With the increasing popularity of personalized tourism experiences, recommendation systems play a crucial role in helping travelers discover destinations, activities, and itineraries that match their preferences. Traditional recommendation models often rely on collaborative filtering or content-based filtering, which may struggle with cold-start issues, lack of contextual awareness, and limited adaptability to dynamic tourism trends. Knowledge graphs (KGs) provide structured representations of entities and their relationships, offering a powerful way to enhance recommendation systems by integrating domain knowledge, user-generated content, and external tourism data. Additionally, Large Language Models (LLMs) can be used to enrich the KG with semantic understanding, improving recommendations by leveraging context-aware reasoning and natural language interactions. This thesis explores the development of a knowledge graph-based tourism recommendation system for Chinese travelers by constructing a time-sensitive ontology, integrating tourism data from Xiaohongshu (Red Notes), and leveraging LLMs for enhanced personalization and recommendation generation.
Thesis Type |
|
Student |
Ziyi Xu |
Status |
Running |
Presentation room |
Seminar room I5 6202 |
Supervisor(s) |
Stefan Decker |
Advisor(s) |
Yongli Mou |
Contact |
mou@dbis.rwth-aachen.de |
Objectives
- Construct a time-sensitive ontology that models tourism-related entities (e.g., locations, attractions, events, user preferences) and their relationships.
- Build a knowledge graph that integrates multi-source tourism data, including Xiaohongshu posts, reviews, travel guides, and historical trends.
- Develop a recommendation system that leverages the knowledge graph and LLMs to provide personalized tourism suggestions based on user preferences, seasonal factors, and real-time trends.
Tasks
- Tourism Ontology Construction
Define key entities (e.g., destinations, attractions, restaurants, travel activities).
Model relationships (e.g., “located in,” “popular in season,” “recommended by users”).
Ensure the ontology supports temporal factors (e.g., best travel seasons, holiday events). - Knowledge Graph Construction
Extract structured and unstructured data from Xiaohongshu and other sources (e.g., GeoNames, Dianping).
Use Natural Language Processing (NLP) and Large Language Models (LLMs) to process travel reviews and user-generated content. - Tourism Recommendation System Development
Implement LLM-powered recommendation models, incorporating contextual awareness.
Design a hybrid recommendation engine combining knowledge graph reasoning and LLM-based natural language interactions.
Evaluate recommendations using real-world tourism datasets and user feedback.
- Machine Learning and Deep Learning
- Basics of recommendation systems (collaborative filtering, content-based, hybrid models).
- Experience with LLMs (e.g., LLaMA, Qwen, GPT and Deepseek).
- Knowledge Graphs and NLP
- Familiarity with knowledge graph construction and ontology modeling.
- Proficiency in NLP techniques for text mining, sentiment analysis, and entity recognition.
- Programming and Tools
- Python, PyTorch for deep learning.
- Graph databases (Neo4j, RDF, or PyTorch Geometric).
- Hugging Face Transformers for LLM-based recommendations.
- Web scraping and API handling for Xiaohongshu data collection.