TikTok vs. the Fourth Estate: Engagement With News on TikTok
Bibliographic record
Abstract
In addition to content from accounts the user follows, TikTok frequently emphasizes content with similar subject matter to videos the user has previously liked. As long as a user has indicated an interest in the topic (most likely by engaging with a related video), they may see a TikTok about it despite not following anyone who has ever interacted with it. Consequently, political networks and communities do not always emerge around prominent figures like politicians or professional content creators, but rather manifest as ephemeral trending topics. Our methodological approach to studying engagement with politics on TikTok therefore uses topic modeling to identify how and when TikTok users respond to news coverage about prominent current events. Specifically, we examine a large dataset of news articles, TikTok videos, and TikTok comments to uncover how TikTok discussion of the Russian-Ukrainian war temporally differs from coverage in mainstream news outlets. By examining points in time where the proportion of TikTok content about a specific topic within the war mirrors its discussion in the news – and more importantly, where it diverges – we are able to see how TikTok users include news events in their engagement with political issues. We find that the majority of TikTok videos about the Russian-Ukrainian war rarely feature prominent news stories, but rather focus on the users’ personal experiences and perspectives. However, TikTok comments are more strongly engaged with specific events and ‘hot-button’ issues related to the war. The application of our methodology allows us to observe how major news events inform the creation and discussion of content on TikTok, the discrepancy between video descriptions/hashtags and video subject matter, and the importance of the comment section as a site for political conversation.
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 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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".