Should We Feed the Trolls? Using Marketer-Generated Content to Explain Average Toxicity and Product Usage
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Marketers and researchers recognize the importance and impact on consumer behavior of marketer-generated content (MGC) in social media channels. In this study, the authors present a method to classify MGC using a combination of unsupervised and supervised machine learning. They gather a large data set of posts from Facebook, Instagram, and Twitter and use a time-series model (panel-data vector autoregression) to demonstrate how MGC can be used to explain average toxicity on the part of users. They contribute to the field by examining what types of MGC lead to toxic comments and how these toxic comments impact product usage. The authors find that MGC that demonstrates the quality of products and MGC that is aimed at creating a sense of belonging to a group are more likely to increase average toxicity. Furthermore, the authors find that higher average toxicity in social media communities leads to an increase in usage of the focal product. Finally, the results contribute to the literature by providing insights on the impact of MGC on product usage.
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.022 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 it