Emotion analysis of Turkish texts by using machine learning methods

Download

index.pdf

Date

2012

Author

Boynukalın, Zeynep

Metadata

Show full item record

Item Usage Stats

949
views

308
downloads

Automatically analysing the emotion in texts is in increasing interest in today’s research fields. The aim is to develop a machine that can detect type of user’s emotion from his/her text. Emotion classification of English texts is studied by several researchers and promising results are achieved. In this thesis, an emotion classification study on Turkish texts is introduced. To the best of our knowledge, this is the first study on emotion analysis of Turkish texts. In English there exists some well-defined datasets for the purpose of emotion classification, but we could not find datasets in Turkish suitable for this study. Therefore, another important contribution is the generating a new data set in Turkish for emotion analysis. The dataset is generated by combining two types of sources. Several classification algorithms are applied on the dataset and results are compared. Due to the nature of Turkish language, new features are added to the existing methods to improve the success of the proposed method.

Subject Keywords

Machine learning., Artificial intelligence., Text processing (Computer science)., Text editors (Computer programs)., Data mining.

URI

http://etd.lib.metu.edu.tr/upload/12614521/index.pdf
https://hdl.handle.net/11511/21693

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

Mapping Human–Computer Interaction Research Themes and Trends from Its Existence to Today: A Topic Modeling-Based Review of past 60 Years GÜRCAN, FATİH; Cagiltay, Nergiz Ercil; Çağıltay, Kürşat (Informa UK Limited, 2020-01-01) As it covers a wide spectrum, the research literature of human-computer interaction (HCI) studies has a rich and multi-disciplinary content where there are limited studies demonstrating the big picture of the field. Such an analysis provides researchers with a better understanding of the field, revealing current issues, challenges, and potential research gaps. This study aims to explore the research trends in the developmental stages of the HCI studies over the past 60 years. Automated text mining with prob...
Making sense of statistical and probabilistic information in the media texts Pre service teachers critical thinking processes ÖZEN, MEHTAP; Çakıroğlu, Erdinç (2015-02-08) This study aimed to investigate the critical thinking processes that pre-service middle school mathematics teachers utilize when they intensely engaged with the media text based on statistical and probabilistic information. Data were collected through in-depth interviews with four pre-service middle school mathematics teachers in a public university. The findings of the study pointed out that pre-service middle school mathematics teachers progressed through different critical thinking processes, including c...
Hybrid statistical and machine learning modeling of cognitive neuroscience data Çakar, Serenay; Gökalp Yavuz, Fulya (2023-01-01) The nested data structure is prevalent for cognitive measure experiments due to repeatedly taken observations from different brain locations within subjects. The analysis methods used for this data type should consider the dependency structure among the repeated measurements. However, the dependency assumption is mainly ignored in the cognitive neuroscience data analysis literature. We consider both statistical, and machine learning methods extended to repeated data analysis and compare distinct algorithms ...
Investigating the performance of segmentation methods with deep learning models for sentiment analysis on turkish informal texts Kurt, Fatih; Karagöz, Pınar; Department of Information Systems (2018) This work investigates segmentation approaches for informal short texts in morphologically rich languages in order to e ectively classify the sentiment. The two building blocks of the proposed work in this thesis are segmentation and deep neural network model building. Segmentation focuses on preprocessing of text with di erent methodologies. These methodologies are grouped under four distinct approaches; namely, morphological, sub-word, tokenization, and hybrid approaches. There is mostly multiple numbers ...
Positive impact of state similarity on reinforcement learning performance Girgin, Sertan; Polat, Faruk; Alhaj, Reda (Institute of Electrical and Electronics Engineers (IEEE), 2007-10-01) In this paper, we propose a novel approach to identify states with similar subpolicies and show how they can be integrated into the reinforcement learning framework to improve learning performance. The method utilizes a specialized tree structure to identify common action sequences of states, which are derived from possible optimal policies, and defines a similarity function between two states based on the number of such sequences. Using this similarity function, updates on the action-value function of a st...

Citation Formats

Z. Boynukalın, “Emotion analysis of Turkish texts by using machine learning methods,” M.S. - Master of Science, Middle East Technical University, 2012.