New conversational agent uses LLMs and KG-BERT for student psychological and learning analysis

Researchers have developed a psychologically-aware conversational agent that integrates large language models (LLMs), a knowledge graph-enhanced BERT (KG-BERT), and a bidirectional LSTM network. This system aims to improve both learning performance and emotional well-being in educational settings by analyzing textual semantics, speech features, and behavioral trends. A pilot study involving 45 university students indicated increased motivation, reduced stress, and moderate academic gains compared to unimodal approaches. The study also included an ablation analysis to assess the contributions of the knowledge-graph component and individual modalities. AI

IMPACT This research could lead to more adaptive and supportive educational tools by enabling AI agents to better understand and respond to student cognitive and emotional states.

RANK_REASON The cluster contains an academic paper detailing a new research methodology and findings. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• arXiv
• Bert
• DagsHub
• Hugging Face
• KG-BERTScore: Incorporating Knowledge Graph into BERTScore for Reference-Free Machine Translation Evaluation
• large-language models
• long short-term memory
• Nour El Houda Ben Chaabene

• paper
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →