Text mining methods for innovation studies: limits and future perspectives
Bibliographic record
Abstract
This study offers alternative and promising approaches to word count methods, largely used to develop innovation indicators from unstructured text. We propose a method based on Information Retrieval (IR) and word-embedding models to tackle the semantic ellipsis, one of the main issues of word count methods. We test our IR model by investigating the concept of collaboration and comparing our approach with a baseline corresponding to the keyword search. To ensure the best performances, we use several ways to represent queries and documents in a vector space and three pre-trained word-embedding models. The results prove that our approach can alleviate the semantic ellipsis problem. Indeed, the IR model developed outperforms the classical keyword search in terms of F1-score and Recall. Moreover, we create a combined method that achieves the highest F1-score. These preliminary results can facilitate the creation of reliable innovation indicators from unstructured textual data substituting or complementing survey-based questionnaires.
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 | 0.037 | 0.077 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.007 | 0.010 |
| Science and technology studies | 0.001 | 0.005 |
| Scholarly communication | 0.010 | 0.020 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.004 | 0.004 |
| Insufficient payload (model declined to judge) | 0.008 | 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".