Dynamic Embeddings for User Profiling in Twitter

Shangsong Liang, Xiangliang Zhang, Zhaochun Ren, Evangelos Kanoulas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

39 Scopus citations


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.
Original languageEnglish (US)
Title of host publicationProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18
PublisherAssociation for Computing Machinery (ACM)
Number of pages10
ISBN (Print)9781450355520
StatePublished - Jul 19 2018


Dive into the research topics of 'Dynamic Embeddings for User Profiling in Twitter'. Together they form a unique fingerprint.

Cite this