Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction
This empirical study analyzes 26,399 education-focused user reviews of ChatGPT from the Google Play Store to investigate factors shaping perceptions of educational usability. Using quantitative methods including feature engineering, sentiment analysis, and ordinary least-squares regression, we exami...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | en |
| Published: |
John Wiley and Sons
2026
|
| Subjects: | |
| Online Access: | http://psasir.upm.edu.my/id/eprint/123777/1/123777.pdf http://psasir.upm.edu.my/id/eprint/123777/ https://onlinelibrary.wiley.com/doi/10.1155/ahci/3363262 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1860590898468880384 |
|---|---|
| author | Sun, Peng Haque, Md Ziaul Li, Le Hossain, Md Shamim |
| author_facet | Sun, Peng Haque, Md Ziaul Li, Le Hossain, Md Shamim |
| author_sort | Sun, Peng |
| building | UPM Library |
| collection | Institutional Repository |
| content_provider | Universiti Putra Malaysia |
| content_source | UPM Institutional Repository |
| continent | Asia |
| country | Malaysia |
| description | This empirical study analyzes 26,399 education-focused user reviews of ChatGPT from the Google Play Store to investigate factors shaping perceptions of educational usability. Using quantitative methods including feature engineering, sentiment analysis, and ordinary least-squares regression, we examine how emotional sentiment, content quality, and review scores influence usability perceptions. Results reveal a counterintuitive emotional pattern: while surprise and anticipation enhance perceived usability, joy and disgust are associated with lower usability perceptions. Overall sentiment emerges as the strongest predictor of usability (coefficient = 0.8565, p ≤ 0.001), with content quality also exerting a significant positive effect (coefficient = 0.0334, p ≤ 0.001). In contrast, review scores show a small but significant negative relationship with usability (coefficient = −0.0210, p ≤ 0.001). Trust exhibits a slight negative effect, whereas fear, anger, and sadness show no significant associations. These findings highlight the critical role of emotional factors in educational AI usability, suggesting that developers should prioritize both high-quality content and positive emotional engagement. This research contributes to HCI and educational technology by providing a replicable framework for analyzing user perceptions of AI tools while emphasizing the importance of affective dimensions in technology adoption. |
| format | Article |
| id | my.upm.eprints-123777 |
| institution | Universiti Putra Malaysia |
| language | en |
| publishDate | 2026 |
| publisher | John Wiley and Sons |
| record_format | eprints |
| spelling | my.upm.eprints-1237772026-03-18T07:26:02Z http://psasir.upm.edu.my/id/eprint/123777/ Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction Sun, Peng Haque, Md Ziaul Li, Le Hossain, Md Shamim This empirical study analyzes 26,399 education-focused user reviews of ChatGPT from the Google Play Store to investigate factors shaping perceptions of educational usability. Using quantitative methods including feature engineering, sentiment analysis, and ordinary least-squares regression, we examine how emotional sentiment, content quality, and review scores influence usability perceptions. Results reveal a counterintuitive emotional pattern: while surprise and anticipation enhance perceived usability, joy and disgust are associated with lower usability perceptions. Overall sentiment emerges as the strongest predictor of usability (coefficient = 0.8565, p ≤ 0.001), with content quality also exerting a significant positive effect (coefficient = 0.0334, p ≤ 0.001). In contrast, review scores show a small but significant negative relationship with usability (coefficient = −0.0210, p ≤ 0.001). Trust exhibits a slight negative effect, whereas fear, anger, and sadness show no significant associations. These findings highlight the critical role of emotional factors in educational AI usability, suggesting that developers should prioritize both high-quality content and positive emotional engagement. This research contributes to HCI and educational technology by providing a replicable framework for analyzing user perceptions of AI tools while emphasizing the importance of affective dimensions in technology adoption. John Wiley and Sons 2026-03-08 Article PeerReviewed text en cc_by_4 http://psasir.upm.edu.my/id/eprint/123777/1/123777.pdf Sun, Peng and Haque, Md Ziaul and Li, Le and Hossain, Md Shamim (2026) Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction. Advances in Human-Computer Interaction, 2026 (1). art. no. 3363262. pp. 1-17. ISSN 1687-5893; eISSN: 1687-5907 https://onlinelibrary.wiley.com/doi/10.1155/ahci/3363262 Human-Computer Interaction 10.1155/ahci/3363262 |
| spellingShingle | Human-Computer Interaction Sun, Peng Haque, Md Ziaul Li, Le Hossain, Md Shamim Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title | Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title_full | Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title_fullStr | Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title_full_unstemmed | Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title_short | Exploring emotional and content influences on ChatGPT’s educational usability within the field of Human–Computer Interaction |
| title_sort | exploring emotional and content influences on chatgpt’s educational usability within the field of human–computer interaction |
| topic | Human-Computer Interaction |
| url | http://psasir.upm.edu.my/id/eprint/123777/1/123777.pdf http://psasir.upm.edu.my/id/eprint/123777/ https://onlinelibrary.wiley.com/doi/10.1155/ahci/3363262 |
| url_provider | http://psasir.upm.edu.my/ |