A New Feature Selection Method for Sentiment Analysis of Turkish Reviews

Basit Öğe Kaydı
dc.contributor.authorParlar, Tuba
dc.contributor.authorOzel, Selma Ayse
dc.date.accessioned2024-09-18T20:56:55Z
dc.date.available2024-09-18T20:56:55Z
dc.date.issued2016
dc.departmentHatay Mustafa Kemal Üniversitesien_US
dc.descriptionInternational Symposium on Innovations in Intelligent Systems and Applications (INISTA) -- AUG 02-05, 2016 -- Sinaia, ROMANIAen_US
dc.description.abstractSentiment analysis identifies people's opinions, sentiments about a product, a service, an organization, or an event. Because of huge review documents, researchers explore different feature selection methods that aim to eliminate non valuable features. However, not much work has been done on feature selection methods for sentiment analysis of Turkish reviews. In this study, we propose a new feature selection method called Query Expansion Ranking that is based on query expansion term weighting methods, which are used in Information Retrieval domain to determine the most valuable terms for query expansion. We compare Query Expansion Ranking with Chi Square method, which is a well-known and successful feature selector, and Document Frequency Difference which is a feature selection method proposed for sentiment analysis of English reviews. Experiments are conducted on four Turkish product review datasets that are book, DVDs, electronics, and kitchen appliances reviews by using a supervised machine learning classification method, namely Naive Bayes Multinomial classifier. We show that our new proposed method improves sentiment analysis performance in terms of classification accuracy and time. In the experimental evaluation, we also show that our new feature selector improves classification accuracy better than Chi Square, and Document Frequency Difference methods.en_US
dc.description.sponsorshipIEEE,IDS Res Grp,Fac Automat Comp & Elect, Dept Comp & Informat Technol,Fac Econ & Business Adm, Dept Stat & Business Informat,Fac Math & Nat Sci, Dept Informat,Univ Craiovaen_US
dc.identifier.isbn978-1-4673-9910-4
dc.identifier.scopus2-s2.0-84992092170en_US
dc.identifier.scopusqualityN/Aen_US
dc.identifier.urihttps://hdl.handle.net/20.500.12483/12185
dc.identifier.wosWOS:000386824000014en_US
dc.identifier.wosqualityN/Aen_US
dc.indekslendigikaynakWeb of Scienceen_US
dc.indekslendigikaynakScopusen_US
dc.language.isoenen_US
dc.publisherIeeeen_US
dc.relation.ispartofProceedings of The 2016 International Symposium on Innovations in Intelligent Systems and Applications (Inista)en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.rightsinfo:eu-repo/semantics/closedAccessen_US
dc.subjectSentiment analysisen_US
dc.subjectfeature selectionen_US
dc.subjecttext classificationen_US
dc.titleA New Feature Selection Method for Sentiment Analysis of Turkish Reviewsen_US
dc.typeConference Objecten_US

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
[ N/A ]
İsim:
Tam Metin / Full Text
Boyut:
228.58 KB
Biçim:
Adobe Portable Document Format
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Scopus İndeksli Yayınlar Koleksiyonu