Multidimensional classification of posts for online course discussion forum curation

2025/08/05 by Candido, Antonio Leandro Martins, Maia, Jose Everardo Bessa
#68 #Computation and Language (cs.CL) #FOS: Computer and information sciences #I.2.7 #Machine Learning (cs.LG)

paper · doi:10.48550/arxiv.2508.10008

Abstract

The automatic curation of discussion forums in online courses requires constant updates, making frequent retraining of Large Language Models (LLMs) a resource-intensive process. To circumvent the need for costly fine-tuning, this paper proposes and evaluates the use of Bayesian fusion. The approach combines the multidimensional classification scores of a pre-trained generic LLM with those of a classifier trained on local data. The performance comparison demonstrated that the proposed fusion improves the results compared to each classifier individually, and is competitive with the LLM fine-tuning approach

Citations

• Adaptable and Reliable Text Classification using Large Language Models
• A Closer Look at Classification Evaluation Metrics and a Critical Reflection of Common Evaluation Practice
• Deep Dependency Networks for Multi-Label Classification
• Bayesian Classifier Fusion with an Explicit Model of Correlation
• Metrics for Multi-Class Classification: an Overview
• Don't Stop Pretraining: Adapt Language Models to Domains and Tasks
• The MUIR Framework: Cross-Linking MOOC Resources to Enhance Discussion Forums
• Longitudinal Analysis of Discussion Topics in an Online Breast Cancer Community using Convolutional Neural Networks
• Methods of combining multiple classifiers and their applications to handwriting recognition

Related

• Semi-supervised and Unsupervised Methods for Categorizing Posts in Web Discussion Forums
• Tracing Forum Posts to MOOC Content using Topic Analysis
• Communication Communities in MOOCs
• Personalized Thread Recommendation for MOOC Discussion Forums
• Spam filtering on forums: A synthetic oversampling based approach for imbalanced data classification