Contemporary Considerations
From Prompts to Presentations: ChatGPT in the EFL Classroom
Paper Presentation in a Themed Session Shao Hsuan Wu
This study examines the integration of ChatGPT in assisting sixth-grade EFL students to create and deliver PowerPoint presentations using simplified, adaptive scripts. In this paper, I describe how ChatGPT was used to generate presentation drafts tailored to students’ English proficiency levels and how this process supported differentiated instruction and guided students’ preparation for presentations. Over one semester, students used ChatGPT to produce initial drafts of presentation scripts. These drafts were refined through interactions with the AI and discussions with the teacher. Data were collected through classroom observations, teacher reflection journals, student interviews, and analysis of presentation scripts and slides. Findings reveal four key observations: (1) Simplifying Script Generation Process—with ChatGPT's assistance, students could quickly generate draft scripts for their PowerPoint presentations, bypassing the need to type out each sentence or come up with content entirely on their own.; (2) Differentiated Support—ChatGPT provided scripts with varying levels of complexity based on students’ needs, enabling tailored support within the classroom; (3) Familiarization with Content—students engaged in repeated interactions with the scripts, helping them become more acquainted with their material; and (4) Structured Preparation—the AI-generated scripts offered a clear framework that guided students through the preparation process and reduced uncertainty. This study presents the role of AI tools like ChatGPT in supporting differentiated instruction and promoting a more engaging and inclusive learning environment for young EFL learners. It provides insights into how technology can be used to assist in language education and the development of multimodal communication skills.
Fostering Learners' Agency and Voice: A Case Study of AI-Supported Revision in Second Language Writing
Paper Presentation in a Themed Session Hisae Matsui
This paper explores the impact of AI-powered tools, DeepL and ChatGPT, on self-expression and the learning process in a fourth-semester university-level Japanese language speech project. This case study involved 15 students, with limited survey data. Students used AI tools during revision of their speech manuscripts through a multi-stage drafting process. Survey results indicate that while students generally conveyed their intended meaning using AI, preserving individual style was challenging, particularly for lower-achieving students. A clear correlation was observed between students' engagement with AI tools during revision and both their revision strategies and their grades. Analysis of open-ended responses revealed higher-achieving students tended to actively engage with AI, viewing it as a learning partner, critically evaluating suggestions, and demonstrated more specific usage patterns. For example, these students leveraged translation functions to verify their intent and selectively integrated AI suggestions. Conversely, lower-achieving students tended to rely passively on AI, accepting AI-generated text during revision, demonstrating less critical engagement. Furthermore, higher-achieving students’ initial drafts showed minor changes after AI-supported revision, while lower-achieving students’ drafts showed substantial alterations. These findings suggest a student's approach to AI tools during revision is significantly associated with their self-expression abilities and grades. Viewing AI as a partner that enhances self-expression and learning during revision, while maintaining a critical lens, is associated with greater effectiveness. This study offers practical implications for integrating AI in language education and highlight the importance of nurturing learner agency and critical thinking.
Leveraging AI Conversations for English Learning: Effects of ChatGPT on TOEIC and Speech Ace Scores in a PBL Setting
Paper Presentation in a Themed Session Tsukasa Yamanaka, Chiho Toyoshima
This paper examines the effects of incorporating ChatGPT-based English conversations into a Project-Based English Learning course, focusing on TOEIC Listening and Reading scores and Speech Ace assessment metrics. A total of 110 first- and second-year university students participated in the study, divided into two groups: a Homework group, which engaged in weekly ChatGPT conversations, and a No-Homework group, which did not. The findings indicate mixed results. While the Homework group demonstrated significant improvements in pronunciation, vocabulary, and fluency, especially among second-year students, there was no clear correlation between the number of completed assignments and score improvements. Moreover, TOEIC scores showed greater progress in Listening and Reading for the Homework group compared to the No-Homework group. However, the reliance on text-based interaction with ChatGPT seems to have disproportionately benefited reading and vocabulary development, while its impact on spoken communication skills was less consistent. One notable drawback was an increase in unnatural pauses, suggesting that AI-generated conversations may not always foster natural speech patterns. These findings highlight both the potential and the limitations of using AI tools in English education. While ChatGPT can be an effective supplement for developing language skills, task design must be carefully refined to encourage more natural and dynamic conversational engagement. This study suggests that while AI-driven learning has promise, further pedagogical adjustments are necessary to fully integrate it into language education effectively.
