Massive-STEPS: Massive Semantic Trajectories for Understanding POI Check-ins -- Dataset and Benchmarks

2025-05-16

AI Summary

Existing POI recommendation research relies heavily on outdated (2012–2013) and geographically narrow datasets, lacking reproducible, cross-cultural, city-scale benchmarks for modern urban contexts. To address this, we introduce Semantic Trails+, the first large-scale, multi-city POI check-in benchmark covering 12 culturally diverse global cities, built from 24 months of real-world trajectory data (2017–2018). It integrates semantic POI metadata, cross-city spatiotemporal alignment, and hierarchical POI knowledge injection. We propose a standardized evaluation framework supporting both supervised and zero-shot POI recommendation. Extensive experiments across十余 state-of-the-art models demonstrate that semantic enhancement significantly improves cross-city generalization performance. The benchmark dataset and code are publicly released and have been widely adopted by the research community, effectively bridging a decade-long gap in both data recency and cultural diversity.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Applications of semantic technologies for improving search, browsing, recommendation, personalization
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Understanding human mobility through Point-of-Interest (POI) recommendation is increasingly important for applications such as urban planning, personalized services, and generative agent simulation. However, progress in this field is hindered by two key challenges: the over-reliance on older datasets from 2012-2013 and the lack of reproducible, city-level check-in datasets that reflect diverse global regions. To address these gaps, we present Massive-STEPS (Massive Semantic Trajectories for Understanding POI Check-ins), a large-scale, publicly available benchmark dataset built upon the Semantic Trails dataset and enriched with semantic POI metadata. Massive-STEPS spans 12 geographically and culturally diverse cities and features more recent (2017-2018) and longer-duration (24 months) check-in data than prior datasets. We benchmarked a wide range of POI recommendation models on Massive-STEPS using both supervised and zero-shot approaches, and evaluated their performance across multiple urban contexts. By releasing Massive-STEPS, we aim to facilitate reproducible and equitable research in human mobility and POI recommendation. The dataset and benchmarking code are available at: https://github.com/cruiseresearchgroup/Massive-STEPS

Problem

• Lack of recent, diverse city-level POI check-in datasets
• Over-reliance on outdated (2012-2013) mobility datasets
• Need reproducible benchmarks for global POI recommendation models

Innovation

• Large-scale dataset with semantic POI metadata
• Covers 12 diverse cities globally
• Benchmarked supervised and zero-shot models