ 266 đïž Cupom: MODA2310 đ https://meli.la/1PZ54Me #Afazenda #SDV #Entregou #promoção #oferta | 4 | 0 | 4 |
account_counts <- clean %>% filter(handle != "") %>% count(batch, handle, name = "posts") %>%
group_by(batch) %>% mutate(share_of_named_posts = posts / sum(posts)) %>%
arrange(desc(posts), handle, .by_group = TRUE) %>% slice_head(n = 5) %>% ungroup()
kable(account_counts, digits = 3, caption = "Most frequent accounts; denominator excludes blank handles")
| batch | handle | posts | share_of_named_posts |
|---|---|---|---|
| Scrape 1 | kickterminal.bsky.social | 15 | 0.156 |
| Scrape 1 | garfieldelric.bsky.social | 8 | 0.083 |
| Scrape 1 | sneakerscouts.bsky.social | 8 | 0.083 |
| Scrape 1 | promobit-promo.bsky.social | 5 | 0.052 |
| Scrape 1 | ofertandopromocoes.bsky.social | 4 | 0.042 |
| Scrape 2 | solefeen.bsky.social | 5 | 0.333 |
| Scrape 2 | vibecircuit.bsky.social | 3 | 0.200 |
| Scrape 2 | dealzbro.bsky.social | 2 | 0.133 |
| Scrape 2 | backthefudgeoff.bsky.social | 1 | 0.067 |
| Scrape 2 | butterflygirl24.bsky.social | 1 | 0.067 |
| Scrape 3 | kickterminal.bsky.social | 15 | 0.155 |
| Scrape 3 | garfieldelric.bsky.social | 8 | 0.082 |
| Scrape 3 | sneakerscouts.bsky.social | 8 | 0.082 |
| Scrape 3 | promobit-promo.bsky.social | 5 | 0.052 |
| Scrape 3 | ofertandopromocoes.bsky.social | 4 | 0.041 |
Compare original wording before describing what top posts have in common. Engagement counts reflect different collection methods and observation times. They do not measure sales or establish the reasons a post attracted attention.
All readable posts are tokenized. Frequency results are separated by batch and language. English stop words are removed only for posts explicitly marked as English. Non-English or unknown-language frequencies need language-specific review. URLs are removed for tokenization; original text remains available.
token_input <- clean %>%
mutate(text_for_tokens = str_remove_all(text_clean, "https?://\\S+|www\\.\\S+"),
english_eligible = str_detect(language, "^en(?:$|[-;,_ ])"))
tokens <- token_input %>% select(record_id, batch, language, english_eligible, text_for_tokens) %>%
unnest_tokens(word, text_for_tokens)
stopword_lookup <- tidytext::stop_words %>% distinct(word) %>% mutate(is_stopword = TRUE)
content_tokens <- tokens %>% left_join(stopword_lookup, by = "word") %>%
filter(str_detect(word, "\\p{L}"),
!(english_eligible & replace_na(is_stopword, FALSE)))
word_counts <- content_tokens %>% count(batch, language, word, sort = TRUE)
kable(word_counts %>% group_by(batch) %>% slice_max(n, n = 10, with_ties = FALSE) %>% ungroup(),
caption = "Common retained words; language shown to avoid mixing vocabularies")
| batch | language | word | n |
|---|---|---|---|
| Scrape 1 | en | nike | 39 |
| Scrape 1 | fr | nike | 35 |
| Scrape 1 | unknown | nike | 24 |
| Scrape 1 | fr | chez | 15 |
| Scrape 1 | unknown | the | 15 |
| Scrape 1 | en | tĂȘnis | 13 |
| Scrape 1 | fr | ad | 13 |
| Scrape 1 | fr | sneakers | 12 |
| Scrape 1 | en | cupom | 11 |
| Scrape 1 | fr | le | 11 |
| Scrape 2 | unknown | nike | 27 |
| Scrape 2 | unknown | sneakers | 10 |
| Scrape 2 | unknown | air | 9 |
| Scrape 2 | unknown | the | 8 |
| Scrape 2 | unknown | force | 6 |
| Scrape 2 | unknown | low | 6 |
| Scrape 2 | unknown | airforce1 | 5 |
| Scrape 2 | unknown | availability | 5 |
| Scrape 2 | unknown | price | 5 |
| Scrape 2 | unknown | retail | 5 |
| Scrape 3 | en | nike | 39 |
| Scrape 3 | fr | nike | 35 |
| Scrape 3 | unknown | nike | 24 |
| Scrape 3 | fr | chez | 15 |
| Scrape 3 | unknown | the | 15 |
| Scrape 3 | en | tĂȘnis | 13 |
| Scrape 3 | fr | ad | 13 |
| Scrape 3 | fr | sneakers | 12 |
| Scrape 3 | en | cupom | 11 |
| Scrape 3 | fr | le | 11 |
write_csv(word_counts, file.path(output_dir, "word_counts.csv"))
english_words <- content_tokens %>% filter(english_eligible, batch == "Scrape 1") %>% count(word, sort = TRUE) %>%
slice_head(n = 15) %>% arrange(n, word)
if (nrow(english_words) > 0) {
