An AI-powered conversational system for college students learning English as a second language

作者：Lili Dai, Fengming Wu · 发表于：Education and Information Technologies · 年份：2025 · DOI：10.1007/s10639-025-13640-3 · 被引用次数：11 · 研究领域：AI in Service Interactions、Online Learning and Analytics、Intelligent Tutoring Systems and Adaptive Learning

With the advancement of artificial intelligence, natural language processing, and speech recognition, conversational agents have emerged as promising tools for second language acquisition. This study designed an English conversational bot to help learners of English as a second language among Chinese university students learning English. The bot was implemented as a web application using Python Flask. A six-day comparative study was conducted with 56 students from the English department, who were randomly assigned to either the conversational bot or a traditional listen-and-repeat interface. The bot was implemented as a web application using Python Flask as a web application. To evaluate its feasibility, we compared it with an old listen-and-repeat interface using 56 Chinese college students from the English department over six days. We conducted Shapiro-Wilk normality tests, followed by t-tests to evaluate time spent on the application, engagement, anxiety change, vocabulary, and speaking tests. Findings shows that the conversational bot group reported significantly higher engagement scores (M = 4.37, SD = 0.44) compared to the control group (M = 3.87, SD = 0.51; t (26) = 2.8, p <.05). While both groups showed a reduction in language anxiety, the difference was not statistically significant. Participants using the bot demonstrated greater vocabulary use as responders ( t (26) = 3.5, p <.005) and higher speaking test gains ( p <.0001). In conclusion our findings suggest that ...