Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
December 11, 2025ElectronicsOpen Access

Dynamic Topic Analysis and Visual Analytics for Trajectory Data: A Spatial Embedding Approach

View Full Paper
Ask AI
Bookmark
Share

Authors

HCHuarong ChenYWYadong WuLJLei Jing

Discussion

Loading...

Member takes

Overview

Novel approach leverages interactive visualization and topic modeling to explore trajectory data, highlighting dynamic patterns in urban mobility.

Key Points

  • This research aims to enhance the analysis of trajectory topics in urban mobility using a dynamic approach.
  • Introduced a novel embedding method using a retrained RoBERTa model on Morton-coded trajectories.
  • Employed a BERTopic-based approach enabling flexible analysis of topics across varying time windows.
  • Developed an interactive visualization system to facilitate exploration of trajectory topics.
  • Successfully identified coherent and meaningful patterns of dynamic trajectory topics.
  • Enabled multi-scale temporal analysis without model retraining.
  • Demonstrated effectiveness on a large-scale taxi trajectory dataset.

Cite This Study

Chen et al. (2025) studied this question.

synapsesocial.com/papers/694019342d562116f28f6e5chttps://doi.org/10.3390/electronics14244873
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Topic modelling for spatial insights: Uncovering space use from movement data2024 · 1 citations
  2. 2Trajectory Classification through Topological Data Analysis Perspectives2024
  3. 3A visual analytics tool for taxonomy-based trajectory data exploration2025
  4. 4Let's Speak Trajectories: A Vision to Use NLP Models for Trajectory Analysis Tasks2024 · 11 citations
  5. 5Analyzing Critical Regions in Human Trajectories: A Context‐Aware Framework for Deep Learning‐Based Movement Prediction2026