Show simple item record

dc.contributor.authorSotiropoulos, Konstantinosen_US
dc.contributor.authorByers, John W.en_US
dc.contributor.authorPratikakis, Polyviosen_US
dc.contributor.authorTsourakakis, Charalampos E.en_US
dc.date.accessioned2020-05-06T19:37:22Z
dc.date.available2020-05-06T19:37:22Z
dc.date.issued2019-09
dc.identifier.citationKonstantinos Sotiropoulos, John W Byers, Polyvios Pratikakis, Charalampos E Tsourakakis. 2019. "TwitterMancer: Predicting User Interactions on Twitter." 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton). 2019-09-24 - 2019-09-27. https://doi.org/10.1109/allerton.2019.8919702
dc.identifier.urihttps://hdl.handle.net/2144/40641
dc.description.abstractThis paper investigates the interplay between different types of user interactions on Twitter, with respect to predicting missing or unseen interactions. For example, given a set of retweet interactions between Twitter users, how accurately can we predict reply interactions? Is it more difficult to predict retweet or quote interactions between a pair of accounts? Also, how important is time locality, and which features of interaction patterns are most important to enable accurate prediction of specific Twitter interactions? Our empirical study of Twitter interactions contributes initial answers to these questions.We have crawled an extensive data set of Greek-speaking Twitter accounts and their follow, quote, retweet, reply interactions over a period of a month. We find we can accurately predict many interactions of Twitter users. Interestingly, the most predictive features vary with the user profiles, and are not the same across all users. For example, for a pair of users that interact with a large number of other Twitter users, we find that certain “higher-dimensional” triads, i.e., triads that involve multiple types of interactions, are very informative, whereas for less active Twitter users, certain in-degrees and out-degrees play a major role. Finally, we provide various other insights on Twitter user behavior. Our code and data are available at https://github.com/twittermancer/.en_US
dc.language.isoen_US
dc.publisherIEEEen_US
dc.relation.ispartof2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
dc.subjectTwitteren_US
dc.subjectMachine learningen_US
dc.subjectNonhomogeneous mediaen_US
dc.subjectLogisticsen_US
dc.subjectFeature extractionen_US
dc.subjectCorrelationen_US
dc.subjectLearning (artificial intelligence)en_US
dc.subjectSocial networking (online)en_US
dc.subjectUser profilesen_US
dc.subjectActive Twitter usersen_US
dc.subjectTwitter user behavioren_US
dc.subjectPredicting user interactionsen_US
dc.subjectPredicting missing interactionsen_US
dc.subjectUnseen interactionsen_US
dc.subjectRetweet interactionsen_US
dc.subjectReply interactionsen_US
dc.subjectInteraction patternsen_US
dc.subjectSpecific Twitter interactionsen_US
dc.subjectTwitter accountsen_US
dc.subjectPredictive featuresen_US
dc.subjectGraph miningen_US
dc.subjectMachine learningen_US
dc.subjectSocial mediaen_US
dc.subjectSocial networksen_US
dc.titleTwitterMancer: predicting user interactions on Twitteren_US
dc.title.alternativeTwitterMancer: predicting interactions on Twitter accuratelyen_US
dc.typeConference materialsen_US
dc.description.versionAccepted manuscripten_US
dc.identifier.doi10.1109/allerton.2019.8919702
pubs.elements-sourcecrossrefen_US
pubs.notesEmbargo: Not knownen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, College of Arts & Sciencesen_US
pubs.organisational-groupBoston University, College of Arts & Sciences, Department of Computer Scienceen_US
pubs.publication-statusPublisheden_US
dc.identifier.mycv540398


This item appears in the following Collection(s)

Show simple item record