Exploiting Class Bias for Discovery of Topical Experts in Social Media
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
Discovering contexts of user's expertise can be a challenging task, especially if there is no explicit attribution provided. With more professionals adopting social networks as a mean of communicating with their colleagues and broadcasting updates on the area of their competence, it is crucial to detect such individuals automatically. This would not only allow for better follower recommendation, but would also help to mine valuable insights and emerging signals in different communities. We posit that topical groups have their unique semantic signatures. Hence, we can treat identification of expert's topical attribution as a binary classification task, exploiting the class bias to generate training sample without any manual labor. In thiswork, we present profile-and behavior-based models to explore experts topicality. While the former focuses on the static profile of user activity, the latter takes into account consistency and dynamics of a topic in user feed. We also propose a naive baseline tailored to a domain used in evaluation. All models are assessed on a case study of Twitter investment community.
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 | 0.000 | 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 | 0.000 | 0.000 |
| 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