Publicação
An explorative investigation into leveraging LLMs to predict university students' learning motivation
| Resumo: | Learning motivation is a key variable in learning. Therefore, its assessment has consistently been a popular research topic. While traditional methods like self-report still dominate, methods integrating passive mobile sensing have emerged, using smartphones to collect behavioral data and assess learning motivation via statistical and machine learning techniques. Recent advances in large language models (LLMs) offer new perspectives for psychological measurements, yet their application in learning motivation assessment remains underexplored. To bridge this gap, we propose a novel approach that integrates LLMs with passive mobile sensing to assess and predict students' learning motivation. We constructed our dataset using mobile sensing data and self-report measures, then designed zero-shot and few-shot tasks embedded in LLMs to evaluate the performance. Ultimately, our findings indicate the feasibility and highlight the potential of leveraging LLMs to predict learning motivation levels based on mobile sensing data. |
|---|---|
| Autores principais: | Feng, Yu |
| Outros Autores: | Zhao, Tongyu; Zu, Yatong; Tavares, Adriano; Gomes, Tiago Manuel Ribeiro; Xu, Hao |
| Ano: | 2025 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| Resumo: | Learning motivation is a key variable in learning. Therefore, its assessment has consistently been a popular research topic. While traditional methods like self-report still dominate, methods integrating passive mobile sensing have emerged, using smartphones to collect behavioral data and assess learning motivation via statistical and machine learning techniques. Recent advances in large language models (LLMs) offer new perspectives for psychological measurements, yet their application in learning motivation assessment remains underexplored. To bridge this gap, we propose a novel approach that integrates LLMs with passive mobile sensing to assess and predict students' learning motivation. We constructed our dataset using mobile sensing data and self-report measures, then designed zero-shot and few-shot tasks embedded in LLMs to evaluate the performance. Ultimately, our findings indicate the feasibility and highlight the potential of leveraging LLMs to predict learning motivation levels based on mobile sensing data. |
|---|
Atividades financiadas
Não foram encontrados projetos financiados.