
International Journal of Educational Technology in Higher Education, Journal Year: 2025, Volume and Issue: 22(1)
Published: May 8, 2025
Abstract Academic stress significantly affects students’ well-being and academic performance, highlighting the need for more effective assessment methods to guide targeted interventions. This study investigates how self-disclosure chatbots—designed share relevant experiences thoughts—can enhance assessments by increasing student engagement, improving accuracy, fostering deeper self-reflection. Two chatbot conditions were developed: a (SD) that used personal narratives build empathy, non-self-disclosure (NSD) chatbot. In randomized experiment with 50 university students, participants interacted either SD or NSD Results showed elicited higher as evidenced longer session lengths (15.55 ± 5.92 min) word counts (240 114.02 words), compared (11.31 5.21 min; 162.38 66.24 words). Assessment accuracy—evaluated comparing results from SISCO Inventory of Stress chatbot-generated evaluations—was slightly (0.936) than (0.862), based on accuracy within one-point deviation. Moreover, students who reported self-reflection developed actionable strategies managing their stress. Overall, these findings illuminate value in chatbot-based highlight broader applications addressing mental health challenges educational settings.
Language: Английский