Problem
Research questions and friction points this paper is trying to address.
Dialogue Act
GenAI
L2 oral practice
learner-chatbot interaction
sequential analysis
Dialogue Act Patterns in GenAI-Mediated L2 Oral Practice: A Sequential Analysis of Learner-Chatbot Interactions
🤖 AI Summary
This study investigates the conversational behavior patterns of generative AI–powered voice chatbots in second language (L2) speaking practice and their relationship with learning outcomes. Drawing on 70 dialogues produced by 12 middle school students over a 10-week intervention, the research team developed a pedagogically oriented dialogue act coding framework and employed manual annotation, sequential analysis, and comparative statistics to analyze interactions from both educational linguistics and human–computer interaction perspectives. Findings reveal that high-gain learners more frequently initiated questions and exhibited a higher incidence of prompt corrective feedback immediately following responses, whereas low-gain dialogues were predominantly characterized by clarification requests triggered by comprehension difficulties. The study underscores the critical role of feedback type and timing in fostering effective learner–agent interaction, offering theoretical insights and practical guidance for designing generative AI systems as L2 speaking partners.
📝 Abstract
While generative AI (GenAI) voice chatbots offer scalable opportunities for second language (L2) oral practice, the interactional processes related to learners' gains remain underexplored. This study investigates dialogue act (DA) patterns in interactions between Grade 9 Chinese English as a foreign language (EFL) learners and a GenAI voice chatbot over a 10-week intervention. Seventy sessions from 12 students were annotated by human coders using a pedagogy-informed coding scheme, yielding 6,957 coded DAs. DA distributions and sequential patterns were compared between high- and low-progress sessions. At the DA level, high-progress sessions showed more learner-initiated questions, whereas low-progress sessions exhibited higher rates of clarification-seeking, indicating greater comprehension difficulty. At the sequential level, high-progress sessions were characterised by more frequent prompting-based corrective feedback sequences, consistently positioned after learner responses, highlighting the role of feedback type and timing in effective interaction. Overall, these findings underscore the value of a dialogic lens in GenAI chatbot design, contribute a pedagogy-informed DA coding framework, and inform the design of adaptive GenAI chatbots for L2 education.
Innovation
Methods, ideas, or system contributions that make the work stand out.
dialogue act
sequential analysis
generative AI
corrective feedback
L2 oral practice
🔎 Similar Papers
No similar papers found.
