Two-paragraph reflection

Using AI made the coding part of this assignment easier, but I still need to check whether the results make sense. The code can label words as positive or negative without understanding the whole sentence. For example, it might count “good” as positive even when someone says a product is “not good.” It could also confuse someone’s opinion about Hailey Bieber with their opinion about Rhode’s products. This shows why running the code without errors is only one part of the assignment.

My judgment matters when deciding whether a post is about Rhode skincare and what the person actually means. Searching for “Rhode” could include unrelated posts, while searching for “Rhode skincare” could leave out people who only mention a product’s name. Bluesky users also may not represent all Rhode customers, so I would be careful about making broad claims from this sample. To improve the lab, I would include a short comparison between the computer’s labels and students’ labels so we can see where the results differ and explain why.

Question and data source

What topics appear in this sample of Rhode skincare posts, what sentiment does a simple dictionary detect, and how credible are those labels after human review? This is one dataset for the current lab; the provided instructions do not require a Day 1/Day 3 comparison. Public posts are not verified purchases or a random sample of customers. Results apply to the collected sample only.

Import and clean

The code removes missing/blank text and duplicate post URIs. When a URI is absent, it retains the row and uses a local row identifier; the absence of stable IDs limits duplicate detection. Identical text on different URIs remains because it can represent separate posts. URLs and handles are removed only from the analysis copy; original text is preserved. Missing engagement counts remain missing.

raw <- read.csv(params$csv,stringsAsFactors=FALSE,check.names=FALSE,
                fileEncoding="UTF-8-BOM",na.strings=c("NA"))
aliases <- list(text=c("text","post_text"),uri=c("uri","post_uri"),
  author_handle=c("author_handle","handle"),
  like_count=c("like_count","likeCount","likes"),
  repost_count=c("repost_count","repostCount","reposts"))
for(nm in names(aliases)) {
  hit <- intersect(aliases[[nm]],names(raw))
  if(length(hit)) raw[[nm]] <- raw[[hit[1]]]
}
if(!"text" %in% names(raw)) stop("CSV needs a text column. Available columns: ",paste(names(raw),collapse=", "))
raw$source_row <- seq_len(nrow(raw))
if(!"uri" %in% names(raw)) raw$uri <- NA_character_
if(!"author_handle" %in% names(raw)) raw$author_handle <- NA_character_
for(nm in c("like_count","repost_count")) {
  if(!nm %in% names(raw)) raw[[nm]] <- NA_real_
  raw[[nm]] <- suppressWarnings(as.numeric(raw[[nm]]))
  raw[[nm]][!is.na(raw[[nm]]) & (!is.finite(raw[[nm]]) | raw[[nm]]<0)] <- NA_real_
}
raw <- raw %>% mutate(text=as.character(text),
  missing_text=is.na(text) | !nzchar(trimws(text)),
  has_uri=!is.na(uri) & nzchar(trimws(uri)),
  duplicate_uri=has_uri & duplicated(uri),
  removal_reason=case_when(missing_text ~ "missing/blank text",
    duplicate_uri ~ "duplicate URI",TRUE ~ "retained"))
posts <- raw %>% filter(removal_reason=="retained") %>%
  mutate(post_id=if_else(has_uri,uri,paste0("local_row_",source_row)),
    text_clean=str_squish(str_replace_all(str_replace_all(
      text,"https?://[^[:space:]]+"," "),"@[A-Za-z0-9_.-]+"," ")),
    engagement=like_count+repost_count)
if(!nrow(posts)) stop("No nonblank unique posts remain.")
cleaning <- raw %>% count(removal_reason,name="rows")
write.csv(raw %>% select(source_row,uri,removal_reason),
  "results/cleaning_decisions.csv",row.names=FALSE)
write.csv(posts,"results/cleaned_posts.csv",row.names=FALSE,na="")
removal_reason rows
missing/blank text 55
retained 245

There are 300 input rows and 245 retained posts. 0 retained posts lack an original URI. If your CSV includes several pulls, this report deduplicates across them; analyze pulls separately if you intend a temporal comparison.

