High-resolution home location prediction from Twitter activities using consensus deep learning

Meysam Ghaffari, Ashok Srinivasan, Xiuwen Liu, Shayok Chakraborty

Abstract: Timely and high-resolution estimates of the home locations of a sufficiently large subset of the population are critical for effective disaster response and public health intervention, but this is still an open problem. Conventional data sources, such as census and surveys, have a substantial time lag and cannot capture seasonal trends. Recently, social media data has been exploited to address this problem by leveraging its large user-base and real-time nature. However, inherent sparsity and noise, along with large estimation uncertainty in home locations, have limited their effectiveness. Consequently, much of previous research has aimed only at a coarse spatial resolution, with accuracy being limited for high-resolution methods. In this paper, we develop a consensus deep-learning solution that uses two deep neural networks to deal with sparse and noisy social media data. In the first step, high accuracy is achieved by implementing a deep neural network that has more balanced home location candidates, using batch normalization, and duplicating home location records. We obtained over 92% accuracy for large subsets on a commonly used dataset. Compared to other high-resolution methods, our approach yields up to 60% error reduction by reducing high-resolution home prediction error from over 21% to less than 8%. Systematic comparisons show that our method gives the highest accuracy both for the entire sample and for subsets. Evaluation on a real-world public health problem further validates the effectiveness of our approach.