Please use this identifier to cite or link to this item: https://hdl.handle.net/11147/11267
Full metadata record
DC FieldValueLanguage
dc.contributor.authorJabrayilzade, Elgün-
dc.contributor.authorPoyraz Arslan, Algın-
dc.contributor.authorPara, Hasan-
dc.contributor.authorPolatbilek, Ozan-
dc.contributor.authorSezerer, Erhan-
dc.contributor.authorTekir, Selma-
dc.date.accessioned2021-11-06T09:27:14Z-
dc.date.available2021-11-06T09:27:14Z-
dc.date.issued2020-
dc.identifier.isbn9781728172064-
dc.identifier.urihttp://doi.org/10.1109/SIU49456.2020.9302027-
dc.identifier.urihttps://hdl.handle.net/11147/11267-
dc.description28th Signal Processing and Communications Applications Conference, SIU 2020 -- 5 October 2020 through 7 October 2020en_US
dc.description.abstractStatistical topic modeling aims to assign topics to documents in an unsupervised way. Latent Dirichlet Allocation (LDA) is the standard model for topic modeling. It shows good performance on document collections, documents being relatively long texts but it has poor performance on short texts. Topic modeling on short texts is on the rise due to the potential of social media. Thus, approaches that are able to nd topics on short texts as well as long texts are sought. However, there is a lack of datasets that include both long and short texts which have the same ground-truth categories. In this work, we release a Turkish movie dataset which contain both short lm descriptions and long subscripts where lm genre can be considered as topic. Furthermore, we provide multi-label movie genre classication results using a Feed Forward Neural Network (FFNN) taking LDA document-topic or Doc2Vec dense representations. © 2020 IEEE.en_US
dc.language.isotren_US
dc.publisherInstitute of Electrical and Electronics Engineersen_US
dc.relation.ispartof2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedingsen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDoc2Vecen_US
dc.subjectFeed-forward neural networksen_US
dc.subjectLDAen_US
dc.subjectLong text classicationen_US
dc.subjectShort text classicationen_US
dc.subjectText classication dataseten_US
dc.titleÇok-etiketli film türü sınıflandırması için Türkçe konu modellemesi veri kümesien_US
dc.title.alternativeA Turkish topic modeling dataset for multi-label classification of movie genreen_US
dc.typeConference Objecten_US
dc.departmentIzmir Institute of Technology. Computer Engineeringen_US
dc.identifier.wosWOS:000653136100001-
dc.identifier.scopus2-s2.0-85100310802en_US
dc.relation.publicationcategoryKonferans Öğesi - Uluslararası - Kurum Öğretim Elemanıen_US
dc.identifier.doi10.1109/SIU49456.2020.9302027-
item.openairecristypehttp://purl.org/coar/resource_type/c_18cf-
item.cerifentitytypePublications-
item.fulltextWith Fulltext-
item.grantfulltextopen-
item.openairetypeConference Object-
item.languageiso639-1tr-
crisitem.author.dept03.04. Department of Computer Engineering-
Appears in Collections:Computer Engineering / Bilgisayar Mühendisliği
Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
WoS İndeksli Yayınlar Koleksiyonu / WoS Indexed Publications Collection
Files in This Item:
File SizeFormat 
A_Turkish_Topic.pdf223.29 kBAdobe PDFView/Open
Show simple item record

CORE Recommender

Page view(s)

3,502
checked on Aug 15, 2022

Download(s)

34
checked on Aug 15, 2022

Google ScholarTM

Check

Altmetric


Items in GCRIS Repository are protected by copyright, with all rights reserved, unless otherwise indicated.