Show simple item record

dc.contributor.authorToroman, C.en_US
dc.contributor.authorCan, F.en_US
dc.date.accessioned2019-01-23T14:27:28Z
dc.date.available2019-01-23T14:27:28Z
dc.date.issued2015en_US
dc.identifier.issn0165-5515
dc.identifier.urihttp://hdl.handle.net/11693/48286
dc.description.abstractFront-page news selection is the task of finding important news articles in news aggregators. In this study, we examine news selection for public front pages using raw text, without any meta-attributes such as click counts. A novel algorithm is introduced by jointly considering the importance and diversity of selected news articles and the length of front pages. We estimate the importance of news, based on topic modelling, to provide the required diversity. Then we select important documents from important topics using a priority-based method that helps in fitting news content into the length of the front page. A user study is subsequently conducted to measure effectiveness and diversity, using our newly-generated annotation program. Annotation results show that up to seven of 10 news articles are important and up to nine of them are from different topics. Challenges in selecting public front-page news are addressed with an emphasis on future research.en_US
dc.language.isoEnglishen_US
dc.source.titleJournal of Information Scienceen_US
dc.relation.isversionofhttps://journals.sagepub.com/doi/pdf/10.1177/0165551515589069en_US
dc.subjectDiversityen_US
dc.subjectDocument importanceen_US
dc.subjectFront pageen_US
dc.subjectLDAen_US
dc.subjectNews selectionen_US
dc.subjectPriority schedulingen_US
dc.subjectTopic importanceen_US
dc.subjectTopic modellingen_US
dc.titleA front-page news-selection algorithm based on topic modelling using raw texten_US
dc.typeArticleen_US
dc.departmentDepartment of Computer Engineeringen_US
dc.citation.spage676en_US
dc.citation.epage685en_US
dc.citation.volumeNumber41en_US
dc.citation.issueNumber5en_US
dc.identifier.doi10.1177/0165551515589069en_US
dc.publisherSage Publications Ltd.en_US
dc.identifier.eissn1741-6485


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record