english_words$word <- factor(english_words$word, levels = english_words$word)
plotly::plot_ly(english_words, x = ~n, y = ~word, type = "bar", orientation = "h",
marker = list(color = "#32867C"),
hovertemplate = "%{y}<br>Occurrences: %{x}<extra></extra>") %>%
plotly::layout(title = "Frequent English words in Scrape 1 (shared posts not pooled)",
xaxis = list(title = "Occurrences"), yaxis = list(title = ""),
margin = list(l = 120))
} else cat("No posts are explicitly marked as English; no English word chart was produced.")
The Bing lexicon labels English words as positive or negative. The score is the number of positive word occurrences minus negative word occurrences. The scoring tokens are taken before stop-word removal, so frequency filtering cannot silently change sentiment inputs.
bing <- tidytext::get_sentiments("bing")
matched_words <- tokens %>% filter(english_eligible) %>% inner_join(bing, by = "word")
per_post_matches <- matched_words %>% group_by(record_id) %>% summarise(
positive_words = sum(sentiment == "positive"),
negative_words = sum(sentiment == "negative"), .groups = "drop")
scored <- token_input %>% left_join(per_post_matches, by = "record_id") %>%
mutate(across(c(positive_words, negative_words), ~replace_na(.x, 0L)),
positive_words = if_else(english_eligible, positive_words, NA_integer_),
negative_words = if_else(english_eligible, negative_words, NA_integer_),
matched_count = positive_words + negative_words,
score = positive_words - negative_words,
automated_label = case_when(
!english_eligible ~ "Not scored: language",
matched_count == 0 ~ "No matches",
score > 0 ~ "Positive", score < 0 ~ "Negative", TRUE ~ "Balanced matches"))
language_coverage <- scored %>% count(batch, language, english_eligible, name = "posts")
kable(language_coverage, caption = "Language coverage and scoring eligibility")
| batch | language | english_eligible | posts |
|---|---|---|---|
| Scrape 1 | de | FALSE | 1 |
| Scrape 1 | en | TRUE | 45 |
| Scrape 1 | fr | FALSE | 15 |
| Scrape 1 | nl | FALSE | 1 |
| Scrape 1 | pt | FALSE | 6 |
| Scrape 1 | pt-br | FALSE | 4 |
| Scrape 1 | unknown | FALSE | 24 |
| Scrape 2 | unknown | FALSE | 15 |
| Scrape 3 | de | FALSE | 2 |
| Scrape 3 | en | TRUE | 45 |
| Scrape 3 | fr | FALSE | 15 |
| Scrape 3 | nl | FALSE | 1 |
| Scrape 3 | pt | FALSE | 6 |
| Scrape 3 | pt-br | FALSE | 4 |
| Scrape 3 | unknown | FALSE | 24 |
coverage <- scored %>% group_by(batch) %>% summarise(
retained = n(), eligible = sum(english_eligible),
with_dictionary_matches = sum(english_eligible & matched_count > 0, na.rm = TRUE),
not_scored = sum(!english_eligible), .groups = "drop")
kable(coverage)
| batch | retained | eligible | with_dictionary_matches | not_scored |
|---|---|---|---|---|
| Scrape 1 | 96 | 45 | 21 | 51 |
| Scrape 2 | 15 | 0 | 0 | 15 |
| Scrape 3 | 97 | 45 | 21 | 52 |
sentiment_summary <- scored %>% filter(english_eligible) %>%
count(batch, automated_label, name = "posts") %>% group_by(batch) %>%
mutate(percent_of_eligible = 100 * posts / sum(posts)) %>% ungroup()
kable(sentiment_summary, digits = 1,
caption = "Percentages use all English-eligible retained posts in the corresponding sample")
| batch | automated_label | posts | percent_of_eligible |
|---|---|---|---|
| Scrape 1 | Negative | 5 | 11.1 |
| Scrape 1 | No matches | 24 | 53.3 |
| Scrape 1 | Positive | 16 | 35.6 |
| Scrape 3 | Negative | 5 | 11.1 |
| Scrape 3 | No matches | 24 | 53.3 |
| Scrape 3 | Positive | 16 | 35.6 |
write_csv(scored, file.path(output_dir, "automated_sentiment.csv"))
write_csv(matched_words, file.path(output_dir, "sentiment_word_matches.csv"))
Scrape 2 has no language metadata in the supplied file and is not automatically scored. Read its posts and document their language before extending English scoring to them. Scrape 3 repeats first-scrape IDs and has no documented collection time. This report therefore does not claim a sentiment trend across the three supplied versions.
