Getting the Most from Eye-Tracking: User-Interaction Based Reading Region Estimation Dataset and Models
This work addresses the problem of understanding user interests for content platforms, enabling personalization and recommendations, but it is incremental as it builds on existing interaction-based methods.
The paper tackled predicting per-region reading time in digital newsletters using easy-to-collect browser tracking data instead of expensive eye-tracking, achieving a 27% error rate with a two-tower neural network compared to 46% for baselines.
A single digital newsletter usually contains many messages (regions). Users' reading time spent on, and read level (skip/skim/read-in-detail) of each message is important for platforms to understand their users' interests, personalize their contents, and make recommendations. Based on accurate but expensive-to-collect eyetracker-recorded data, we built models that predict per-region reading time based on easy-to-collect Javascript browser tracking data. With eye-tracking, we collected 200k ground-truth datapoints on participants reading news on browsers. Then we trained machine learning and deep learning models to predict message-level reading time based on user interactions like mouse position, scrolling, and clicking. We reached 27\% percentage error in reading time estimation with a two-tower neural network based on user interactions only, against the eye-tracking ground truth data, while the heuristic baselines have around 46\% percentage error. We also discovered the benefits of replacing per-session models with per-timestamp models, and adding user pattern features. We concluded with suggestions on developing message-level reading estimation techniques based on available data.