Enhancing Tourism Recommender Systems for Sustainable City Trips Using Retrieval-Augmented Generation

2024-09-26

arXiv.org

AI Summary

Traditional tourism recommendation systems (TRS) largely neglect sustainability objectives, failing to align with the United Nations’ Sustainable Development Goals (SDGs). Method: This paper proposes a sustainability-oriented recommendation framework for urban tourism, built upon a Retrieval-Augmented Generation (RAG) architecture enhanced with a Sustainability-Aware Re-ranking (SAR) mechanism. SAR explicitly models three interdependent sustainability dimensions—environmental impact, community well-being, and tourist experience—by integrating city-level popularity and seasonal demand signals during prompt augmentation. A dynamic sustainability scoring module leverages open-source large language models (e.g., Llama-3.1-Instruct-8B and Mistral-Instruct-7B) to refine generation and ranking. Results: Extensive experiments demonstrate consistent and statistically significant improvements over SAR-free baselines across multiple evaluation metrics. The results confirm that embedding sustainability constraints not only enhances recommendation accuracy and relevance but also strengthens socio-environmental value alignment—thereby advancing responsible and resilient urban tourism.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Systems and Infrastructure for Web, Mobile and WoT: Sustainability and carbon-aware systems for Web, mobile, and WoT

Abstract

Tourism Recommender Systems (TRS) have traditionally focused on providing personalized travel suggestions, often prioritizing user preferences without considering broader sustainability goals. Integrating sustainability into TRS has become essential with the increasing need to balance environmental impact, local community interests, and visitor satisfaction. This paper proposes a novel approach to enhancing TRS for sustainable city trips using Large Language Models (LLMs) and a modified Retrieval-Augmented Generation (RAG) pipeline. We enhance the traditional RAG system by incorporating a sustainability metric based on a city's popularity and seasonal demand during the prompt augmentation phase. This modification, called Sustainability Augmented Reranking (SAR), ensures the system's recommendations align with sustainability goals. Evaluations using popular open-source LLMs, such as Llama-3.1-Instruct-8B and Mistral-Instruct-7B, demonstrate that the SAR-enhanced approach consistently matches or outperforms the baseline (without SAR) across most metrics, highlighting the benefits of incorporating sustainability into TRS.

Problem

• Balancing tourism preferences with sustainability goals in recommendations
• Integrating environmental and community factors into travel suggestion systems
• Enhancing recommender systems using LLMs and sustainability metrics

Innovation

• Uses Retrieval-Augmented Generation for sustainability
• Integrates sustainability metrics into RAG pipeline
• Enhances recommendations with SAR reranking method