Od kamnitega do spletnega portala: samodejno zaznavanje sprememb v rabi besed
Bibliographic record
Abstract
This paper presents a system for detecting changes in Slovene word usage, enabling the automatic identification of semantic and other shifts across different time periods. We first introduce the system’s technical design and requirements, the methodology for detecting changes, and the graphical user interface, which ensures a user-friendly experience. We then demonstrate how the system can be implemented on the reference corpus of Slovene, Gigafida 2.0, and used to search for and analyse changes in word usage across various time periods. The system’s results are evaluated through a cognitive-linguistic and lexical analysis of the most changed adjectives and nouns, where we examine and categorise word meanings and usages within the detected clusters based on their semantic motivation and representation in dictionaries. Finally, we apply the system to a case study of migration representation in different time periods with manually defined boundaries, which have significantly influenced attitudes toward migration and migrants in Slovenia, thereby testing its applicability for sociolinguistic research. From a linguistic perspective, we observe that the system distinguishes between semantic, syntactic, and other contextually distinct usages, demonstrating its ability to detect both short-term and long-term changes. Furthermore, we observe that the system clearly illustrates the impact of external factors on language and discourse in specific time periods, making it a valuable tool for sociolinguistic analysis.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.004 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.005 | 0.005 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.004 |
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".