if (nrow(sentiment_summary) > 0) {
plotly::plot_ly(sentiment_summary, x = ~batch, y = ~percent_of_eligible,
color = ~automated_label, type = "bar",
text = ~paste0(posts, " posts; ", round(percent_of_eligible, 1), "%"),
hovertemplate = "%{x}<br>%{text}<extra>%{fullData.name}</extra>") %>%
plotly::layout(title = "Dictionary sentiment among English-eligible posts",
barmode = "stack", xaxis = list(title = "Sample with language coverage"),
yaxis = list(title = "Percent of English-eligible posts", range = c(0, 100)))
} else cat("No English-eligible posts were available for dictionary sentiment analysis.")
The workbookâs labels are retained as supplied. A favorable promotional description is not necessarily a customerâs endorsement, and a negative running experience is not necessarily criticism of the shoe brand. Inspect the stated reasons rather than treating the labels as a gold standard.
manual <- manual_raw %>% transmute(
manual_row = row_number(), author = `Author name`,
text_original = `Post text`, text_key = str_to_lower(normalize_text(`Post text`)),
manual_label = str_to_title(str_trim(Sentiment)),
supplied_reason = `Reason (manual tag)`)
stopifnot(all(manual$manual_label %in% c("Positive", "Negative", "Neutral")))
manual_summary <- manual %>% count(manual_label, name = "posts") %>%
mutate(percent = 100 * posts / sum(posts))
kable(manual_summary, digits = 1, caption = "Existing supplied labels, recomputed from the 20-row sample")
