A Hierarchical Location Prediction Neural Network for Twitter User Geolocation

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 4732–4742, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 4732 A Hierarchical Location Prediction Neural Network for Twitter User Geolocation Binxuan Huang School of Computer Science Carnegie Mellon University binxuanh@cs.cmu.edu Kathleen M. Carley School of Computer Science Carnegie Mellon University kathleen.carley@cs.cmu.edu Abstract Accurate estimation of user location is impor- tant for many online services. Previous neural network based methods largely ignore the hi- erarchical structure among locations. In this paper, we propose a hierarchical location pre- diction neural network for Twitter user ge- olocation. Our model first predicts the home country for a user, then uses the country re- sult to guide the city-level prediction. In ad- dition, we employ a character-aware word em- bedding layer to overcome the noisy informa- tion in tweets. With the feature fusion layer, our model can accommodate various feature combinations and achieves state-of-the-art re- sults over three commonly used benchmarks under different feature settings. It not only im- proves the prediction accuracy but also greatly reduces the mean error distance. 1 Introduction Accurate estimation of user location is an impor- tant factor for many online services, such as rec- ommendation systems (Quercia et al., 2010), event detection (Sakaki et al., 2010), and disaster man- agement (Carley et al., 2016). Though internet ser- vice providers can directly obtain users’ location information from some explicit metadata like IP address and GPS signal, such private information is not available for third-party contributors. With this motivation, researchers have developed loca- tion prediction systems for various platforms, such as Wikipedia (Overell, 2009), Facebook (Back- strom et al., 2010), and Twitter (Han et al., 2012). In the case of Twitter, due to the sparsity of geotagged tweets (Graham et al., 2014) and the unreliability of user self-declared home location in profile (Hecht et al., 2011), there is a growing body of research trying to determine users’ loca- tions automatically. Various methods have been proposed for this purpose. They can be roughly di- vided into three categories. The first type consists of tweet text-based methods, where the word dis- tribution is used to estimate geolocations of users (Roller et al., 2012; Wing and Baldridge, 2011). In the second type, methods combining metadata features such as time zone and profile descrip- tion are developed to improve performance (Han et al., 2013). Network-based methods form the last type. Several studies have shown that incorporat- ing friends’ information is very useful for this task (Miura et al., 2017; Ebrahimi et al., 2018). Em- pirically, models enhanced with network informa- tion work better than the other two types, but they do not scale well to larger datasets (Rahimi et al., 2015a). In recent years, neural network based prediction methods have shown great success on this Twit- ter user geolocation prediction task (Rahimi et al., 2017; Miura et al., 2017). However, these neu- ral network based methods largely ignore the …

Content truncated to 500 words