A Deep Metric Learning Approach to Account Linking
This addresses account linking for social media platforms, enabling automated identity management, though it appears incremental as it adapts deep metric learning to this specific task.
The paper tackles the problem of linking social media accounts belonging to the same author by learning an embedding from content and metadata without human-annotated training data. It achieves high linking accuracy with small samples from unseen accounts, outperforming competitive baselines.
We consider the task of linking social media accounts that belong to the same author in an automated fashion on the basis of the content and metadata of their corresponding document streams. We focus on learning an embedding that maps variable-sized samples of user activity -- ranging from single posts to entire months of activity -- to a vector space, where samples by the same author map to nearby points. The approach does not require human-annotated data for training purposes, which allows us to leverage large amounts of social media content. The proposed model outperforms several competitive baselines under a novel evaluation framework modeled after established recognition benchmarks in other domains. Our method achieves high linking accuracy, even with small samples from accounts not seen at training time, a prerequisite for practical applications of the proposed linking framework.