Yayın:
Feeling Analysis for Sadness and Happiness using Googlen-gram Database Googlen-gram Veritabanı ile Üzüntü ve Mutluluk Üzerine Duygu Analizi

dc.contributor.authorDonmez, Ilknur
dc.contributor.authorSonmez, Elena Battini
dc.date.accessioned2026-01-29T06:14:16Z
dc.date.issued2018-09-01
dc.description.abstractThe current era has been defined as “Digital Age” and “Information Age” since it is characterized by an exponential grow of data, generated by both human, i.e. social environments, and machine, i.e. Internet of things. The challenge is to convert “data” into “information”, by analyzing the data and discovering patterns hidden inside it. In this paper the two basic human feelings of Happiness and Sadness are extracted from a subset of Google n-grams corpus and analyzed. Google n-grams corpus is generated from millions of scanned books published between year 1500 and 2008; it can be considered as an indicator for human specific feature and behavior. Under the hypothesis that user's emotion can be extrapolated by the frequency of the corresponding emotional words, this study applies regression to predict the importance of the Happiness and Sadness emotional states in future years.Oz—“Bilgicagi”yada“dijitalcag”olarakad-landirilan21. yuzyildahayatimizinheralanindakullandigimizveri,elektronik olarak toplanabilmekte, islenebilmekte, analiz edilip kullanilabilmektedir.Buverilersosyalaglardan,kul-landigimiz araclardan (Nesnelerin Interneti), kamera sistem-leri ve tarayicilardan elde edilebilmektedir. Gunumuzde cig gibi buyuyen buyuk verinin analiz edilmesi ve veriyi bilgiye donusţurecek faydalikaliplarin bulunmasionemli bir konudur. Bu calismada “Mutluluk” ve “Huzun” gibi iki temel insan duygusu, Google n-gram derleminden faydalanilarak analiz edilmisţir. Bu derlem, 1500 ve 2008 yillariarasinda yayinlanan milyonlarca kitap taranarak elde edilmisţir. Insanlarin milyonlarca kitapta kullandigikelimelerden olusan bu derlem, insana ozguozellikvedavranisļaricinbir gosterge olarak dusunulebilir. Bu calisma, insan duygularinin, duygularina karsilik gelen kelimelerin sikligiyla tahmin edilebilecegi hipotezine dayanmaktadir. Makalemizde, gelecek yillardaki “Mutluluk” ve “Huzun” duygularinin kullanim sikliginitahmin etmek icin regresyon analizyontemlerikullanilmaktadir.
dc.description.urihttps://doi.org/10.1109/ubmk.2018.8566245
dc.description.urihttps://dx.doi.org/10.1109/ubmk.2018.8566245
dc.identifier.doi10.1109/ubmk.2018.8566245
dc.identifier.endpage60
dc.identifier.openairedoi_dedup___::a04add568f84251b69167df16b8e4b76
dc.identifier.orcid0000-0002-8344-1180
dc.identifier.orcid0000-0003-0090-984x
dc.identifier.startpage56
dc.identifier.urihttps://hdl.handle.net/11527/68804
dc.publisherIEEE
dc.relation.ispartof2018 3rd International Conference on Computer Science and Engineering (UBMK)
dc.titleFeeling Analysis for Sadness and Happiness using Googlen-gram Database Googlen-gram Veritabanı ile Üzüntü ve Mutluluk Üzerine Duygu Analizi
dc.typeArticle
dspace.entity.typePublication

Dosyalar

Koleksiyonlar