# Getting the Most from Eye-Tracking: User-Interaction Based Reading Region Estimation Dataset and Models

arXiv: https://arxiv.org/abs/2306.07455 · HTML: https://mlsanity.com/paper/2306.07455/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 12 Jun 2023.

## Builds on (most cited first, 6 of 6)

- [On Estimating Recommendation Evaluation Metrics under Sampling](https://mlsanity.com/paper/2103.01474/) (2021)
- [HierCat: Hierarchical Query Categorization from Weakly Supervised Data at Facebook Marketplace](https://mlsanity.com/paper/2302.10527/) (2023)
- [Que2Engage: Embedding-based Retrieval for Relevant and Engaging Products at Facebook Marketplace](https://mlsanity.com/paper/2302.11052/) (2023)
- [Intermittent Learning: On-Device Machine Learning on Intermittently Powered System](https://mlsanity.com/paper/1904.09644/) (2019)
- [Multi-Objective Personalization in Multi-Stakeholder Organizational Bulk E-mail: A Field Experiment](https://mlsanity.com/paper/2302.11156/) (2023)
- [The Informational Role of Online Recommendations: Evidence from a Field Experiment](https://mlsanity.com/paper/2211.14219/) (2022)

## Built on by (most cited first, 2 of 2)

- [Less Can Be More: Exploring Population Rating Dispositions with Partitioned Models in Recommender Systems](https://mlsanity.com/paper/2306.11279/) (2023)
- [Organizational Bulk Email Systems: Their Role and Performance in Remote Work](https://mlsanity.com/paper/2308.05085/) (2023)

## Abstract (arXiv)

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.