Show simple item record

dc.contributor.authorLiang, Shangsong
dc.contributor.authorZhang, Xiangliang
dc.contributor.authorRen, Zhaochun
dc.contributor.authorKanoulas, Evangelos
dc.date.accessioned2018-09-26T13:28:58Z
dc.date.available2018-09-26T13:28:58Z
dc.date.issued2018-07-19
dc.identifier.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.
dc.identifier.doi10.1145/3219819.3220043
dc.identifier.urihttp://hdl.handle.net/10754/628781
dc.description.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.
dc.description.sponsorshipThis work was supported by the King Abdullah University of Science and Technology (KAUST), Saudi Arabia.
dc.publisherAssociation for Computing Machinery (ACM)
dc.relation.urlhttps://dl.acm.org/citation.cfm?doid=3219819.3220043
dc.rightsArchived with thanks to Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18
dc.subjectDynamic model
dc.subjectProfiling
dc.subjectWord embeddings
dc.titleDynamic Embeddings for User Profiling in Twitter
dc.typeConference Paper
dc.contributor.departmentComputer Science Program
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
dc.identifier.journalProceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining - KDD '18
dc.conference.date2018-08-19 to 2018-08-23
dc.conference.name24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2018
dc.conference.locationLondon, GBR
dc.eprint.versionPublisher's Version/PDF
dc.contributor.institutionData Science Lab, JD.com, Beijing, China
dc.contributor.institutionUniversity of Amsterdam, Amsterdam, Netherlands
kaust.personLiang, Shangsong
kaust.personZhang, Xiangliang
refterms.dateFOA2018-09-27T07:46:23Z
dc.date.published-online2018-07-19
dc.date.published-print2018


Files in this item

Thumbnail
Name:
p1764-liang.pdf
Size:
1.410Mb
Format:
PDF
Description:
Published version

This item appears in the following Collection(s)

Show simple item record