View in EDS

Multimodal prediction of student performance: A fusion of signed graph neural networks and large language models.

Saved in:
Bibliographic Details
Title: Multimodal prediction of student performance: A fusion of signed graph neural networks and large language models.
Authors: Wang, Sijie1,2 (AUTHOR) swan387@aucklanduni.ac.nz, Ni, Lin2 (AUTHOR) lni600@aucklanduni.ac.nz, Zhang, Zeyu1 (AUTHOR) zzha669@aucklanduni.ac.nz, Li, Xiaoxuan2 (AUTHOR) xli443@aucklanduni.ac.nz, Zheng, Xianda2 (AUTHOR) xzhe162@aucklanduni.ac.nz, Liu, Jiamou2 (AUTHOR) jiamou.liu@auckland.ac.nz
Source: Pattern Recognition Letters. May2024, Vol. 181, p1-8. 8p.
Subjects: Graph neural networks, Language models, Bipartite graphs, Natural language processing, School dropout prevention, At-risk students
Abstract: In online education platforms, accurately predicting student performance is essential for timely dropout prevention and interventions for at-risk students. This task is made difficult by the prevalent use of Multiple-Choice Questions (MCQs) in learnersourcing platforms, where noise in student-generated content and the limitations of existing unsigned graph-based models, specifically their inability to distinguish the semantic meaning between correct and incorrect responses, hinder accurate performance predictions. To address these issues, we introduce the L arge L anguage M odel enhanced S igned B ipartite graph C ontrastive L earning (LLM-SBCL) model—a novel Multimodal Model utilizing Signed Graph Neural Networks (SGNNs) and a Large Language Model (LLM). Our model uses a signed bipartite graph to represent students' answers, with positive and negative edges denoting correct and incorrect responses, respectively. To mitigate noise impact, we apply contrastive learning to the signed graphs, combined with knowledge point embeddings from the LLM to further enhance our model's predictive performance. Upon evaluating our model on five real-world datasets, it demonstrates superior accuracy and stability, exhibiting an average F1 improvement of 3.7% over the best baseline models. • Student-question interactions modeled via a signed bipartite graph. • Problem cast as link sign prediction in signed bipartite graph. • Contrastive learning employed to handle student content noise. • Using large language model to extract knowledge from questions. [ABSTRACT FROM AUTHOR]
Copyright of Pattern Recognition Letters is the property of Elsevier B.V. and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:In online education platforms, accurately predicting student performance is essential for timely dropout prevention and interventions for at-risk students. This task is made difficult by the prevalent use of Multiple-Choice Questions (MCQs) in learnersourcing platforms, where noise in student-generated content and the limitations of existing unsigned graph-based models, specifically their inability to distinguish the semantic meaning between correct and incorrect responses, hinder accurate performance predictions. To address these issues, we introduce the L arge L anguage M odel enhanced S igned B ipartite graph C ontrastive L earning (LLM-SBCL) model—a novel Multimodal Model utilizing Signed Graph Neural Networks (SGNNs) and a Large Language Model (LLM). Our model uses a signed bipartite graph to represent students' answers, with positive and negative edges denoting correct and incorrect responses, respectively. To mitigate noise impact, we apply contrastive learning to the signed graphs, combined with knowledge point embeddings from the LLM to further enhance our model's predictive performance. Upon evaluating our model on five real-world datasets, it demonstrates superior accuracy and stability, exhibiting an average F1 improvement of 3.7% over the best baseline models. • Student-question interactions modeled via a signed bipartite graph. • Problem cast as link sign prediction in signed bipartite graph. • Contrastive learning employed to handle student content noise. • Using large language model to extract knowledge from questions. [ABSTRACT FROM AUTHOR]
ISSN:01678655
DOI:10.1016/j.patrec.2024.03.007