Bibliographic record
Abstract
Purpose – The purpose of this paper is to present an empirical comparison between the recommendations generated by a citation-based recommender for research articles in a digital library with those produced by a user-based recommender (ExLibris “bX”). Design/methodology/approach – For these computer experiments 9,453 articles were randomly selected from among 6.6 M articles in a digital library as starting points for generating recommendations. The same seed articles were used to generate recommendations in both recommender systems and the resulting recommendations were compared according to the “semantic distance” between the seed articles and the recommended ones, the coverage of the recommendations and the spread in publication dates between the seed and the resulting recommendations. Findings – Out of the 9,453 test runs, the recommendation coverage was 30 per cent for the user-based recommender vs 24 per cent for the citation-based one. Only 12 per cent of seed articles produced recommendations with both recommenders and none of the recommended articles were the same. Both recommenders yielded recommendations with about the same semantic distance between the seed article and the recommended articles. The average differences between the publication dates of the recommended articles and the seed articles is dramatically greater for the citation-based recommender (+7.6 years) compared with the forward-looking user-based recommender. Originality/value – This paper reports on the only known empirical comparison between the Ex Librix “bX” recommendation system and a citation-based collaborative recommendation system. It extends prior preliminary findings with a larger data set and with an analysis of the publication dates of recommendations for each system.
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 | 0.013 | 0.152 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.026 | 0.030 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".