| manual_label | posts | percent |
|---|---|---|
| Negative | 1 | 5 |
| Neutral | 10 | 50 |
| Positive | 9 | 45 |
# A text-only match is used because the manual sheet has no stable post ID.
# Match only when exactly one first-scrape record has that normalized text.
manual_lookup <- scored %>% filter(batch == "Scrape 1") %>%
mutate(text_key = str_to_lower(text_clean)) %>% group_by(text_key) %>%
filter(n() == 1) %>% ungroup() %>%
select(text_key, record_id, language, english_eligible, automated_label, score)
manual_comparison <- manual %>% left_join(manual_lookup, by = "text_key") %>%
mutate(comparison_status = case_when(
is.na(record_id) ~ "No unique retained text match",
!english_eligible ~ "Not comparable: language",
!automated_label %in% c("Positive", "Negative") ~ "Review no-match or balanced label",
manual_label == automated_label ~ "Same label",
TRUE ~ "Different label: inspect wording"))
kable(manual_comparison %>% select(manual_row, manual_label, automated_label,
language, comparison_status, supplied_reason))
| manual_row | manual_label | automated_label | language | comparison_status | supplied_reason |
|---|---|---|---|---|---|
| 1 | Neutral | Positive | en | Different label: inspect wording | Product listing/discount code; mainly informational promotion, no clear emotional opinion. |
| 2 | Positive | Not scored: language | unknown | Not comparable: language | Highlights a large discount, framing the product deal favorably. |
| 3 | Neutral | No matches | en | Review no-match or balanced label | Simple link prompt with no clear positive or negative opinion. |
| 4 | Positive | No matches | en | Review no-match or balanced label | Uses favorable wording such as ânewestâ and âlimited editionâ to promote a release. |
| 5 | Positive | No matches | en | Review no-match or balanced label | Expresses enthusiastic affection for the art/design. |
| 6 | Neutral | No matches | en | Review no-match or balanced label | Product name only; no clear opinion. |
| 7 | Positive | Not scored: language | unknown | Not comparable: language | Frames the price as a deal by comparing it with retail price. |
| 8 | Neutral | NA | NA | No unique retained text match | Post text is missing, so sentiment cannot be inferred; counted as neutral/unclear. |
| 9 | Neutral | No matches | en | Review no-match or balanced label | Hashtags only; no clear opinion. |
| 10 | Neutral | Not scored: language | unknown | Not comparable: language | News-style product headline and a question; does not clearly express an opinion. |
| 11 | Positive | Not scored: language | pt | Not comparable: language | Promotional wording emphasizes a low price and a coupon. |
| 12 | Negative | Positive | en | Different label: inspect wording | Uses strongly critical language and explicitly calls for a boycott. |
| 13 | Positive | Not scored: language | fr | Not comparable: language | Promotional product post invites opinions and presents the item for sale. |
| 14 | Positive | No matches | en | Review no-match or balanced label | Positive styling suggestion pairing a business suit with Nike sneakers. |
| 15 | Positive | NA | NA | No unique retained text match | Promotional post highlights the product and price. |
| 16 | Positive | NA | NA | No unique retained text match | Emphasizes a low price compared with many listings. |
| 17 | Neutral | Positive | en | Different label: inspect wording | Product listing with no clear evaluative language. |
| 18 | Neutral | No matches | en | Review no-match or balanced label | Product listing with no clear evaluative language. |
| 19 | Neutral | Positive | en | Different label: inspect wording | Short product announcement without a clear positive or negative opinion. |
| 20 | Neutral | Not scored: language | unknown | Not comparable: language | Reports a legal/trademark development in a factual tone. |
write_csv(manual_comparison, file.path(output_dir, "manual_vs_automated.csv"))
imported_check <- imported_manual %>% filter(Sentiment != "Total") %>%
transmute(manual_label = Sentiment, imported_posts = metric_number(`Number of posts`)) %>%
full_join(manual_summary %>% select(manual_label, posts), by = "manual_label") %>%
mutate(matches = !is.na(imported_posts) & !is.na(posts) & imported_posts == posts)
kable(imported_check, caption = "Independent reconciliation to the separately supplied sentiment totals")
| manual_label | imported_posts | posts | matches |
|---|---|---|---|
| Positive | 9 | 9 | TRUE |
| Negative | 1 | 1 | TRUE |
| Neutral | 10 | 10 | TRUE |
manual3 <- manual3_raw %>% transmute(
raw_row = as.integer(`Raw row`), author = Author, text_original = `Post text`,
manual_label = str_to_title(str_trim(Sentiment)),
supplied_reason = `Coding rationale`, sampling_note = `Random method`)
stopifnot(all(manual3$manual_label %in% c("Positive", "Negative", "Neutral")))
manual3_summary <- manual3 %>% count(manual_label, name = "posts") %>%
mutate(percent = 100 * posts / sum(posts))
kable(manual3_summary, digits = 1, caption = "Separate supplied Scrape 3 sample (15 labels)")
