A Unified Neural Network Model for Geolocating

Abstract

Locations of social media users are important to many applications such as rapid disaster response, targeted advertisement, and news recommendation. However, many users do not share their exact geographical coordinates due to reasons such as privacy concerns. The lack of explicit location information has motivated a growing body of research in recent years looking at different automatic ways of determining the user's primary location. In this paper, we propose a unified user geolocation method which relies on a fusion of neural networks. Our joint model incorporates different types of available information including tweet text, user network, and metadata to predict users' locations. Moreover, we utilize a bidirectional LSTM network augmented with an attention mechanism to identify the most location indicative words in textual content of tweets. The experiments demonstrate that our approach achieves state-of-the-art performance over two Twitter benchmark geolocation datasets. We also conduct an ablation study to evaluate the contribution of each type of information in user geolocation performance.

A Hierarchical Location Prediction Neural Network for Twitter User Geolocation

“…integrate text and user profile metadata into a single model using convolutional neural networks, and their experiments show superior performance over stacked naive Bayes classifiers. Miura et al (2017); Ebrahimi et al (2018) incorporate user network connection information into their neural models, where they use network embeddings to represent users in a social network. also uses text and network feature together, but their approach is based on graph convolutional neural networks.…”

Dense Node Representation for Geolocation

“…Similarly to our study, Rahimi et al (2015) exploited the mentions, even though they used them to build undirected graphs. Ebrahimi et al (2017Ebrahimi et al ( , 2018 also used mentions to create an undirected graph, that they pruned and fed into an embedding layer followed by an attention mechanism, in order to create a network representation.…”

“…These works represent the state-of-the-art benchmark with respect to the implementation of network views in the models. Other models (Ebrahimi et al, 2017(Ebrahimi et al, , 2018Do et al, 2018) also include metadata or other source of information.…”

“…Even though social media allows for worldwide connections, most people have a larger number of connections with people who live close-by (from their school, workplace, or friend network). The most successful predictive models are therefore architectures that combine these different kinds of inputs (Rahimi et al, 2018;Ebrahimi et al, 2018).…”

Identifying Linguistic Areas for Geolocation

“…Most works use deep learning techniques for classification (Miura et al, 2016). Often, they include multi-view models, considering different sources (Miura et al, 2017;Lau et al, 2017;Ebrahimi et al, 2018;Fornaciari and Hovy, 2019a). In particular, Lau et al (2017) implemented a multi-channel convolutional network, structurally similar to our model.…”