News recommendation based on opinion mining: an approach to assist the automatic classification of controversies
Bibliographic record
Abstract
Web-based reading services such as Google News and Yahoo! News have become increasingly popular with the growth of news information services on the Internet. To help users cope with the information overload on these search engines, recommender systems and personalization techniques are proposed. Acting as a kind of algorithmic curators, these services help users find content that matches their personal interests and tastes using their browser history and past behavior as a basis for recommendations. However, several researchers have criticized recommender systems, arguing that overspecialized recommendations lead to the creation of isolated communities (Van Alstyne and Brynjolfsson, 2005), the emergence of extremist opinions (Mutz and Young, 2011) and the overall degradation of the public sphere (Parisier, 2011; Sustein, 2007). The aim of our research to propose an opinion mining method to classify divergent opinions from a controversial debate on the press. We want to contribute to a solution to diversify recommendations in web-based reading services. Our classification approach advocates for the study of linguistics aspects of corpus prior to the classification task, to orientate the selection of the textual criteria which may contribute to the application performance. This approach explores theoretical concepts from Interpretative Semantics formulated by Francois Rastier and uses textometric techniques for the corpora analyses. Our corpora are composed by opinionated articles about the 2012 student protest in Quebec against the raise of the tuition fees announced by the Liberal Premier Jean Charest.
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 | 0.004 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.009 | 0.006 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.003 |
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".