| manual_label | posts | percent |
|---|---|---|
| Negative | 2 | 13.3 |
| Neutral | 5 | 33.3 |
| Positive | 8 | 53.3 |
manual3_comparison <- manual3 %>% left_join(
scored %>% filter(batch == "Scrape 3") %>%
select(raw_row = source_row, record_id, automated_label, score, language), by = "raw_row")
kable(manual3_comparison %>% select(raw_row, manual_label, automated_label, language,
text_original, supplied_reason))
| raw_row | manual_label | automated_label | language | text_original | supplied_reason |
|---|---|---|---|---|---|
| 83 | Negative | Negative | en | Check out what Iâm selling. OT Sports blank Minor League Baseball Tacoma Rainers jersey (size M, w/stains): Get up to $20 off* when you use my code JCGUWH to sign up for Mercari. *Terms apply #mercari www.mercari.com/us/item/m441⊠| Complaint, negative affect, or unfavorable cue. |
| 16 | Positive | Not scored: language | fr | #ad |
đ EN STOCK CHEZ NIKE
đ Chaussures de running sur route Nike Journey Run pour homme - Noir
En stock chez Nike Ă 70⏠đ„
Celle-lĂ mĂ©rite un coup dâĆil
#Nike #Sneakers
https://www.kickterminal.com/cop/nike/2q3KgQ?c=bluesky |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 5|Neutral |Not scored: language |pt |Ah, sim, meus queridos Nike, Adidas e⊠|Primarily factual/ambiguous; no clear positive or negative evaluation. | | 96|Negative |Positive |en |The Golden Gate Bridge taken from an outlook near the Nike Missile Silo. âčïž |Complaint, negative affect, or unfavorable cue. | | 37|Positive |Not scored: language |unknown |Nike G.T. Future âDMVâ
Available via @nikestore for $110.97 (retail $200) #ad
https://ow.ly/G2B550ZY5qE |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 33|Neutral |Not scored: language |unknown |7-Elevenâs trademark case over Nikeâs convenience-store Air Max 95 ended with prejudice and no explanation. Hereâs where the shoe stands now. |Primarily factual/ambiguous; no clear positive or negative evaluation. | | 30|Positive |Not scored: language |unknown |Nike Ja 3 âAnimal Packâ
Available via @footlocker |$130| #ad @JaMorant
https://ow.ly/Nhop50ZY5Pa |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 19|Positive |Not scored: language |fr |#ad
đ REPĂRĂ CHEZ NIKE
đ Chaussure de tennis pour surface dure Nike Vapor Lite 3 pour homme - Bleu
Disponible sur le site, 59⏠đ
Elle vous tente ?
#Nike #Sneakers
https://www.kickterminal.com/cop/nike/4rxAyV?c=bluesky |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 15|Positive |Not scored: language |fr |#ad
đ REPĂRĂ CHEZ NIKE
đ Chaussure dâentraĂźnement Nike Metcon 10 AMP pour homme - Rouge
En stock chez Nike Ă 105⏠đ„
Celle-lĂ mĂ©rite un coup dâĆil
#Nike #Sneakers
https://www.kickterminal.com/cop/nike/9df2he?c=bluesky |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 88|Positive |Not scored: language |unknown |đ„ TĂȘnis Nike Uplift Sc Masculino
đ” Por: R$ 266,79 đïž Cupom: MODA2310 https://meli.la/2Y4c5g9
âą AnĂșncio Mercado Livre |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 71|Neutral |Negative |en |I mean I donât know that Travis Knight, Nike scion, is hurting for money, but Laika movies are extremely time and labor intensive endeavors and they spent $100 million dollars making a stop motion movie, and by they, I mean also heâs the producer and head of the company that produced it. |Primarily factual/ambiguous; no clear positive or negative evaluation. | | 13|Positive |Not scored: language |fr |#ad
đ 31 OCTOBRE CHEZ ASPHALTGOLD
đ Nike Air Jordan 14 Retro Forest Green â Gorge Green Light Graphite
PrĂ©vu pour le 31 octobre đ„
Vous comptez tenter ? đ
#Jordan #AirJordan14 #AJ14 #Sneakers #SneakerRelease
https://www.kickterminal.com/cop/asphaltgold/3STrjq?c=bluesky |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 77|Positive |Not scored: language |unknown |Nike x SKIMS just dropped a bold red collection, these are the styles Iâd shop first |Promotional/enthusiastic language, product availability, deal, or favorable shopping cue. | | 56|Neutral |No matches |en |TĂȘnis Nike Mc Trainer 3 Masculino |Primarily factual/ambiguous; no clear positive or negative evaluation. | | 6|Neutral |Not scored: language |unknown |Nike Tech Fleece (M), L â $11 all-in. The lowest of 1224 current size-L listings in the same condition on the same site (oldest listed ~28 months ago). (sized from a single reference garment) |Primarily factual/ambiguous; no clear positive or negative evaluation. |
write_csv(manual3_comparison, file.path(output_dir, "scrape3_manual_vs_automated.csv"))
The source labels report their sampling method as a fixed-seed random sample; this is a supplied claim rather than a reconstruction of that sampling process. The 15 labels differ from the earlier 20-row sample and should not be pooled as 35 unique people or used to estimate a sentiment change. Inspect each rationale. For example, a resale description mentioning a stained jersey may describe a productâs condition without expressing dissatisfaction with the brand.
