supervisor: ahsen Çini
Topic
Advancements in conversational AI technologies have transformed educational practices, offering learners interactive and adaptive tools to support their learning processes. Conversational agents, powered by artificial intelligence, can provide personalized feedback, answer queries, and guide learners through complex topics. As these tools become increasingly integrated into educational environments, understanding the metacognitive strategies learners employ when interacting with them is essential for optimizing their effectiveness.
Metacognitive strategies involve planning, monitoring, and evaluating one’s cognitive processes. These strategies enable learners to reflect on their understanding, identify gaps in knowledge, and adapt their approaches to learning. When learners interact with conversational agents, they may employ various metacognitive strategies, such as asking clarifying questions, seeking feedback, or summarizing learned content. This study aims to explore the relationship between learners’ metacognitive strategies and their use of conversational AI, focusing on how these strategies influence the learning process and outcomes.
The primary goal of this research is to identify the types of metacognitive strategies learners use when engaging with conversational agents and to analyze how these strategies impact their ability to learn new topics effectively. By doing so, the study seeks to provide insights into designing AI systems that better support learners’ metacognitive processes and enhance educational outcomes.
Method
Participants will be selected to represent varying levels of familiarity with conversational AI and metacognitive strategies.
Recommended data collection
Pre-Study Surveys: Participants will complete surveys assessing their prior knowledge of the subject matter, familiarity with conversational AI, and baseline metacognitive awareness using validated tools such as the Metacognitive Awareness Inventory (MAI).
Learning Tasks: Participants will use a conversational agent to learn a new topic (e.g., sustainability, coding, or historical events). The AI will be designed to simulate a tutor, providing explanations, answering questions, and prompting learners to reflect on their understanding.
Interaction Logs: All interactions with the conversational agent will be recorded, capturing the types of questions, requests, and feedback learners provide and receive.
Proposed research questions
- What metacognitive strategies do learners employ when interacting with conversational agents?
- What types of questions and requests do learners make to conversational agents to regulate their learning processes?
references
Azevedo, R., & Cromley, J. G. (2004). Does training on self-regulated learning facilitate students' learning with hypermedia? Journal of Educational Psychology, 96(3), 523-535.
Çini, A., Järvelä, S., Dindar, M., & Malmberg, J. (2023). How multiple levels of metacognitive awareness operate in collaborative problem solving. Metacognition and Learning, 18(3), 891-922.
Flavell, J. H. (1979). Metacognition and cognitive monitoring: A new area of cognitive–developmental inquiry. American Psychologist, 34(10), 906-911
Papadopoulos, P. M., Obwegeser, N., & Weinberger, A. (2021). Concurrent and retrospective metacognitive judgements as feedback in audience response systems: Impact on performance and self-assessment accuracy. Computers and Education Open, 2, 100046.
Schraw, G., & Dennison, R. S. (1994). Assessing metacognitive awareness. Contemporary Educational Psychology, 19(4), 460-475.
Winne, P. H., & Hadwin, A. F. (1998). Studying as self-regulated learning. In D. J. Hacker, J. Dunlosky, & A. C. Graesser (Eds.), Metacognition in Educational Theory and Practice (pp. 277-304). Routledge.