Foreign language anxiety remains a persistent affective barrier that can hinder students’ engagement and performance in English language classrooms. With the increasing integration of artificial intelligence in education, chatbots have emerged as potential pedagogical tools that can provide low-stakes interaction and emotional support. However, empirical evidence on their effectiveness in reducing anxiety in EFL contexts is still limited. This study investigates the efficacy of a chatbot in reducing anxiety levels among students in an English language classroom. Adopting a mixed-methods design, the study involved 30 undergraduate students over a 16-week semester. Quantitative data were collected using pre- and post-tests based on an adapted version of the Foreign Language Classroom Anxiety Scale (FLCAS). A paired-samples t-test was conducted to measure changes in anxiety levels, while a one-way ANOVA examined differences based on chatbot usage frequency. To complement the quantitative findings, semi-structured interviews were conducted with six participants and were analyzed thematically. A paired-samples t-test revealed a significant reduction in anxiety levels following the integration of the chatbot into classroom activities (p < .001). Although a one-way ANOVA showed no significant difference in anxiety reduction across varying levels of chatbot usage frequency (F(2,27) = 0.303, p = .741), students' qualitative responses highlighted the chatbot’s value in lowering anxiety. Three themes emerged from the interviews, including reduced pressure due to quick responses, enhanced confidence through answer validation, and emotional comfort gained from the chatbot’s presence. These findings suggest that chatbots can contribute to a more supportive language learning environment, particularly in addressing anxiety issues in foreign language classrooms.
Copyrights © 2025