percent_check <- sentiment_summary %>% group_by(batch) %>%
summarise(total = sum(percent_of_eligible), .groups = "drop")
checks <- tibble(
check = c("Source row accounting balances for each batch",
"No repeated within-batch post keys remain",
"All analytic text is nonblank",
"One sentiment output per retained record",
"Every retained post has an automated status",
"Matched dictionary words reconcile to per-post counts",
"Eligible sentiment percentages total 100 per sample",
"Supplied sentiment totals reconcile to sample labels"),
passed = c(
all(audit$source_records == audit$unusable_text + audit$duplicates_removed + audit$retained),
!anyDuplicated(paste(clean$batch, clean$dedup_key)),
all(nchar(clean$text_clean) > 0),
nrow(scored) == nrow(clean) && !anyDuplicated(scored$record_id),
all(!is.na(scored$automated_label)),
sum(scored$matched_count, na.rm = TRUE) == nrow(matched_words),
all(abs(percent_check$total - 100) < 1e-8),
all(imported_check$matches)))
kable(checks)
| check | passed |
|---|---|
| Source row accounting balances for each batch | TRUE |
| No repeated within-batch post keys remain | TRUE |
| All analytic text is nonblank | TRUE |
| One sentiment output per retained record | TRUE |
| Every retained post has an automated status | TRUE |
| Matched dictionary words reconcile to per-post counts | TRUE |
| Eligible sentiment percentages total 100 per sample | TRUE |
| Supplied sentiment totals reconcile to sample labels | TRUE |
stopifnot(all(checks$passed))
These tests check internal consistency, not the truth of opinions or the representativeness of the collection.
The first record in the supplied All Posts table lists
25 likes and 1 repost. The hand calculation is 25 + 1 =
26. Verify these values in Excel as well.
first_record <- clean %>% filter(batch == "Scrape 1", source_row == 2L)
stopifnot(nrow(first_record) == 1L)
hand_check <- tibble(record_id = first_record$record_id,
hand_expected = 26, code_total = first_record$engagement,
matches_expected = first_record$likes == 25 &
first_record$reposts == 1 & first_record$engagement == 26)
kable(hand_check)
| record_id | hand_expected | code_total | matches_expected |
|---|---|---|---|
| Scrape1-row2 | 26 | 26 | TRUE |
The expected value refers to this supplied workbook snapshot. A mismatch in a future refreshed workbook calls for a new source check rather than forcing the data to match an old expected number.
set.seed(4000)
eligible_review_ids <- scored$record_id[scored$english_eligible %in% TRUE]
review_ids <- if (length(eligible_review_ids) > 0L) {
sample(eligible_review_ids, size = min(10L, length(eligible_review_ids)), replace = FALSE)
} else character(0)
review_records <- scored %>% filter(record_id %in% review_ids) %>%
select(record_id, text_original, automated_label, positive_words, negative_words, score)
kable(review_records, caption = "Reproducible sample for your own contextual review")
| record_id | text_original | automated_label | positive_words | negative_words | score |
|---|---|---|---|---|---|
| Scrape1-row21 | Tottenham 2027/28 away kit leak reveals historic pink design for outfield players |
www.spurs-web.com/spurs-news/t⊠|Negative | 0| 1| -1| |Scrape1-row29 |If Iâm Nike Iâd be asking a lot of questions, too. |No matches | 0| 0| 0| |Scrape1-row35 |Business suit and Nike sneakers
For the working woman in your households |No matches | 0| 0| 0| |Scrape1-row42 |Please and thank you. |Positive | 1| 0| 1| |Scrape1-row96 |The Golden Gate Bridge taken from an outlook near the Nike Missile Silo. âčïž |Positive | 1| 0| 1| |Scrape3-row56 |TĂȘnis Nike Mc Trainer 3 Masculino |No matches | 0| 0| 0| |Scrape3-row66 |đ Mochila Masculina Nike Heritage Backpack cor preta por R$ 115
Ganhe R$30 no Mercado Pago: https://mpago.li/2gudrhL use o cupom mercado livre MODA2310 https://meli.la/1jf9P2M
