Using Sentiment Analysis to Investigate Peer Feedback by Native and Non-Native English Speakers

2025-07-23

AI Summary

This study investigates disparities in emotional expression and reception of peer feedback between native English-speaking (NES) and non-native English-speaking (NNES) learners in U.S.-based online computer science courses. Method: We applied fine-grained sentiment analysis using the Twitter-roBERTa model and conducted multivariate regression integrating quantitative feedback scores with demographic variables—language background, gender, and age. Contribution/Results: NNES students authored significantly more positively valenced feedback, yet received markedly fewer positive emotional responses; NES peers rated such feedback lower overall. Significant interaction effects emerged among language background, gender, and age. This work provides the first empirical evidence of systemic sentiment asymmetry tied to linguistic identity in online programming education, revealing a critical equity gap in peer feedback dynamics. Findings offer actionable insights for designing culturally responsive, linguistically inclusive feedback mechanisms and fairness-aware interventions in multilingual learning environments.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Application Domains: Humanities & Computational Social Science
• Computer Vision: Language and Vision

Application Category

• Social Networks and Social Media: Fairness and bias in social network and social media analysis
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

Graduate-level CS programs in the U.S. increasingly enroll international students, with 60.2 percent of master's degrees in 2023 awarded to non-U.S. students. Many of these students take online courses, where peer feedback is used to engage students and improve pedagogy in a scalable manner. Since these courses are conducted in English, many students study in a language other than their first. This paper examines how native versus non-native English speaker status affects three metrics of peer feedback experience in online U.S.-based computing courses. Using the Twitter-roBERTa-based model, we analyze the sentiment of peer reviews written by and to a random sample of 500 students. We then relate sentiment scores and peer feedback ratings to students' language background. Results show that native English speakers rate feedback less favorably, while non-native speakers write more positively but receive less positive sentiment in return. When controlling for sex and age, significant interactions emerge, suggesting that language background plays a modest but complex role in shaping peer feedback experiences.

Problem

• Examines how native vs non-native English speakers affect peer feedback
• Analyzes sentiment of peer reviews using Twitter-roBERTa model
• Investigates language background's role in feedback sentiment and ratings

Innovation

• Sentiment analysis with Twitter-roBERTa model
• Comparing native and non-native feedback sentiment
• Controlling for sex and age variables