Online mouse tracking as a measure of attention in videos, using a mouse-contingent bi-resolution display
Bibliographic record
Abstract
Data on human visual attention is increasingly collected online, but there are limited tools available to study attention to video stimuli in online experiments. Webcam-based eye tracking is improving, but it faces issues with precision and attrition that prevent its adoption by many researchers. Here I detail an alternative mouse-based paradigm that can be used to measure attention to videos online. This method uses a blurred display and a high-resolution window centered on the user’s computer mouse location. As the user moves their mouse to view different screen content, their mouse movements are recorded, providing an approximation of eye movements and the attended screen location. To validate this Mouse-Contingent Bi-Resolution Display (MCBRD) paradigm, mouse movements collected from online participants watching twenty-seven videos were compared to eye movements from the DIEM dataset. Display settings of window size and blur level were manipulated to identify the settings that resulted in mouse movements most similar to eye movements. This validation study found differences in speed between mouse and eye movements, but similarities in attended regions of interest, especially when the MCBRD screen was blurred with the highest tested Gaussian blur sigma of 0.45 degrees of visual angle. These results suggest that the MCBRD paradigm can be used to measure what regions viewers find salient, interesting, or visually informative in online videos.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
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".