New dual knowledge graph framework enhances user intent inference from reviews

Researchers have developed DKG-MTI, a novel dual knowledge graph framework designed to improve user intent inference from online travel reviews. This framework addresses limitations in existing methods by constructing a User-Specific Intent Knowledge Graph from individual reviews and aligning it with a Global Hotel Knowledge Graph using structure-aware semantic smoothing. The integrated knowledge is then processed by a large language model to simultaneously predict aspect ratings and generate reverse user intent statements, outperforming current LLM and retrieval-based baselines on TripAdvisor data. AI

IMPACT This framework could improve the accuracy and explainability of user intent analysis in domains like travel, potentially leading to better personalized recommendations and services.

RANK_REASON The cluster contains a research paper detailing a new framework for AI-based user intent inference. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• arXiv
• DKG-MTI
• Global Hotel Knowledge Graph
• Tripadvisor
• User-Specific Intent Knowledge Graph

• paper
• other

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