Un outil d'evaluation neurocognitive des interactions humain-machine
Bibliographic record
Abstract
More and more researches on Human-Computer Interactions (HCI) are trying to perform detailed analyses of interaction to determine its influence on users’ behaviours. A particular emphasis is now put on emotional reactions during the interaction, whether it’s from the perspective of user experience evaluation or user performance. Standard qualitative approaches are limited because they are based on observations and interviews after the interaction, therefore limiting the precision of the diagnosis. User experience and emotional reactions being, by nature, highly dynamic and contextualized, evaluation approaches should be the same to accurately diagnose the quality of interaction. This thesis presents an evaluation approach, both dynamic and quantitative, which allows contextualising users’ emotional reactions to help identify their causes during the interaction with a system. To this end, our work focuses on three main axes: 1) automatic task recognition using machine learning modeling of eye tracking and interaction data; 2) automatic inference of psychological constructs (emotional activation, emotional valence, and cognitive load) through physiological signals analysis; and 3) diagnosis of users’ reactions during interaction based on the coupling of the two previous operations. The ideas and development of our approach are illustrated using two experimental contexts: e-commerce and simulation-based training. We also present the tool we implemented in order to allow HCI professionals (e.g.: user experience expert, training supervisor, or game designer) to use our evaluation approach to assess interaction. This tool is designed to facilitate the triangulation of measuring instruments and the integration with more classical Human-Computer Interaction methods (ex.: surveys and observation coding).
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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; both teacher heads agree on what is shown here.
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".