TwitterMancer: predicting user interactions on Twitter
dc.contributor.author | Sotiropoulos, Konstantinos | en_US |
dc.contributor.author | Byers, John W. | en_US |
dc.contributor.author | Pratikakis, Polyvios | en_US |
dc.contributor.author | Tsourakakis, Charalampos E. | en_US |
dc.date.accessioned | 2020-05-06T19:37:22Z | |
dc.date.available | 2020-05-06T19:37:22Z | |
dc.date.issued | 2019-09 | |
dc.identifier.citation | Konstantinos 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.uri | https://hdl.handle.net/2144/40641 | |
dc.description.abstract | This 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.iso | en_US | |
dc.publisher | IEEE | en_US |
dc.relation.ispartof | 2019 57th Annual Allerton Conference on Communication, Control, and Computing (Allerton) | |
dc.subject | en_US | |
dc.subject | Machine learning | en_US |
dc.subject | Nonhomogeneous media | en_US |
dc.subject | Logistics | en_US |
dc.subject | Feature extraction | en_US |
dc.subject | Correlation | en_US |
dc.subject | Learning (artificial intelligence) | en_US |
dc.subject | Social networking (online) | en_US |
dc.subject | User profiles | en_US |
dc.subject | Active Twitter users | en_US |
dc.subject | Twitter user behavior | en_US |
dc.subject | Predicting user interactions | en_US |
dc.subject | Predicting missing interactions | en_US |
dc.subject | Unseen interactions | en_US |
dc.subject | Retweet interactions | en_US |
dc.subject | Reply interactions | en_US |
dc.subject | Interaction patterns | en_US |
dc.subject | Specific Twitter interactions | en_US |
dc.subject | Twitter accounts | en_US |
dc.subject | Predictive features | en_US |
dc.subject | Graph mining | en_US |
dc.subject | Machine learning | en_US |
dc.subject | Social media | en_US |
dc.subject | Social networks | en_US |
dc.title | TwitterMancer: predicting user interactions on Twitter | en_US |
dc.title.alternative | TwitterMancer: predicting interactions on Twitter accurately | en_US |
dc.type | Conference materials | en_US |
dc.description.version | Accepted manuscript | en_US |
dc.identifier.doi | 10.1109/allerton.2019.8919702 | |
pubs.elements-source | crossref | en_US |
pubs.notes | Embargo: Not known | en_US |
pubs.organisational-group | Boston University | en_US |
pubs.organisational-group | Boston University, College of Arts & Sciences | en_US |
pubs.organisational-group | Boston University, College of Arts & Sciences, Department of Computer Science | en_US |
pubs.publication-status | Published | en_US |
dc.identifier.mycv | 540398 |
This item appears in the following Collection(s)