Utilizing External Knowledge to Enhance Location Prediction for Twitter/X Users in Low Resource Settings

Abstract

Accurate estimates of user location are important for many online services, including event detection, disaster management, and determining public opinion. Neural network-based techniques have proven to be highly effective in predicting user location. However, these models typically require a large amount of labeled training data, which can be difficult to obtain in real-world scenarios. In this article, we present two approaches to tackle the issue of limited training data when predicting city level location. First, we consider a self-supervised approach that trains a state-level model without labeled data and then integrate this knowledge into the training dataset used for city-level predictions. Second, we explore the option of increasing the number of training examples by utilizing external resources to generate synthetic users . Finally, we combine these two strategies, exploiting the benefits of both. We empirically evaluate our proposed techniques on multiple Twitter/X datasets and show that our models perform significantly better than the state-of-the-art with improvements of up to 6% for Acc@161 and 8% for F1 score.