# Semantic Trajectory Data Mining with LLM-Informed POI Classification

arXiv: https://arxiv.org/abs/2405.11715 · HTML: https://mlsanity.com/paper/2405.11715/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 45 references that are in the map.
- First posted on arXiv 20 May 2024.

## Builds on (most cited first, 7 of 7)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [LLM as A Robotic Brain: Unifying Egocentric Memory and Control](https://mlsanity.com/paper/2304.09349/) (2023)
- [Using Connected Vehicle Trajectory Data to Evaluate the Effects of Speeding](https://mlsanity.com/paper/2303.16396/) (2023)
- [Tracking COVID-19 by Tracking Infectious Trajectories](https://mlsanity.com/paper/2005.05523/) (2020)

## Built on by (most cited first, 13 of 13)

- [A Survey on Point-of-Interest Recommendation: Models, Architectures, and Security](https://mlsanity.com/paper/2410.02191/) (2024)
- [Deep Activity Model: A Generative Approach for Human Mobility Pattern Synthesis](https://mlsanity.com/paper/2405.17468/) (2024)
- [Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Review](https://mlsanity.com/paper/2506.01364/) (2025)
- [TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs](https://mlsanity.com/paper/2406.10310/) (2024)
- [Human Mobility Modeling with Household Coordination Activities under Limited Information via Retrieval-Augmented LLMs](https://mlsanity.com/paper/2409.17495/) (2024)
- [Learning Universal Human Mobility Patterns with a Foundation Model for Cross-domain Data Fusion](https://mlsanity.com/paper/2503.15779/) (2025)
- [Urban Computing in the Era of Large Language Models](https://mlsanity.com/paper/2504.02009/) (2025)
- [Reconstructing Human Mobility Pattern: A Semi-Supervised Approach for Cross-Dataset Transfer Learning](https://mlsanity.com/paper/2410.03788/) (2024)
- [Popular LLMs Amplify Race and Gender Disparities in Human Mobility](https://mlsanity.com/paper/2411.14469/) (2024)
- [MobiVerse: Scaling Urban Mobility Simulation with Hybrid Lightweight Domain-Specific Generator and Large Language Models](https://mlsanity.com/paper/2506.21784/) (2025)
- [Beyond 9-to-5: A Generative Model for Augmenting Mobility Data of Underrepresented Shift Workers](https://mlsanity.com/paper/2507.19510/) (2025)
- [TurnBack: A Geospatial Route Cognition Benchmark for Large Language Models through Reverse Route](https://mlsanity.com/paper/2509.18173/) (2025)
- [Uncertainty-Aware Trip Purpose Inference from GPS Trajectories via POI Semantic Zones and Pareto Calibration](https://mlsanity.com/paper/2605.01257/) (2026)

## Abstract (arXiv)

Human travel trajectory mining is crucial for transportation systems, enhancing route optimization, traffic management, and the study of human travel patterns. Previous rule-based approaches without the integration of semantic information show a limitation in both efficiency and accuracy. Semantic information, such as activity types inferred from Points of Interest (POI) data, can significantly enhance the quality of trajectory mining. However, integrating these insights is challenging, as many POIs have incomplete feature information, and current learning-based POI algorithms require the integrity of datasets to do the classification. In this paper, we introduce a novel pipeline for human travel trajectory mining. Our approach first leverages the strong inferential and comprehension capabilities of large language models (LLMs) to annotate POI with activity types and then uses a Bayesian-based algorithm to infer activity for each stay point in a trajectory. In our evaluation using the OpenStreetMap (OSM) POI dataset, our approach achieves a 93.4% accuracy and a 96.1% F-1 score in POI classification, and a 91.7% accuracy with a 92.3% F-1 score in activity inference.