Discover Your Social Identity from What You Tweet: a Content Based Approach
This work addresses identity classification for social media users, which is incremental as it builds on existing content-based methods with a new model and transfer approach.
The paper tackles the problem of classifying Twitter users based on their social identities from tweet content, proposing a hierarchical self-attention neural network that significantly outperforms baselines and a transfer learning scheme that improves performance while reducing the need for labeled data.
An identity denotes the role an individual or a group plays in highly differentiated contemporary societies. In this paper, our goal is to classify Twitter users based on their role identities. We first collect a coarse-grained public figure dataset automatically, then manually label a more fine-grained identity dataset. We propose a hierarchical self-attention neural network for Twitter user role identity classification. Our experiments demonstrate that the proposed model significantly outperforms multiple baselines. We further propose a transfer learning scheme that improves our model's performance by a large margin. Such transfer learning also greatly reduces the need for a large amount of human labeled data.