Word frequency

Tokenize into lowercase English-style word tokens, remove numbers and stop words for word frequency, and exclude the search terms “rhode,” “skin,” and “skincare.” Sentiment uses the token stream before these frequency exclusions. Frequency is not the same as topic modeling: read posts before claiming a theme.

tokens <- posts %>% select(post_id,text_clean) %>%
  unnest_tokens(word,text_clean) %>% filter(str_detect(word,"[a-z]"))
words <- tokens %>% anti_join(tidytext::stop_words,by="word") %>%
  filter(!word %in% c("rhode","skin","skincare")) %>%
  count(word,sort=TRUE,name="occurrences")
write.csv(words,"results/word_frequency.csv",row.names=FALSE)
word occurrences
hailey 195
beauty 119
bieber 115
billion 81
brand 81
bieber’s 59
deal 50
bieber’s 39
makeup 38
elf 29
sephora 29
justin 28
acquired 22
products 21
company 20

Sentiment method

The Bing lexicon assigns positive or negative labels to individual English words (Silge & Robinson, 2017). For each post, score = positive-word occurrences minus negative-word occurrences. Scores above/below zero are positive/negative. A zero with matches is balanced; zero matches is unclassified. Neither is automatically a neutral human opinion. Repeated words count repeatedly. The model does not handle negation, sarcasm, emojis, or the target of the opinion.

lexicon <- tidytext::get_sentiments("bing") %>% distinct(word,sentiment)
matches <- tokens %>% inner_join(lexicon,by="word")
counts <- matches %>% group_by(post_id) %>% summarise(
  positive=sum(sentiment=="positive"),negative=sum(sentiment=="negative"),.groups="drop")
scored <- posts %>% left_join(counts,by="post_id") %>%
  mutate(positive=replace_na(positive,0L),negative=replace_na(negative,0L),
    matched_words=positive+negative,score=positive-negative,
    model_label=case_when(matched_words==0 ~ "unclassified",
      score>0 ~ "positive",score<0 ~ "negative",TRUE ~ "balanced"))
levels_sent <- c("positive","negative","balanced","unclassified")
sentiment <- data.frame(model_label=levels_sent,
  posts=as.integer(table(factor(scored$model_label,levels=levels_sent)))) %>%
  mutate(percent=100*posts/nrow(scored))
write.csv(matches,"results/sentiment_word_matches.csv",row.names=FALSE)
write.csv(scored,"results/posts_with_sentiment.csv",row.names=FALSE,na="")
write.csv(sentiment,"results/sentiment_summary.csv",row.names=FALSE)
model_label posts percent
positive 145 59.183673
negative 18 7.346939
balanced 16 6.530612
unclassified 66 26.938775

Interactive Plotly chart

Hover over a bar to inspect its exact count and percentage. The denominator is all retained posts, including balanced and unclassified posts.

fig <- plotly::plot_ly(sentiment,x=~model_label,y=~posts,type="bar",
  text=~paste0(model_label,": ",posts," posts (",round(percent,1),"%)"),
  hoverinfo="text",marker=list(color=c("#27877C","#C05D66","#A29175","#818995")))
fig <- plotly::layout(fig,title="Rhode skincare: dictionary sentiment",
  xaxis=list(title="Model classification",categoryorder="array",categoryarray=levels_sent),
  yaxis=list(title="Number of posts"))
fig

Verify the code and interpretation

Automatic sanity checks

checks <- data.frame(check=c("Cleaning counts reconcile","One row per retained ID",
  "All retained posts scored","Sentiment counts reconcile","Percentages sum to 100",
  "Matched-word totals reconcile"),
  passed=c(sum(cleaning$rows)==nrow(raw),!anyDuplicated(posts$post_id),
    nrow(scored)==nrow(posts),sum(sentiment$posts)==nrow(scored),
    abs(sum(sentiment$percent)-100)<1e-8,
    sum(scored$matched_words)==nrow(matches)))
stopifnot(all(checks$passed))
check passed
Cleaning counts reconcile TRUE
One row per retained ID TRUE
All retained posts scored TRUE
Sentiment counts reconcile TRUE
Percentages sum to 100 TRUE
Matched-word totals reconcile TRUE

