Name
Abstract | ||
|---|---|---|
Predicting the locations of non-geotagged tweets is an active research area in geographical information retrieval. In this work, we propose a method to detect term co-occurrences in tweets that exhibit spatial clustering or dispersion tendency with significant deviation from the underlying single-term patterns, and use these co-occurrences to extend the feature space in probabilistic language models. We observe that using term pairs that spatially attract or repel each other yields significant increase in the accuracy of predicted locations. The method we propose relies purely on statistical approaches and spatial point patterns without using external data sources or gazetteers. Evaluations conducted on a large set of multilingual tweets indicate higher accuracy than the existing state-of-the-art methods. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1007/978-3-319-76941-7_37 | ADVANCES IN INFORMATION RETRIEVAL (ECIR 2018) |
Keywords | Field | DocType |
Location prediction,Tweet localization,Spatial point patterns,Feature extraction | Spatial analysis,Data mining,Feature vector,Computer science,Feature extraction,Probabilistic logic,Location prediction,Cluster analysis,Language model | Conference |
Volume | ISSN | Citations |
10772 | 0302-9743 | 1 |
PageRank | References | Authors |
0.36 | 15 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Özer Özdikiş | 1 | 50 | 5.49 |
| Heri Ramampiaro | 2 | 154 | 20.46 |
| Kjetil Nørvåg | 3 | 1311 | 79.26 |