Text-Based Twitter User Geolocation Prediction

• Published in: The Journal of artificial intelligence research 2014-01, Vol.49, p.451-500
• Main Authors: Han, B., Cook, P., Baldwin, T.
• Format: Article
• Language: English
• Subjects: Artificial intelligence; Geographical locations
• ISSN: 1076-9757; 1076-9757; 1943-5037
• DOI: 10.1613/jair.4200

Geographical location is vital to geospatial applications like local search and event detection. In this paper, we investigate and improve on the task of text-based geolocation prediction of Twitter users. Previous studies on this topic have typically assumed that geographical references (e.g., gazetteer terms, dialectal words) in a text are indicative of its author’s location. However, these references are often buried in informal, ungrammatical, and multilingual data, and are therefore non-trivial to identify and exploit. We present an integrated geolocation prediction framework and investigate what factors impact on prediction accuracy. First, we evaluate a range of feature selection methods to obtain “location indicative words”. We then evaluate the impact of non-geotagged tweets, language, and user-declared metadata on geolocation prediction. In addition, we evaluate the impact of temporal variance on model generalisation, and discuss how users differ in terms of their geolocatability. We achieve state-of-the-art results for the text-based Twitter user geolocation task, and also provide the most extensive exploration of the task to date. Our findings provide valuable insights into the design of robust, practical text-based geolocation prediction systems.