TY - GEN
T1 - How Self-Disclosing Chatbots Influence Student Engagement, Assessment Accuracy, and Self-Reflection in Academic Stress Assessment
AU - Park, Minyoung
AU - Park, Bogyeom
AU - Seo, Kyoungwon
N1 - Publisher Copyright:
© 2025 Copyright held by the owner/author(s).
PY - 2025/4/26
Y1 - 2025/4/26
N2 - Academic stress poses substantial risks to students’ well-being and academic performance, emphasizing the need for assessment tools that encourage deeper self-reflection while ensuring accuracy. This study explores how self-disclosure in chatbots can enhance student engagement, assessment accuracy, and self-reflection in academic stress assessments. Two chatbots were developed: a non-self-disclosing (NSD) chatbot and a self-disclosing (SD) chatbot, both integrating the SISCO Inventory of Academic Stress (SISCO-AS) questionnaire. Chatbot interaction logs and interview responses from 40 university students were analyzed to measure student engagement, assessment accuracy, and the depth of self-reflection. The findings demonstrate that the SD chatbot significantly increased engagement, showed improvements in assessment accuracy, and facilitated deeper self-reflection compared to the NSD chatbot. This study highlights the pivotal role of self-disclosure in improving the quality of chatbot-based stress assessments and provides insights for designing tools that support students in recognizing and managing academic stress.
AB - Academic stress poses substantial risks to students’ well-being and academic performance, emphasizing the need for assessment tools that encourage deeper self-reflection while ensuring accuracy. This study explores how self-disclosure in chatbots can enhance student engagement, assessment accuracy, and self-reflection in academic stress assessments. Two chatbots were developed: a non-self-disclosing (NSD) chatbot and a self-disclosing (SD) chatbot, both integrating the SISCO Inventory of Academic Stress (SISCO-AS) questionnaire. Chatbot interaction logs and interview responses from 40 university students were analyzed to measure student engagement, assessment accuracy, and the depth of self-reflection. The findings demonstrate that the SD chatbot significantly increased engagement, showed improvements in assessment accuracy, and facilitated deeper self-reflection compared to the NSD chatbot. This study highlights the pivotal role of self-disclosure in improving the quality of chatbot-based stress assessments and provides insights for designing tools that support students in recognizing and managing academic stress.
KW - Academic stress assessment
KW - Assessment accuracy
KW - Chatbot
KW - Large language model
KW - Self-disclosure
KW - Self-reflection
KW - Student engagement
UR - https://www.scopus.com/pages/publications/105005762015
U2 - 10.1145/3706599.3719684
DO - 10.1145/3706599.3719684
M3 - Conference contribution
AN - SCOPUS:105005762015
T3 - Conference on Human Factors in Computing Systems - Proceedings
BT - CHI EA 2025 - Extended Abstracts of the 2025 CHI Conference on Human Factors in Computing Systems
PB - Association for Computing Machinery
T2 - 2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025
Y2 - 26 April 2025 through 1 May 2025
ER -
