An AI Agent Facilitating Student Help-Seeking: Producing Data on Student Support Needs
Merikko, Joonas; Silvola, Anni
Rheinisch-Westfaelische Technische Hochschule Aachen
Merikko, J., & Silvola, A. (2024). An AI agent facilitating student help-seeking: Producing data on student support needs. Joint Proceedings of LAK 2024 Workshops co-located with 14th International Conference on Learning Analytics and Knowledge (LAK 2024), 185-194. https://ceur-ws.org/Vol-3667/GenAILA-paper2.pdf
https://creativecommons.org/licenses/by/4.0/
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/
© 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202405213789
https://urn.fi/URN:NBN:fi:oulu-202405213789
Tiivistelmä
Abstract
Large language models (LLMs) have provided unprecedented possibilities for personalizing educational experiences. Studies have addressed the potential of these models in supporting the learning process. Still, less attention has been given to how LLMs could help students to sustain their academic well-being. The current paper examines the use of LLMs in facilitating students’ help-seeking behaviors in an educational context. We build on earlier work on a rule-based chatbot providing students with support opportunities. First, we use thematic analysis with student support experts’ wordings on student support needs to build a support need classification model. Then, we utilize this classification model, GPT-4 API, and WhatsApp API, to build a support bot prototype and describe the development process and technological architecture. We discuss the possibilities of such technology in lowering barriers to help-seeking and producing data on student support needs and well-being for learning analytics applications.
Large language models (LLMs) have provided unprecedented possibilities for personalizing educational experiences. Studies have addressed the potential of these models in supporting the learning process. Still, less attention has been given to how LLMs could help students to sustain their academic well-being. The current paper examines the use of LLMs in facilitating students’ help-seeking behaviors in an educational context. We build on earlier work on a rule-based chatbot providing students with support opportunities. First, we use thematic analysis with student support experts’ wordings on student support needs to build a support need classification model. Then, we utilize this classification model, GPT-4 API, and WhatsApp API, to build a support bot prototype and describe the development process and technological architecture. We discuss the possibilities of such technology in lowering barriers to help-seeking and producing data on student support needs and well-being for learning analytics applications.
Kokoelmat
- Avoin saatavuus [34186]
Ellei muuten mainita, aineiston lisenssi on https://creativecommons.org/licenses/by/4.0/