These checks detect processing inconsistencies, not whether sentiment labels are correct. Below is the first retained post and the exact dictionary matches used to score it. Read the text, count positive and negative matches yourself, and confirm that the difference equals the displayed score.

post_id text positive negative score model_label
at://did:plc:dm4eys2zqvfkxqnt4b3dyhys/app.bsky.feed.post/3mzq4r62zra24

The Rhode founder is promoting a more positive approach to skincare

#HaileyBieber #AntiAgeing #BeautyStandards #Skincare #BeautyIndustry

Read More : https://ift.tt/x4GDKvT

https://ift.tt/vx5rOpQ

November 7, 2026 at 02:36PM
1 0 1 positive
word sentiment occurrences
positive positive 1

My independent hand calculation: [positive occurrences] − [negative occurrences] = [score]. [Explain whether the computed label fits the meaning of the post.]

Human spot check of up to 20 posts

The first knit creates manual_review.csv. Before looking at the model labels, open that CSV and read each sampled post. Enter positive, negative, neutral, or unclear in human_sentiment; judge sentiment toward Rhode’s products. Enter yes, no, or uncertain in brand_relevant, and explain disagreements or ambiguities in notes. Save as CSV UTF-8, close Excel, then knit again. Only English posts are suitable for this English lexicon; note other languages. The sample stays fixed across knits. Existing reviews are never overwritten.

review_path <- "manual_review.csv"
if(!file.exists(review_path)) {
  set.seed(4000)
  sample_ids <- sample(sort(scored$post_id),min(20,nrow(scored)))
  review <- scored[match(sample_ids,scored$post_id),c("post_id","text")]
  review$human_sentiment <- ""; review$brand_relevant <- ""; review$notes <- ""
  write.csv(review,review_path,row.names=FALSE,na="",fileEncoding="UTF-8")
}
review <- read.csv(review_path,stringsAsFactors=FALSE,check.names=FALSE,
  fileEncoding="UTF-8-BOM",na.strings=c("NA"))
required <- c("post_id","human_sentiment","brand_relevant","notes")
if(!all(required %in% names(review))) stop("Keep the original manual_review.csv columns.")
if(nrow(review)!=min(20,nrow(scored)) || anyNA(review$post_id) ||
   anyDuplicated(review$post_id) || any(!review$post_id %in% scored$post_id))
  stop("Review file does not match dataset. Move it aside and knit to regenerate, then relabel.")
for(nm in c("human_sentiment","brand_relevant")) {
  review[[nm]][is.na(review[[nm]])] <- ""
  review[[nm]] <- tolower(trimws(review[[nm]]))
}
if(any(!review$human_sentiment %in% c("","positive","negative","neutral","unclear")))
  stop("Use positive, negative, neutral, unclear, or blank in human_sentiment.")
if(any(!review$brand_relevant %in% c("","yes","no","uncertain")))
  stop("Use yes, no, uncertain, or blank in brand_relevant.")
# Join fresh source text so accidental edits in the review CSV do not change evidence.
audit <- review %>% select(-any_of("text")) %>%
  left_join(scored %>% select(post_id,text,model_label,score),by="post_id")
write.csv(audit,"results/human_model_audit.csv",row.names=FALSE,na="")

Human sentiment labels completed: 0 / 20; relevance checks: 0 / 20.

## Manual verification pending. No model accuracy claim is justified yet.

Agreement above excludes neutral, unclear, balanced, unclassified, and unconfirmed brand relevance. It is a restricted diagnostic, not overall model accuracy. Use the cross-tabulation to examine all reviewed labels and abstentions. A small sample also limits how precisely model performance can be estimated.

