Emotion analysis on Turkish tweets


Thesis Type: Postgraduate

Institution Of The Thesis: Orta Doğu Teknik Üniversitesi, Faculty of Engineering, Department of Computer Engineering, Turkey

Approval Date: 2014

Student: SİNEM DEMİRCİ

Co-Supervisor: PINAR KARAGÖZ, İSMAİL HAKKI TOROSLU

Abstract:

Automatically detecting emotions in micro-blogs is a new research area which gains importance with the rapid growth of the micro-blogs in the last few years. Mining emotions in micro-blogs has some practical uses which can improve human-computer interaction. As opposed to regular text used in text mining studies, micro-blog entries are short and not well-formed enough to process directly. Also there are some special usages, symbols and conveniences used in micro-blogs which may greatly influence the affect in the text. Therefore, in this thesis, a general framework which considers those deficiencies is suggested and a new data set of Turkish tweets for emotion analysis is constructed.