Research map / Graph learning / Graph algorithms and clustering
Location-Sensitive User Profiling Using Crowdsourced Labels
Wei Niu, James Caverlee, Haokai Lu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace general folksonomy with location-sensitive folksonomy (ablation) | SC-MC · profile tag prediction | P@5: 0.571 -> 0.677 | Improved |
| replace general folksonomy with location-sensitive folksonomy (ablation) | MS-MC · profile tag prediction | P@5: 0.571 -> 0.663 | Improved |
| replace general folksonomy with location-sensitive folksonomy (ablation) | SC-COS · profile tag prediction | P@5: 0.531 -> 0.663 | Improved |
| replace general folksonomy with location-sensitive folksonomy (ablation) | SC-RBF · profile tag prediction | AF: 12.0 -> 10.1 | Mixed |
| use learning to rank instead of overall popularity ranking | candidate tag ranking · Twitter list profiling | P@1: 0.607 -> 0.763 | Improved |
| use learning to rank instead of Sumsimilarity ranking | candidate tag ranking · Twitter list profiling | AF@5: 18.5 -> 19.2 | Improved |
| use modified confidence similarity instead of PMI | SC folksonomy · profile tag prediction | P@5: 0.362 -> 0.677 | Improved |
| use structure conservation cost instead of maximum similarity (ablation) | SC-COS · profile tag prediction | P@5: 0.656 -> 0.663 | Improved |
| use structure conservation cost instead of maximum similarity (ablation) | SC-MC · profile tag prediction | P@1: 0.754 -> 0.763 | No clear effect |
| use location-sensitive folksonomy profiling instead of CF-KNN | LS Folk. · Twitter list profiling | P@5: 0.542 -> 0.677 | Improved |
| use location-sensitive folksonomy profiling instead of LBPR | LS Folk. · Twitter list profiling | P@5: 0.650 -> 0.677 | Improved |
| use location-sensitive folksonomy profiling instead of LABPR | LS Folk. · Twitter list profiling | P@1: 0.771 -> 0.763 | No clear effect |
Closest papers by meaning
- College Towns, Vacation Spots, and Tech Hubs: Using Geo-Social Media to Model and Compare Locations (AAAI 2016 · similarity 0.86)
- POI2Vec: Geographical Latent Representation for Predicting Future Visitors (AAAI 2017 · similarity 0.84)
- Minimizing User Involvement for Learning Human Mobility Patterns from Location Traces (AAAI 2016 · similarity 0.83)
- Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation (AAAI 2025 · similarity 0.82)
- GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model (AAAI 2025 · similarity 0.81)
- KFNN: K-Free Nearest Neighbor For Crowdsourcing (NeurIPS 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
