IdeaDistiller - AI-support for Idea Synthesis in Concept Mapping: Algorithm Development and Validation (Preprint)
Bibliographic record
Abstract
Background: Concept mapping (CM) is a widely used mixed method research approach for structuring and visualizing complex ideas across various fields, such as the health sciences. A critical bottleneck in the CM process is the idea synthesis phase, which remains labor-intensive, subjective, and consequently challenging to scale for large datasets. Objective: In this study, we propose IdeaDistiller, a semiautomated solution based on semantic clustering to optimize the idea synthesis step while maintaining methodological rigor through a human-in-the-loop approach. Methods: Using 9 health care-related datasets in English and Swedish, we systematically evaluated different embedding models, dimensionality reduction techniques, and clustering algorithms to identify robust and reproducible parameter settings for the proposed approach. IdeaDistiller clusters participant-generated ideas based on semantic similarity to identify similar ideas with different wording, suggests representative and unique ideas per cluster, and provides coherence scores and sorted outputs to aid manual validation. Results: Our findings suggest that IdeaDistiller may substantially reduce the manual effort involved in idea synthesis while preserving quality and transparency. However, human expertise remains indispensable for validating and refining cluster outputs. Conclusions: Integrating semiautomated methods into the CM workflow offers significant potential for improving the efficiency, scalability, and rigor of the CM process. Building on our work will enable the exploration of larger multilingual datasets and integration into future CM studies.
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 | 0.030 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.003 | 0.005 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.032 | 0.009 |
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".