Discovering topical interactions in text-based cascades using hidden Markov Hawkes processes

Show simple item record

dc.contributor.author Bedathur, Srikanta
dc.contributor.author Bhattacharya, Indrajit
dc.contributor.author Choudhari, Jayesh
dc.contributor.author Dasgupta, Anirban
dc.date.accessioned 2018-09-28T07:03:09Z
dc.date.available 2018-09-28T07:03:09Z
dc.date.issued 2018-09
dc.identifier.citation Bedathur, Srikanta; Bhattacharya, Indrajit; Choudhari, Jayesh and Dasgupta, Anirban, "Discovering topical interactions in text-based cascades using hidden Markov Hawkes processes", arXiv, Cornell University Library, DOI: arXiv:1809.04487, Sep. 2018. en_US
dc.identifier.uri https://arxiv.org/abs/1809.04487
dc.identifier.uri https://repository.iitgn.ac.in/handle/123456789/3913
dc.description.abstract Social media conversations unfold based on complex interactions between users, topics and time. While recent models have been proposed to capture network strengths between users, users' topical preferences and temporal patterns between posting and response times, interaction patterns between topics has not been studied. We propose the Hidden Markov Hawkes Process (HMHP) that incorporates topical Markov Chains within Hawkes processes to jointly model topical interactions along with user-user and user-topic patterns. We propose a Gibbs sampling algorithm for HMHP that jointly infers the network strengths, diffusion paths, the topics of the posts as well as the topic-topic interactions. We show using experiments on real and semi-synthetic data that HMHP is able to generalize better and recover the network strengths, topics and diffusion paths more accurately than state-of-the-art baselines. More interestingly, HMHP finds insightful interactions between topics in real tweets which no existing model is able to do.
dc.description.statementofresponsibility by Srikanta Bedathur, Indrajit Bhattacharya, Jayesh Choudhari and Anirban Dasgupta
dc.language.iso en en_US
dc.publisher Cornell University Library en_US
dc.subject Machine Learning en_US
dc.subject Machine Learning en_US
dc.title Discovering topical interactions in text-based cascades using hidden Markov Hawkes processes en_US
dc.type Article en_US


Files in this item

Files Size Format View

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record

Search Digital Repository


Browse

My Account