What’s on Their For You Page? A Large-Scale Computational Approach to Analyzing Adolescents’ TikTok Archives Through Hashtag Topic Modeling
Bibliographic record
Abstract
Short-form video platforms like TikTok play a central role in adolescents’ lives, yet little is known about the actual content they engage with. This study presents a large-scale, computational approach to analyze adolescents’ TikTok feeds using hashtag-based topic modeling applied to user-donated archives from 102 Dutch adolescents (ages 15–19). Using BERTopic, we identified 304 coherent topics, organized them into 32 higher-order content categories, and validated both through a structured human validation study. Analyses reveal that adolescents’ feeds are dominated by entertainment and leisure content, with ‘Media productions,’ ‘Sports,’ ‘Style and appearance,’ ‘Hobbies,’ and ‘Gaming’ as the most prevalent categories. At the same time, there is marked individual variation: niche areas such as K-pop, anime, and specific fandoms are central to some users’ feeds. Latent profile analysis identified six distinct, gendered content-consumption profiles. Together, the findings shed light on adolescents’ TikTok exposure, revealing predominantly benign but highly personalized media diets in which appearance-focused content stands out as a potential risk domain. In all, our approach offers a scalable, efficient way to map short-form video content. Linking these maps to individual users’ media diets opens new possibilities for examining how different content patterns relate to user experiences and outcomes.
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 | 0.001 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".