Classical Feature Embeddings Help in BERT-Based Human Mobility Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908606976229376 |
|---|---|
| author | Liu, Yunzhi Tan, Haokai Kanjaria, Rushi Li, Lihuan Salim, Flora D. |
| author_facet | Liu, Yunzhi Tan, Haokai Kanjaria, Rushi Li, Lihuan Salim, Flora D. |
| contents | Human mobility forecasting is crucial for disaster relief, city planning, and public health. However, existing models either only model location sequences or include time information merely as auxiliary input, thereby failing to leverage the rich semantic context provided by points of interest (POIs). To address this, we enrich a BERT-based mobility model with derived temporal descriptors and POI embeddings to better capture the semantics underlying human movement. We propose STaBERT (Semantic-Temporal aware BERT), which integrates both POI and temporal information at each location to construct a unified, semantically enriched representation of mobility. Experimental results show that STaBERT significantly improves prediction accuracy: for single-city prediction, the GEO-BLEU score improved from 0.34 to 0.75; for multi-city prediction, from 0.34 to 0.56. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_20275 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Classical Feature Embeddings Help in BERT-Based Human Mobility Prediction Liu, Yunzhi Tan, Haokai Kanjaria, Rushi Li, Lihuan Salim, Flora D. Artificial Intelligence Human mobility forecasting is crucial for disaster relief, city planning, and public health. However, existing models either only model location sequences or include time information merely as auxiliary input, thereby failing to leverage the rich semantic context provided by points of interest (POIs). To address this, we enrich a BERT-based mobility model with derived temporal descriptors and POI embeddings to better capture the semantics underlying human movement. We propose STaBERT (Semantic-Temporal aware BERT), which integrates both POI and temporal information at each location to construct a unified, semantically enriched representation of mobility. Experimental results show that STaBERT significantly improves prediction accuracy: for single-city prediction, the GEO-BLEU score improved from 0.34 to 0.75; for multi-city prediction, from 0.34 to 0.56. |
| title | Classical Feature Embeddings Help in BERT-Based Human Mobility Prediction |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.20275 |