Investigating the Neural Models for Irony Detection on Turkish Informal Texts

Cemek, Yesim
Cidecio, Cenk
Ozturk, Asli Umay
Cekinel, Recep Firat
Karagöz, Pınar
Irony is defined as the expression of one's meaning by using language that normally signifies the opposite, typically for humorous or emphatic effect. In the textual context, it can be considered as a specific type of opinion mining problem. However, due to the nature of the problem, it is generally more challenging to detect. Irony detection is useful to understand the semantics of a text. It also helps improving the accuracy of many other text mining tasks. In this paper, we study the irony detection problem on Turkish informal texts. In the literature there are several solutions proposed mostly for English texts. However, the number of studies on Turkish texts is very limited. The reason for using informal text is that ironic expressions are seen more frequently in informal communication media such as blogs, social media posts. Previously, performance of conventional supervised learning based solutions, such as Naive Bayes Classifier and SVM, on Turkish texts have been studied. In this work, we investigate the performance of neural network based models in comparison to conventional supervised learning models.


Automatic sense prediction of explicit discourse connectives in Turkish with the help of centering theory and morphosyntactic features
Çetin, Savaş; Zeyrek Bozşahin, Deniz; Department of Cognitive Sciences (2018)
Discourse connectives (and, but, however) are one of many means of keeping the discourse coherent. Discourse connectives are classified into groups based on their senses (expansion, contingency, etc.). They describe the semantic relationship of two discourse units. This study aims to build a machine learning system to predict the sense of explicit discourse connectives on the Turkish Discourse Bank data, which is manually gold-annotated. To do so, this study examines the effect of several features: i.e. tra...
Explicit evaluative comments on Turkish impoliteness Building a model of impoliteness2 on impoliteness1
Işık Güler, Hale (2009-07-02)
Many past politeness theories have been devised “at the expense of ignoring the lay person’s conception of politeness as revealed through their uses of the terms polite and impolite” (Culpeper, 2008, p.19). With the intention of using (im)politeness1 (lay) conceptualisations to inform the (scientific) theorizing of (im)politeness2, this study investigates the conceptualisation of ‘impoliteness’ (Tr. Kaba) for Turkish native speakers (hereafter, TNS). The data for the study comes from a number of sources: a ...
A Closer look at rumination in adolescence: investigation of possible risk factors and moderators
Akkaya, Sevinç; Kazak Berument, Sibel; Department of Psychology (2017)
Rumination is defined as excessive thinking about causes or consequences of negative event or dwelling on negative mood experienced. In the literature, two types of rumination (anger and depressive rumination) have been identified. Ruminative style thinking increases through adolescence and predicts several internalizing and externalizing problems. However, despite the evidence on consequences, the studies focusing on their developmental antecedents are limited. Therefore, the current study aims to investig...
Teacher educators’ emotions: a phenomenological study of university teachers’ emotional experiences
Calik, Basak; Yıldırım, Ali (null; 2018-09-07)
The term “affect” refers to non-cognitive constructs involving beliefs, moods and emotions (Boekaerts, 2007; Pekrun & Linnenbrick-Garcia, 2014) that could be crucial on teaching and learning outcomes. Among these constructs, emotions have either been neglected or considered to be destructive, primitive (Sutton & Wheatley, 2003), irrelevant and bothersome in scientific research (Frenzel & Stephens, 2013). However, in recent years this picture has changed drastically in many disciplines which placed emotions ...
Strawson on Intended Meaning and Context
AKMAN, VAROL; Alpaslan, Ferda Nur (1999-09-11)
Strawson proposed in the early seventies an attractive three-fold distinction regarding how context bears on the meaning of ‘what is said’ when a sentence is uttered. The proposed scheme is somewhat crude and, being aware of this aspect, Strawson himself raised various points to make it more adequate. In this paper, we review the scheme of Strawson, note his concerns, and add some of our own. However, our main point is to defend the essence of Strawson’s approach and to recommend it as a starting point for ...
Citation Formats
Y. Cemek, C. Cidecio, A. U. Ozturk, R. F. Cekinel, and P. Karagöz, “Investigating the Neural Models for Irony Detection on Turkish Informal Texts,” presented at the 28th Signal Processing and Communications Applications Conference (SIU), ELECTR NETWORK, 2020, Accessed: 00, 2021. [Online]. Available: