Can Pedagogical Agent-Based Scaffolding Boost Information Problem-Solving in One-on-One Collaborative Learning with a Virtual Learning Companion?
Saved in:
| Title: | Can Pedagogical Agent-Based Scaffolding Boost Information Problem-Solving in One-on-One Collaborative Learning with a Virtual Learning Companion? |
|---|---|
| Language: | English |
| Authors: | Yung-Hsiang Hu (ORCID |
| Source: | Education and Information Technologies. 2025 30(18):25853-25880. |
| Availability: | Springer. Available from: Springer Nature. One New York Plaza, Suite 4600, New York, NY 10004. Tel: 800-777-4643; Tel: 212-460-1500; Fax: 212-460-1700; e-mail: customerservice@springernature.com; Web site: https://link.springer.com/ |
| Peer Reviewed: | Y |
| Page Count: | 28 |
| Publication Date: | 2025 |
| Document Type: | Journal Articles Reports - Research |
| Education Level: | Higher Education Postsecondary Education |
| Descriptors: | Intelligent Tutoring Systems, Scaffolding (Teaching Technique), Cooperative Learning, Problem Solving, Artificial Intelligence, College Students, Information Literacy, Individualized Instruction |
| DOI: | 10.1007/s10639-025-13784-2 |
| ISSN: | 1360-2357 1573-7608 |
| Abstract: | The rapid emergence of generative AI has enabled students to participate in one-on-one online collaborative learning, facilitated by Virtual Learning Companions (VLCs) developed through ChatGPT, targeting specific learning goals. Nevertheless, addressing challenges related to enhancing students' need for cognition, learning performance, and information literacy in a human-bot collaborative context remains critical. In response, this quasi-experimental study introduces and evaluates a Pedagogical Agent (PA)-based Information Problem-Solving (IPS) scaffolding model. The model combines a VLC, referred to as Master Socrates, to present learning themes, and a PA, named TABOT, which helps students achieve the Big Six objectives by offering structured guidance and immediate feedback throughout their learning process. Seventy-eight university students participated, divided into an experimental group and a control group. The experimental group engaged in VLC-supported online collaborative learning with PA-based IPS scaffolding, while the control group used VLCs without scaffolding. Quantitative and qualitative analyses indicated that the scaffolding significantly improved students' learning performance, information literacy, and need for cognition. This scaffolding model presents a promising strategy for one-on-one online collaborative learning tailored to independent learners and educators, and it highlights how integrating sophisticated AI technologies can enrich personalized learning environments, thereby enhancing the educational experience via ChatGPT-powered VLCs. The findings underscore the effectiveness of integrating dual-agent scaffolding (pedagogical agent and virtual learning companion), driven by generative AI, in enhancing university students' information problem-solving skills and cognitive engagement. Educators and instructional designers should consider employing dual-agent scaffolding strategies with generative AI support to optimize students' collaborative information problem-solving performance in virtual learning environments. |
| Abstractor: | As Provided |
| Entry Date: | 2026 |
| Accession Number: | EJ1504230 |
| Database: | ERIC |
Be the first to leave a comment!
