La modélisation de l'analyse documentaire: à la sémiotique, de la psychologie cognitive et de l'intelligence artificielle
Bibliographic record
Abstract
La sémiotique textuelle et la psychologie cognitive sont mises à contribution pour modéliser différentes opérations d'analyse documentaire. On expose les éléments du modèle théorique et la complémentarité des approches. L'attribution de propriétés relevant de systèmes sémiotiques divers sur les textes primaires et secondaires permet de retrouver les unités et certaines des caractéristiques privilégiées de façon générale ou par chaque individu. Les enquêtes cognitives auprès des experts corroborent ou complétent l'analyse des corpus. Quelques exemples de résultats obtenus par l'analyse statistico-linguistique lors de deux expérimentations illustrent l'utilité de la méthodologie, notamment pour la conception de systèmes experts d'aide à la lecture.Textual semiotics and cognitive psychology are advocated to model several types of documentary analysis. A theoretical model is proposed which combines elements from the two disciplines. Thanks to the addition of values of properties pertaining to different semiotic systems to the primary and secondary texts, one can retrieve the units and the characteristics valued by a group of indexers or byone individual. The cognitive studies of the experts confirm or complete the textual analysis. Examples from the findings obtained by the statistico-linguistic analysis of two corpora illustrate the usefulness of the methodology, especially for the conception of expert systems to assist whatever kind of reading.
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 | 0.005 | 0.015 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.003 | 0.003 |
| Science and technology studies | 0.001 | 0.008 |
| Scholarly communication | 0.011 | 0.009 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.003 | 0.003 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
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".