Research purpose and collection status

The keyword Kylie Cosmetics matters because posts can reveal product interests, customer experiences, and content that attracts attention. These are search samples, not a representative survey of all customers or a complete count of Bluesky activity.

Comparison pending: add the actual Day 3 pull as data/Scrape2.csv and knit again.

Volume and time span

scrape posts collected_at_utc earliest_post_utc latest_post_utc unique_authors mean_likes_plus_reposts median_likes_plus_reposts top_author_share_pct minimum_100_met
Scrape1 100 2026-11-19T23:13:22Z 2026-06-06 09:45:01 2026-11-17 15:17:19 69 3.49 0 5 TRUE

A capped sample of 100 posts on each day will have equal volume by design. This does not show that overall conversation volume was unchanged. Publication time spans may differ between pulls. Search results can overlap, and older posts have had more time to accumulate engagement.

Engagement, accounts, and manual analysis

Engagement is likes + reposts; replies are retained separately in the datasets. Ties in the top five are resolved by URI. A frequent account is not automatically an influential account.

On the first knit, a random sample of up to 20 posts per pull is saved in the manual folder. Open each Scrape1_labels.csv / Scrape2_labels.csv in Excel. Fill in sentiment with positive, negative, or neutral, judging the attitude toward Kylie Cosmetics. Use neutral for informational posts or no clear opinion; use notes for ambiguity. Read linked context when necessary. Fill theme with one main topic per post, using consistent names across both pulls. Choose 2–3 recurring topics after reading, rather than forcing posts into invented themes. Save as CSV, close Excel, and knit again. Blank sentiment is unlabeled, not neutral. The sample is retained across knits so your labels are preserved.

Scrape1

Top five posts

uri author_handle text like_count repost_count engagement
at://did:plc:qobvnkudcv3zlaklxxjduqoi/app.bsky.feed.post/3mpbkwqkchw2p motherjones.com Kylie Jenner’s willingness to cozy up to terrible people appears to run in the family. But her ability to sell things is shakier: Kylie Cosmetics is no longer relevant, and Jenner’s clothing line has yet to make an impact since launching in 2023. As for Meta, is there a less cool company? 169 28 197
at://did:plc:qobvnkudcv3zlaklxxjduqoi/app.bsky.feed.post/3mpgq2nqkh62y motherjones.com Kylie Jenner’s willingness to cozy up to terrible people appears to run in the family. But her ability to sell things is shakier these days: Kylie Cosmetics is no longer relevant, and her clothing line has yet to make an impact since launching in 2023. As for Meta, is there a less cool company? 87 13 100
at://did:plc:gsytyhzjivwhl7whwbzmtoxt/app.bsky.feed.post/3n2jdm2ldnq2n consumerreports.org Is there lead in your lipstick? We tested 24 popular products and found that most had very low levels, though results varied widely. “Clean” labels and price were not reliable indicators. See the full results and tips for minimizing exposure below. 11 7 18
at://did:plc:se7sqhgg6jbshe6myfegowcm/app.bsky.feed.post/3mryufalijc25 theandblock.bsky.social ​🌎 Große internationale Brands ​Gymshark (Fitness-Bekleidung) ​Kylie Cosmetics / KKW Beauty (Kylie Jenner / Kim Kardashian) ​Allbirds (Nachhaltige Schuhe) ​Red Bull (Merchandise & Fan-Stores) ​Bombas (Socken & Bekleidung) Vielleicht haben ja ein paar Leute hier Lust die Emailadressen? 4/4 7 1 8
at://did:plc:5hmkw7azxuuiemi4nh6cvyhk/app.bsky.feed.post/3mzgtzltrgd2y lexlanham.bsky.social kylie applies to register her 8 y/o daughter’s name, STORMI JENNER, as a trademark for a range of goods & services incl. skin care, lotions, cleansers, cosmetics, fragrances, hair care & nail polish. neither kylie nor stormi has announced plans to launch a line under that mark 5 1 6

Your interpretation: read these five posts and describe what they share (topic, format, tone, links, or author). Counts alone cannot establish why they performed well.

Who is talking?

author_handle posts share_pct
beauty-glowmuse.bsky.social 5 5
headlinesociety.bsky.social 5 5
newsletter-tf.bsky.social 5 5
durumagazine.com 3 3
entertainmentnow.bsky.social 3 3
instyle.com 3 3
stupiddope.bsky.social 3 3
albarjeel-news.bsky.social 2 2
britbrif.bsky.social 2 2
celebritypictures.bsky.social 2 2

Manual sentiment

sentiment posts percent_of_labeled labeled sample_size
positive 0 NA 0 20
negative 0 NA 0 20
neutral 0 NA 0 20

Labeled 0 of 20 sampled posts. Incomplete: label at least 10 posts, preferably all 20.

Percentages describe labeled sample posts only. Each post has equal weight; they are not percentages of customers.

Themes in the manually reviewed sample

Pending manual theme labels.

Sentiment among manually labeled sample posts; incomplete samples are marked.

Sentiment among manually labeled sample posts; incomplete samples are marked.

Comparison between the two pulls

A second collection is required. One dataset split into groups cannot demonstrate a change between collection days.

Excel evidence and submission writing

Open results/Bluesky_Analysis.xlsx in Excel. It contains the datasets, volume, top posts, accounts, manual labels, sentiment, themes, and available comparisons. Screenshot a relevant Excel table or create and screenshot a chart.

For an Excel PivotTable, open a labels sheet, select the table, and choose Insert → PivotTable. Put sentiment in Rows and uri in Values as Count; exclude blanks, then choose Show Values As → % of Grand Total. Screenshot the result. Your assignment asks for Excel evidence even though this report automates calculations.

Initial post (write 200–250 words using your actual results): Explain your keyword and project connection; give the post count, dates and time span; describe 2–3 supported findings using the top posts, sentiment and account tables; identify 2–3 recurring themes; state a limitation and one marketing question. Include an external reference and your Excel screenshot. Do not submit this scaffold as findings.

Day 3 update (complete these four sentences): “On [actual date], I collected [actual n] posts using the same keyword. Compared with the first pull, [numeric change], while [supported similarity] remained similar. [Theme/top-post evidence] suggests [cautious interpretation], although [sample limitation]. I recommend our team [specific action connected to this evidence].”

Peer replies: Read two classmates’ posts and write 75–100 words for each. Address a specific finding, then suggest an alternative interpretation, a sample or keyword limitation, or a follow-up analysis. Their posts are needed to write accurate personalized replies.

Reflection: Are the people posting here likely to match your brand’s target customers? Do a few days show a meaningful shift or ordinary variation? What did human judgment contribute when interpreting sentiment, sarcasm, and themes? If instructed, post your reflection on your own account with #MKTG4000fiasco.

External reference and disclosure

Clark-Keane, C. (n.d.). A marketer’s guide to Bluesky (& is it worth it?) WordStream. https://www.wordstream.com/blog/bluesky-for-marketing

The guide recommends experimentation to find a brand’s audience and voice. Use your observed themes and high-engagement posts to propose a small content experiment. This is a marketing interpretation, not proof that the brand’s customers are represented in the sample. The reference supplies context; it does not verify the results in this report.

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

Tool disclosure: ChatGPT helped prepare the R collection and reporting code. R computed descriptive summaries; the student manually labeled sentiment and interpreted themes. Change this disclosure if your actual workflow differs.