CityHood: An Explainable Travel Recommender System for Cities and Neighborhoods

2025-07-24

AI Summary

Existing location-based travel recommendation systems suffer from poor interpretability, coarse-grained personalization (inadequate for neighborhood-level recommendations), and opaque decision rationales. To address these limitations, this paper proposes the first interactive travel recommendation system integrating interest modeling, multi-scale spatial analysis, and explainable AI (XAI). The system jointly models Google Places reviews with geographic, sociodemographic, and cultural features to enable dual-level personalization—both city- and neighborhood-scale. It innovatively adapts LIME to generate natural-language explanations that transparently articulate key inference grounds, such as spatial proximity and cultural alignment. A dedicated visualization interface further supports user exploration and validation of recommendations. Experimental results demonstrate significant improvements in recommendation credibility and user engagement compared to state-of-the-art baselines.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

We present CityHood, an interactive and explainable recommendation system that suggests cities and neighborhoods based on users' areas of interest. The system models user interests leveraging large-scale Google Places reviews enriched with geographic, socio-demographic, political, and cultural indicators. It provides personalized recommendations at city (Core-Based Statistical Areas - CBSAs) and neighborhood (ZIP code) levels, supported by an explainable technique (LIME) and natural-language explanations. Users can explore recommendations based on their stated preferences and inspect the reasoning behind each suggestion through a visual interface. The demo illustrates how spatial similarity, cultural alignment, and interest understanding can be used to make travel recommendations transparent and engaging. This work bridges gaps in location-based recommendation by combining a kind of interest modeling, multi-scale analysis, and explainability in a user-facing system.

Problem

• Recommends cities and neighborhoods based on user interests
• Explains recommendations using LIME and natural-language explanations
• Combines interest modeling, multi-scale analysis, and explainability

Innovation

• Leverages Google Places reviews with diverse indicators
• Uses LIME for explainable multi-scale recommendations
• Combines spatial similarity and cultural alignment