Cross-Platform Domain Adaptation for Multi-Modal MOOC Learner Satisfaction Prediction

2026-04-14

AI Summary

This study addresses the performance degradation in cross-platform MOOC satisfaction prediction caused by discrepancies in review styles, user demographics, behavioral log formats, and rating conventions. To tackle this challenge, the authors propose the ADAPT-MS framework, which freezes a large language model to encode textual reviews, standardizes behavioral logs, and jointly integrates domain-adversarial training, rating bias correction, and gated multimodal fusion. Notably, ADAPT-MS achieves unsupervised and few-shot cross-platform transfer for the first time in this domain. Experiments across three major MOOC platforms demonstrate its effectiveness, yielding an RMSE of 0.66 under fully unsupervised settings and further improving to 0.60 with only 1,000 labeled target samples—significantly outperforming existing baselines and confirming the framework’s strong generalization capability and novelty.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Application Domains: Humanities & Computational Social Science
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

Learner satisfaction prediction from MOOC reviews and behavioral logs is valuable for course quality improvement and platform operations. In practice, models trained on one platform degrade significantly when deployed on another due to domain shift in review style, learner population, behavioral logging schemas, and platform-specific rating norms. We study \textbf{cross-platform domain adaptation} for multi-modal MOOC satisfaction prediction under limited or absent target-platform labels. We propose \textbf{ADAPT-MS}, a platform-adaptive framework that (i) encodes review text with a frozen LLM encoder and behavioral traces with a canonical-vocabulary MLP, (ii) aligns cross-platform representations via domain-adversarial training with gradient reversal, (iii) corrects platform-specific rating bias through a latent-variable calibration layer, and (iv) handles missing behavioral modalities via gated fusion with modality dropout. Experiments on a multi-platform MOOC dataset spanning three major platforms demonstrate that ADAPT-MS achieves target-platform RMSE of 0.66 in the unsupervised setting (zero labeled target samples) and 0.60 with 1000 labeled target samples, outperforming strong baselines including naive pooling, domain-adversarial alignment without calibration, and full fine-tuning. Ablation studies confirm the independent contribution of each component, and few-shot adaptation curves demonstrate stable improvement even with as few as 50 labeled target samples.

Problem

• cross-platform domain adaptation
• MOOC learner satisfaction prediction
• domain shift
• multi-modal learning
• unsupervised adaptation

Innovation

• cross-platform domain adaptation
• multi-modal learning
• domain-adversarial training
• rating bias calibration
• modality dropout