KAUST DepartmentComputer Science Program
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Online Publication Date2018-07-19
Print Publication Date2018
Permanent link to this recordhttp://hdl.handle.net/10754/628781
MetadataShow full item record
AbstractIn 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.
CitationLiang S, Zhang X, Ren Z, Kanoulas E (2018) Dynamic Embeddings for User Profiling in Twitter. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD ’18. Available: http://dx.doi.org/10.1145/3219819.3220043.
SponsorsThis work was supported by the King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
JournalProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18
Conference/Event name24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018