Loading...
Please wait, while we are loading the content...
Similar Documents
A stacking-based approach to twitter user geolocation prediction (2013)
| Content Provider | CiteSeerX |
|---|---|
| Author | Han, Bo Cook, Paul |
| Description | We implement a city-level geolocation prediction system for Twitter users. The system infers a user’s location based on both tweet text and user-declared metadata using a stacking approach. We demonstrate that the stacking method substantially outperforms benchmark methods, achieving 49 % accuracy on a benchmark dataset. We further evaluate our method on a recent crawl of Twitter data to investigate the impact of temporal factors on model generalisation. Our results suggest that user-declared location metadata is more sensitive to temporal change than the text of Twitter messages. We also describe two ways of accessing/demoing our system. 1 |
| File Format | |
| Language | English |
| Publisher Date | 2013-01-01 |
| Publisher Institution | In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (ACL 2013): System Demonstrations |
| Access Restriction | Open |
| Subject Keyword | User-declared Location Metadata Temporal Factor Temporal Change User Geolocation Prediction Benchmark Method Benchmark Dataset Twitter Message Tweet Text Twitter Data City-level Geolocation Prediction System Twitter User Model Generalisation User-declared Metadata Stacking Approach Stacking-based Approach Recent Crawl User Location |
| Content Type | Text |
| Resource Type | Article |
