Deep sentiment analysis: a case study on stemmed Turkish Twitter data

Basit Öğe Kaydı
dc.authorid0000-0001-8776-3032
dc.contributor.authorShehu, Harisu Abdullahi
dc.contributor.authorSharif, Md. Haidar
dc.contributor.authorSharif, Md. Haris Uddin
dc.contributor.authorDatta, Ripon
dc.contributor.authorTokat, Sezai
dc.contributor.authorUyaver, Şahin
dc.contributor.authorKusetoğulları, Hüseyin
dc.contributor.authorRamadan, Rabie A.
dc.date.accessioned2021-04-29T09:05:28Z
dc.date.available2021-04-29T09:05:28Z
dc.date.issued2021
dc.departmentTAÜ, Fen Fakültesi, Enerji Bilimi ve Teknolojileri Bölümüen_US
dc.description.abstractSentiment analysis using stemmed Twitter data from various languages is an emerging research topic. In this paper, we address three data augmentation techniques namely Shift, Shuffle, and Hybrid to increase the size of the training data; and then we use three key types of deep learning (DL) models namely recurrent neural network (RNN), convolution neural network (CNN), and hierarchical attention network (HAN) to classify the stemmed Turkish Twitter data for sentiment analysis. The performance of these DL models has been compared with the existing traditional machine learning (TML) models. The performance of TML models has been affected negatively by the stemmed data, but the performance of DL models has been improved greatly with the utilization of the augmentation techniques. Based on the simulation, experimental, and statistical results analysis deeming identical datasets, it has been concluded that the TML models outperform the DL models with respect to both training-time (TTM) and runtime (RTM) complexities of the algorithms; but the DL models outperform the TML models with respect to the most important performance factors as well as the average performance rankings.
dc.identifier.citationShehu, H. A., Sharif, M. H., Sharif, M. H. U., Datta, R., Tokat, S., Uyaver, Ş., ... & Ramadan, R. A. (2021). Deep Sentiment Analysis: A Case Study on Stemmed Turkish Twitter Data. IEEE Access, 9, 56836-56854.
dc.identifier.doi10.1109/ACCESS.2021.3071393
dc.identifier.endpage56854en_US
dc.identifier.scopus2-s2.0-85103885312
dc.identifier.scopusqualityN/A
dc.identifier.startpage56836en_US
dc.identifier.urihttps://hdl.handle.net/20.500.12846/583
dc.identifier.volume9en_US
dc.identifier.wosWOS:000641943600001
dc.identifier.wosqualityQ2
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorUyaver, Şahin
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartofIEEE Access
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subjectSocial networkingen_US
dc.subjectBlogsen_US
dc.subjectSentiment analysisen_US
dc.subjectSosyal ağen_US
dc.subjectBloglaren_US
dc.subjectDuygu analizien_US
dc.subjectSoziales netzwerken_US
dc.subjectStimmungsanalyseen_US
dc.titleDeep sentiment analysis: a case study on stemmed Turkish Twitter data
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim
İsim:
09395633.pdf
Boyut:
2.75 MB
Biçim:
Adobe Portable Document Format
Açıklama:
Tam Metin / Full Text
İndir
Lisans paketi
Listeleniyor 1 - 1 / 1
[ X ]
İsim:
license.txt
Boyut:
1.44 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
İndir

Koleksiyon

WoS İndeksli Yayınlar Koleksiyonu
Enerji Bilimi ve Teknolojileri
Scopus İndeksli Yayınlar Koleksiyonu