Educator Attention: How computational tools can systematically identify the distribution of a key resource for students

2025-02-27

AI Summary

This study systematically quantifies structural biases in teachers’ attention allocation during virtual small-group instruction—a previously unexamined problem. Leveraging 1 million teacher utterances paired with student demographic and academic performance data, we integrate referential discourse analysis, instructional intent classification, multilevel regression, and interaction-effect modeling. Our analysis yields three key contributions: (1) In mixed-gender groups, low-achieving girls receive the least attention, whereas low-achieving boys receive the most—revealing a gender–achievement intersectional neglect; (2) Black students receive significantly heightened attention only when paired with same-race peers; (3) High-achieving English learners receive markedly greater attention than their low-achieving peers. Moving beyond traditional small-sample observational studies, this work establishes a scalable computational paradigm and empirical benchmark for investigating implicit inequities in educational resource distribution.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Ethics, Bias, and Fairness
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Educator attention is critical for student success, yet how educators distribute their attention across students remains poorly understood due to data and methodological constraints. This study presents the first large-scale computational analysis of educator attention patterns, leveraging over 1 million educator utterances from virtual group tutoring sessions linked to detailed student demographic and academic achievement data. Using natural language processing techniques, we systematically examine the recipient and nature of educator attention. Our findings reveal that educators often provide more attention to lower-achieving students. However, disparities emerge across demographic lines, particularly by gender. Girls tend to receive less attention when paired with boys, even when they are the lower achieving student in the group. Lower-achieving female students in mixed-gender pairs receive significantly less attention than their higher-achieving male peers, while lower-achieving male students receive significantly and substantially more attention than their higher-achieving female peers. We also find some differences by race and English learner (EL) status, with low-achieving Black students receiving additional attention only when paired with another Black student but not when paired with a non-Black peer. In contrast, higher-achieving EL students receive disproportionately more attention than their lower-achieving EL peers. This work highlights how large-scale interaction data and computational methods can uncover subtle but meaningful disparities in teaching practices, providing empirical insights to inform more equitable and effective educational strategies.

Problem

• Analyze educator attention distribution in virtual tutoring.
• Identify disparities in attention based on student demographics.
• Use NLP to study attention patterns in large-scale data.

Innovation

• Natural Language Processing
• Large-scale Interaction Data
• Computational Analysis