Flag Counter
AKILLI SİSTEMLER VE UYGULAMALARI DERGİSİ
JOURNAL OF INTELLIGENT SYSTEMS WITH APPLICATIONS
J. Intell. Syst. Appl.
E-ISSN: 2667-6893
Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.

Structured Learning Based Turkish Sentiment Analysis

Yapılandırılmış Öğrenmeye Dayalı Türkçe Duygu Analizi

How to cite: Ülgen O, Öğrenci AS. Structured learning based turkish sentiment analysis. Akıllı Sistemler ve Uygulamaları Dergisi (Journal of Intelligent Systems with Applications) 2019; 2(2): 90-93. DOI: 10.54856/jiswa.201912071

Full Text: PDF, in English.

Total number of downloads: 1048

Title: Structured Learning Based Turkish Sentiment Analysis

Abstract: Sentiment analysis is highly popular topic to identify people's opinions through the social media, forums and other websites. There are an abundance of opinions on internet and analysing those opinions would have many benefits for both private and public sectors. Research has evolved looking on tweets for mining opinions and for the classification of the tweets as positive, negative or neutral in its sentiment. In this research, Turkish tweets are used for sentiment extraction where a two layer neural network is used as the pattern recognition system. The supervised training of this system is based on structured learning. As a conclusion, structured learning seems to be helpful in pattern recognition to classify tweets and mining the opinions. However, it is evident that further research in data processing and training methodology is necessary to obtain reliable sentiment analysis results.

Keywords: Sentiment analysis; twitter; neural network; pattern recognition; structured learning


Başlık: Yapılandırılmış Öğrenmeye Dayalı Türkçe Duygu Analizi

Özet: Duygu analizi, sosyal medyada, forumlarda ve diğer internet sitelerinde insanların fikirlerini belirlemek için sıkça kullanılmaktadır. İnternette çok sayıda fikir bulunmakta ve bu fikirlerin analiz edilmesi özel sektör ve kamu sektörü için birçok faydayı beraberinde getirmektedir. Araştırmalar, fikirleri toplamak için tweetleri kullanma ve bu tweetleri pozitif, negatif ve nötr olarak sınıflandırma yönünde evrildi. Bu araştırmada, örüntü tanıma sistemi olarak çift katmanlı sinir ağı kullanılırken duyguları almak için Türkçe tweetler kullanıldı. Bu sistemin denetlenen eğitimi yapılandırılmış öğrenime dayanmaktadır. Sonuç olarak yapılandırılmış öğrenme, duyguları sınıflandırmak ve görüşleri incelemek için model tanımada yardımcı olur gibi görünüyor. Bununla birlikte, güvenilir bilgi analizi sonuçlarını elde etmek için veri işleme ve eğitim metodolojisinde ileri araştırmaların yapılması gerektiği açıktır.

Anahtar kelimeler: Duygu analizi; Twitter; sinir ağları; örüntü tanıma; yapısal öğrenme


Bibliography:
  • Pak A, Paroubek P. Twitter as a corpus for sentiment analysis and opinion mining. In Proceedings of the International Conference on Language Resources and Evaluation (LREC 2010), May 17-23, 2010, Valletta, Malta, pp. 1320-1326.
  • Yi J, Nasukawa T, Bunescu R, Niblack W. Sentiment analyzer: Extracting sentiments about a given topic using natural language processing techniques. In Third IEEE International Conference on Data Mining, November 20-22, 2003, Melbourne, Florida, USA, pp. 427-434.
  • Rong W, Peng B, Ouyang Y, Li C, Xiong Z. Semi-supervised dual recurrent neural network for sentiment analysis. In IEEE 11th International Conference on Dependable, Autonomic and Secure Computing, December 21-22, 2013, Chengdu, China, pp. 438-445.
  • Wang W. Sentiment analysis of online product reviews with semi-supervised topic sentiment mixture model. In Seventh International Conference on Fuzzy Systems and Knowledge Discovery, August 10-12, 2010, Yantai, China, pp. 2385-2389.
  • Santos RLS, de Sousa RF, Rabelo RAL, Moura RS. An experimental study based on Fuzzy Systems and Artificial Neural Networks to estimate the importance of reviews about product and services. In 2016 International Joint Conference on Neural Networks (IJCNN), July 24-29, 2016, Vancouver, BC, Canada, pp. 647-653.
  • Anjaria M, Guddeti R. Influence factor based opinion mining of twitter data using supervised learning. In Sixth International Conference on Communication Systems and Networks (COMSNETS), January 6-10, 2014, Bangalore, India, pp. 1-8.
  • Neethu M, Rajasree R. Sentiment analysis in Twitter using machine learning techniques. In Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT), July 4-6, 2013, Tiruchengode, India, pp. 1-5.
  • Zamahsyari Z, Nurwidyantoro A. Sentiment analysis of economic news in Bahasa Indonesia using majority vote classifier. In International Conference on Data and Software Engineering (ICoDSE), October 26-27, 2016, Denpasar, Indonesia, pp. 1-6.
  • Liu B. Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012.
  • Abbasi A, Chen H, Salem A. Sentiment analysis in multiple languages: Feature selection for opinion classification in web forums. ACM Transactions on Information Systems 2008; 26(3): 1-32.
  • Zhang W, Skiena S. Trading strategies to exploit blog and news sentiment. In Proceedings of the Fourth International AAAI Conference on Weblogs and Social Media, May 23-26, 2010, Washington, DC, USA.
  • Groh G, Hauffa J. Characterizing social relations via NLP-based sentiment analysis. In Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media, July 17-21, 2011, Barcelona, Spain, 5(1): 502-505.
  • Duncan B, Zhang Y. Neural networks for sentiment analysis on Twitter. In IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC), July 6-8, 2015, Beijing, China, pp. 275-278.
  • Davidov D, Tsur O, Rappoport A. Enhanced sentiment learning using twitter hashtags and smileys. In COLING'10: Proceedings of the 23rd International Conference on Computational Linguistics, August 2010, pp. 241–249.
  • Zhou X, Tao X, Yong J, Yang Z. Sentiment analysis on tweets for social events. In Proceedings of the 2013 IEEE 17th International Conference on Computer Supported Cooperative Work in Design (CSCWD), June 27-29, 2013, Whistler, BC, Canada, pp. 557-562.
  • Kaya M, Fidan G, Toroslu IH. Sentiment analysis of Turkish political news. In IEEE/WIC/ACM International Conferences on Web Intelligence and Intelligent Agent Technology, December 4-7, 2012, Macau, China, pp. 174-180.
  • Coban O, Tumuklu Ozyer G. Sentiment classification for Turkish Twitter feeds using LDA. In 24th Signal Processing and Communication Application Conference (SIU), MAy 16-19, 2016, Zonguldak, Turkey, pp. 129-132.
  • Akin AA, Akin MD. Zemberek: an open source NLP framework for Turkic Languages. Structure 2007; 10: 1-5.