{"title":"Interest classification of Twitter users using Wikipedia","authors":"Kwan Hui Lim, A. Datta","doi":"10.1145/2491055.2491078","DOIUrl":null,"url":null,"abstract":"We present a framework for (automatically) classifying the relative interests of Twitter users using information from Wikipedia. Our proposed framework first uses Wikipedia to automatically classify a user's celebrity followings into various interest categories, followed by determining the relative interests of the user with a weighting compared to his/her other interests. Our preliminary evaluation on Twitter shows that this framework is able to correctly classify users' interests and that these users frequently converse about topics that reflect both their (detected) interest and a related real-life event.","PeriodicalId":155413,"journal":{"name":"Proceedings of the 9th International Symposium on Open Collaboration","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-08-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"35","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 9th International Symposium on Open Collaboration","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/2491055.2491078","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 35
Abstract
We present a framework for (automatically) classifying the relative interests of Twitter users using information from Wikipedia. Our proposed framework first uses Wikipedia to automatically classify a user's celebrity followings into various interest categories, followed by determining the relative interests of the user with a weighting compared to his/her other interests. Our preliminary evaluation on Twitter shows that this framework is able to correctly classify users' interests and that these users frequently converse about topics that reflect both their (detected) interest and a related real-life event.