Evidence-based critique: [Quote or paraphrase one actual sampled post, state the model and human labels, and explain the role of negation, context, relevance, language, or sentiment target. Report the number checked.]

Findings and a marketing implication

My 2–3 themes: [Name themes and cite actual posts supporting each.]

My recommendation: [Connect a specific supported theme to a content test, customer question, or follow-up research. Avoid claiming causal impact, medical benefits, or that popularity proves product quality.]

Sampling limitation: The search wording may exclude product-only references; results may include promotion, repeated authors, non-English posts, and unrelated uses. Likes and reposts reflect accumulated engagement, not buying intention. A single pull does not establish a trend over time.

AI prompt record

Exchange 1: The student requested help adapting a Bluesky/RStudio workflow to Rhode skincare and pasted the assignment requiring cleaning, text and sentiment analysis, Plotly, verification, reflection, and a second AI exchange. This is a summary; screenshot the original chat request and the actual response.

Exchange 2 — proposed improved prompt, not yet used:

Review the Rhode R Markdown code you gave me. Explain exactly how it avoids treating posts with no sentiment-word matches as neutral, how I can verify one post’s score by hand, and how I should critique negation and unrelated uses of Rhode. Identify any remaining limitations. Keep your explanation simple and suggest a specific improvement without inventing data or findings.

Send that prompt to the assistant, read the response, then record what actually changed here: [second prompt used, response summary, revision accepted or rejected, and why]. Screenshot both exchanges for the discussion. Proposed prompts do not count as completed exchanges.

References and tool disclosure

Silge, J., & Robinson, D. (2017). Text mining with R: A tidy approach. O’Reilly Media. Chapter 2: https://www.tidytextmining.com/sentiment.

Plotly. (n.d.). Getting started with Plotly in R. https://plotly.com/r/getting-started/.

Gruber, J., & Guinaudeau, B. (n.d.). atrrr: Basic usage. https://jbgruber.github.io/atrrr/articles/Basic_Usage.html.

ChatGPT assisted with code and a reflection scaffold. R performs the calculations; the student reviews relevance and labels, checks arithmetic, critiques the results, and writes the final reflection. Update this disclosure to match the work done.

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] tidytext_0.4.3 stringr_1.6.0  tidyr_1.3.2    dplyr_1.2.1   
## 
## loaded via a namespace (and not attached):
##  [1] Matrix_1.7-6        gtable_0.3.6        jsonlite_2.0.0     
##  [4] janeaustenr_1.0.0   compiler_4.6.2      tidyselect_1.2.1   
##  [7] Rcpp_1.1.2          jquerylib_0.1.4     scales_1.4.0       
## [10] yaml_2.3.12         fastmap_1.2.0       lattice_0.23-1     
## [13] ggplot2_4.0.4       R6_2.6.1            SnowballC_0.7.1    
## [16] generics_0.1.4      knitr_1.52          htmlwidgets_1.6.4  
## [19] tibble_3.3.1        RColorBrewer_1.1-3  bslib_0.12.0       
## [22] pillar_1.11.1       tokenizers_0.3.0    rlang_1.3.0        
## [25] cachem_1.1.0        stringi_1.8.9       xfun_0.62          
## [28] S7_0.2.2            sass_0.4.10         otel_0.3.0         
## [31] viridisLite_0.4.3   plotly_4.12.1       cli_3.6.6          
## [34] withr_3.0.3         magrittr_2.0.5      crosstalk_1.2.2    
## [37] digest_0.6.39       grid_4.6.2          rstudioapi_0.19.0  
## [40] lifecycle_1.0.5     vctrs_0.7.3         data.table_1.18.6.1
## [43] evaluate_1.0.5      glue_1.8.1          farver_2.1.2       
## [46] httr_1.4.9          rmarkdown_2.32      purrr_1.2.2        
## [49] tools_4.6.2         pkgconfig_2.0.3     htmltools_0.5.9