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

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 the conversational bot is a more engaging and effective platform for improving spoken English proficiency. The tool shows potential for supporting learners in preparing for international academic environments. [ABSTRACT FROM AUTHOR]

Copyright of Education & Information Technologies is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)