AnĂșncio |đMeus Grupos: entr.ai/lamorimpromos |No matches | 0| 0| 0| |Scrape3-row78 |Check out Nike NFL Seattle Seahawks Elite 51 blank navy blue home jersey (adult size 52) ebay.io/m/kgyj0X #eBay via @eBay |Positive | 1| 0| 1| |Scrape3-row81 |Check out what Iâm selling. MLB Nike Los Angeles Dodgers Shohei Ohtani replica #17 jersey (NWT/adult sz XL): Get up to $20 off* when you use my code JCGUWH to sign up for Mercari. *Terms apply #mercari www.mercari.com/us/item/m588⊠|No matches | 0| 0| 0| |Scrape3-row87 |đ„ TĂȘnis Nike Uplift Sc Masculino
đš R$ 266 đïž Cupom: MODA2310
#Revelando #Jonatas #Entregou #oferta #promo |Positive | 1| 0| 1|
kable(matched_words %>% filter(record_id %in% review_ids) %>%
count(record_id, word, sentiment), caption = "Exact word matches for the review sample")
| record_id | word | sentiment | n |
|---|---|---|---|
| Scrape1-row21 | leak | negative | 1 |
| Scrape1-row42 | thank | positive | 1 |
| Scrape1-row96 | golden | positive | 1 |
| Scrape3-row78 | elite | positive | 1 |
| Scrape3-row87 | uplift | positive | 1 |
# Complete reviewer_label and reviewer_note in lab_outputs/my_verification.csv.
# It is created once and then retained so re-knitting does not overwrite your work.
verification_path <- file.path(output_dir, "my_verification.csv")
if (!file.exists(verification_path)) {
write_csv(review_records %>% mutate(reviewer_label = "", reviewer_note = ""), verification_path)
}
verification_notes <- read_csv(verification_path, show_col_types = FALSE,
col_types = cols(.default = col_character()))
stopifnot(all(c("record_id", "reviewer_label", "reviewer_note") %in% names(verification_notes)))
stopifnot(!anyDuplicated(verification_notes$record_id))
review_progress <- tibble(
record_id = review_ids) %>%
left_join(verification_notes %>% select(record_id, reviewer_label, reviewer_note), by = "record_id") %>%
mutate(completed = !is.na(reviewer_label) & str_trim(reviewer_label) != "" &
!is.na(reviewer_note) & str_trim(reviewer_note) != "")
kable(review_progress)
| record_id | reviewer_label | reviewer_note | completed |
|---|---|---|---|
| Scrape3-row56 | NA | NA | FALSE |
| Scrape1-row35 | NA | NA | FALSE |
| Scrape3-row87 | NA | NA | FALSE |
| Scrape1-row96 | NA | NA | FALSE |
| Scrape1-row42 | NA | NA | FALSE |
| Scrape3-row81 | NA | NA | FALSE |
| Scrape3-row78 | NA | NA | FALSE |
| Scrape3-row66 | NA | NA | FALSE |
| Scrape1-row29 | NA | NA | FALSE |
| Scrape1-row21 | NA | NA | FALSE |
cat("Completed contextual reviews:", sum(review_progress$completed), "of", nrow(review_progress))
## Completed contextual reviews: 0 of 10
Open lab_outputs/my_verification.csv, read the original
wording, and enter Positive, Negative, Mixed, Neutral, or Unclear plus a
short reason. Save and re-knit. Do not report that you personally
verified labels until you have done so. The file is keyed by record ID;
re-create it deliberately if a new source workbook changes the selected
sample.
The report imports 215 source records and retains 208 records for text analysis after the stated exclusions. The supplied manual sample contains 20 labels, with 15 additional supplied labels in the third file. These are separate measures and should not be added together.
Complete after inspecting the computed tables and original posts:
My final interpretation: [Replace with your results, one checked example, one limitation, and one recommendation.]
Two requests made in this conversation were:
Request 1: âcan you add this data into my excel sheetâ
Response summary: The assistant produced an updated workbook with separate tabs for both scrapes, collection notes, and the supplied sentiment summary, preserving the four original analysis tabs. It noted that Scrape 2 has 15 posts. This is a summary, not a verbatim transcript; screenshot the actual exchange.
