Reproduce “Characterising Topic Familiarity and Query Specificity Using Eye-Tracking Data” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jiaman He, Zikang Leng, Dana McKay, Johanne R. Trippas, Damiano Spina
This research demonstrates that eye-tracking data collected during the pre-search phase of information retrieval can be used to automatically detect a user's topic familiarity and query specificity. Machine learning models achieved macro F1 scores up to 71.25% for topic familiarity and 60.54% for query specificity, with pupillary responses proving more informative than gaze movements.
Key insights
- Pupillary response features are generally more informative than gaze velocity features for predicting both topic familiarity and query specificity, aligning with their association with cognitive workload.
- Eye-tracking data can infer users' cognitive states (topic familiarity and query specificity) in real-time during the pre-search phase, without requiring explicit feedback.
- The ability to automatically assess these user characteristics offers potential for developing adaptive information retrieval systems that personalize search experiences based on user knowledge and information needs.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.