Using Analytics on Social Media Posts to Gauge the Impact on User Engagement: A Case Study Analysis on #FoundItOnAmazon
Bibliographic record
Abstract
The purpose of this research is to use analytics on social media content to study consumer engagement. Companies and brands may benefit indirectly when trends on social media take on positive hashtags. The hashtags provide exposure to the brand as they are shared and, in some cases, generate engagement as consumers join the trend and/or respond to posts relating to the trend. Certain factors may improve engagement, which in effect extends the trend and leads to more brand exposure. These may include # of followers, time of posting, and post format. While our data do not speak directly to sponsoring social influencers, it can be informational in terms of guiding companies to work with such influencers or content creators to increase or extend engagement. More specifically, we analyze the effect of creator, content, and context-related factors affecting user engagement. The dataset has a total of 1,000 social media posts and 273,586 likes and 6,306 likes and comments on Instagram, YouTube, and Twitter. Of the 1,000 posts, we ran a regression on 295 Instagram posts. The results reveal that the # of followers dominated the "overall engagement". Hence, a second regression using "user engagement rate" as the dependent variable was run. The rationale behind using user engagement rate in the second regression is to understand the relative impact of other factors and eliminate the dominance of followers from the equation. The results for the final regression revealed that posted format and time of posting have a significant impact on user engagement rate.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".