Request 2 (opening phrase): âwith that can you give me a rmarkdown scriptâ
The second request also included the lab requirements: a beginning reflection, cleaning, text and sentiment analysis, Plotly, verification, AI critique, and prompt screenshots. This report is the assistantâs response. Screenshot that request and the response as well.
Suggested improved follow-up â send after you run the report:
Review my R Markdown results using readxl, dplyr, tidytext, and plotly. My input workbook is Social_Media_Analysis_Updated.xlsx; the data come from All Posts, Scrape 1 Raw, Scrape 2, and Sentiment Sample. Verify that duplicate representations are not counted twice, missing text is excluded transparently, and English Bing sentiment is not applied to posts with other or unknown languages. Preserve relative timestamps and do not interpret 100 versus 15 source records as a change in platform volume. Inspect the checks, matched words, and my manual review below; identify one unsupported interpretation and provide corrected R code and an explanation. Do not claim to have run anything you did not run. [Paste my actual output, review notes, and any error messages here.]
This suggested follow-up is not a completed exchange. Record the actual prompt you send and the actual response received. Post screenshots of the exchanges to the discussion forum; do not fabricate screenshots or responses.
Social_Media_Analysis_Updated.xlsx,
especially the source tabs and collection notes cited above.sessionInfo()
## R version 4.6.2 (2026-10-29)
## Platform: x86_64-pc-linux-gnu
## Running under: Ubuntu 24.04.5 LTS
##
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/openblas-pthread/libblas.so.3
## LAPACK: /usr/lib/x86_64-linux-gnu/openblas-pthread/libopenblasp-r0.3.26.so; LAPACK version 3.12.0
##
## locale:
## [1] LC_CTYPE=C.UTF-8 LC_NUMERIC=C LC_TIME=C.UTF-8
## [4] LC_COLLATE=C.UTF-8 LC_MONETARY=C.UTF-8 LC_MESSAGES=C.UTF-8
## [7] LC_PAPER=C.UTF-8 LC_NAME=C LC_ADDRESS=C
## [10] LC_TELEPHONE=C LC_MEASUREMENT=C.UTF-8 LC_IDENTIFICATION=C
##
## time zone: UTC
## tzcode source: system (glibc)
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] knitr_1.52 plotly_4.12.1 ggplot2_4.0.4 tidytext_0.4.3
## [5] lubridate_1.9.5 readr_2.2.0 tibble_3.3.1 stringr_1.6.0
## [9] tidyr_1.3.2 dplyr_1.2.1
##
## loaded via a namespace (and not attached):
## [1] janeaustenr_1.0.0 sass_0.4.10 generics_0.1.4
## [4] stringi_1.8.9 lattice_0.23-1 hms_1.1.4
## [7] digest_0.6.39 magrittr_2.0.5 evaluate_1.0.5
## [10] grid_4.6.2 timechange_0.4.0 RColorBrewer_1.1-3
## [13] fastmap_1.2.0 jsonlite_2.0.0 Matrix_1.7-6
## [16] httr_1.4.9 purrr_1.2.2 crosstalk_1.2.2
## [19] viridisLite_0.4.3 scales_1.4.0 jquerylib_0.1.4
## [22] cli_3.6.6 crayon_1.5.3 rlang_1.3.0
## [25] tokenizers_0.3.0 bit64_4.8.6 withr_3.0.3
## [28] cachem_1.1.0 yaml_2.3.12 otel_0.3.0
## [31] parallel_4.6.2 tools_4.6.2 tzdb_0.5.0
## [34] vctrs_0.7.3 R6_2.6.1 lifecycle_1.0.5
## [37] bit_4.6.0 htmlwidgets_1.6.4 vroom_1.7.1
## [40] pkgconfig_2.0.3 pillar_1.11.1 bslib_0.12.0
## [43] gtable_0.3.6 glue_1.8.1 data.table_1.18.6.1
## [46] Rcpp_1.1.2 xfun_0.62 tidyselect_1.2.1
## [49] farver_2.1.2 htmltools_0.5.9 SnowballC_0.7.1
## [52] rmarkdown_2.32 compiler_4.6.2 S7_0.2.2