Enhancing Emotional Intelligence through Generative AI-Supported Digital Storytelling: A Mixed Methods Study Using Epistemic Network Analysis
Saved in:
| Title: | Enhancing Emotional Intelligence through Generative AI-Supported Digital Storytelling: A Mixed Methods Study Using Epistemic Network Analysis |
|---|---|
| Language: | English |
| Authors: | Gwo-Jen Hwang, Yun-Fang Tu, Yue-I Lin, Hsiu-Ling Chen (ORCID |
| Source: | Journal of Computer Assisted Learning. 2026 42(3). |
| Availability: | Wiley. Available from: John Wiley & Sons, Inc. 111 River Street, Hoboken, NJ 07030. Tel: 800-835-6770; e-mail: cs-journals@wiley.com; Web site: https://www.wiley.com/en-us |
| Peer Reviewed: | Y |
| Page Count: | 18 |
| Publication Date: | 2026 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Junior High Schools Middle Schools Secondary Education |
| Descriptors: | Emotional Intelligence, Artificial Intelligence, Story Telling, Electronic Publishing, Technology Uses in Education, Social Emotional Learning, Junior High School Students, Self Efficacy |
| DOI: | 10.1002/jcal.70245 |
| ISSN: | 0266-4909 1365-2729 |
| Abstract: | Background: Social-emotional learning (SEL) has gained increasing attention in recent years due to its importance for students' emotional regulation, motivation and learning engagement. Digital storytelling (DST) has been widely recognised as a promising approach for supporting SEL; however, students often encounter challenges related to creative expression and technical execution during the storytelling process. Objective: Although DST holds considerable promise for supporting SEL, students often encounter challenges related to creative expression when using DST, which may limit their learning effectiveness. To address this issue, this study proposed a generative-AI (GAI)-supported DST approach. Method: A quasi-experimental design was adopted with 62 junior high school students. The experimental group (n = 30) learned using the GAI-DST approach, while the control group (n = 32) adopted a conventional DST approach. Quantitative data were collected through pre- and post-questionnaires on emotional intelligence and self-efficacy. Qualitative interview data were further analysed using epistemic network analysis (ENA) to explore students' learning perceptions and cognitive-emotional patterns. Results and Conclusions: Results showed that the GAI-DST approach significantly enhanced students' self-efficacy and the motivation dimension of emotional intelligence, while no significant differences were found in other emotional intelligence dimensions. The qualitative findings revealed that students in the GAI-DST group demonstrated a stronger orientation towards practice-based learning, tool-supported problem solving and emotional engagement, whereas students in the control group focused more on mastering basic skills. These findings suggest that the GAI-DST approach may exert selective effects on motivational and self-efficacy-related processes, rather than producing immediate, broad-based improvements across all dimensions of emotional intelligence. By conceptualising GAI as a mediational learning tool that supports mastery experiences and reflective interaction, this study provides a theoretically grounded explanation of how GAI can support SEL and offers suggestions for the design of AI-integrated instructional activities. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1506803 |
| Database: | ERIC |
| Abstract: | Background: Social-emotional learning (SEL) has gained increasing attention in recent years due to its importance for students' emotional regulation, motivation and learning engagement. Digital storytelling (DST) has been widely recognised as a promising approach for supporting SEL; however, students often encounter challenges related to creative expression and technical execution during the storytelling process. Objective: Although DST holds considerable promise for supporting SEL, students often encounter challenges related to creative expression when using DST, which may limit their learning effectiveness. To address this issue, this study proposed a generative-AI (GAI)-supported DST approach. Method: A quasi-experimental design was adopted with 62 junior high school students. The experimental group (n = 30) learned using the GAI-DST approach, while the control group (n = 32) adopted a conventional DST approach. Quantitative data were collected through pre- and post-questionnaires on emotional intelligence and self-efficacy. Qualitative interview data were further analysed using epistemic network analysis (ENA) to explore students' learning perceptions and cognitive-emotional patterns. Results and Conclusions: Results showed that the GAI-DST approach significantly enhanced students' self-efficacy and the motivation dimension of emotional intelligence, while no significant differences were found in other emotional intelligence dimensions. The qualitative findings revealed that students in the GAI-DST group demonstrated a stronger orientation towards practice-based learning, tool-supported problem solving and emotional engagement, whereas students in the control group focused more on mastering basic skills. These findings suggest that the GAI-DST approach may exert selective effects on motivational and self-efficacy-related processes, rather than producing immediate, broad-based improvements across all dimensions of emotional intelligence. By conceptualising GAI as a mediational learning tool that supports mastery experiences and reflective interaction, this study provides a theoretically grounded explanation of how GAI can support SEL and offers suggestions for the design of AI-integrated instructional activities. |
|---|---|
| ISSN: | 0266-4909 1365-2729 |
| DOI: | 10.1002/jcal.70245 |
