Dynamic Embeddings For User Profiling In Twitter

Authors:
Shangsong Liang King Abdullah University of Science and Technology
Xiangliang Zhang King Abdullah University of Science and Technology
Zhaochun Ren JD.com
Evangelos Kanoulas University of Amsterdam

Introduction:

In this paper, the authors study the problem of dynamic user profiling in Twitter. They address the problem by proposing a dynamic user and word embedding model (DUWE), a scalable black-box variational inference algorithm, and a streaming keyword diversification model (SKDM).

Abstract:

In this paper, we study the problem of dynamic user profiling in Twitter. We address the problem by proposing a dynamic user and word embedding model (DUWE), a scalable black-box variational inference algorithm, and a streaming keyword diversification model (SKDM). DUWE dynamically tracks the semantic representations of users and words over time and models their embeddings in the same space so that their similarities can be effectively measured. Our inference algorithm works with a convex objective function that ensures the robustness of the learnt embeddings. SKDM aims at retrieving top-K relevant and diversified keywords to profile users’ dynamic interests. Experiments on a Twitter dataset demonstrate that our proposed embedding algorithms outperform state-of-the-art non-dynamic and dynamic embedding and topic models.

You may want to know: