Murat KOYUNCU, Çiğdem TURHAN, Gökhan YURTALAN

A polarity calculation approach for lexicon-based Turkish sentiment analysis

Sentiment analysis attempts to resolve the senses or emotions that a writer or speaker intends to send across tothe people about an object or event. It generally uses natural language processing and/or artificial intelligence techniquesfor processing electronic documents and mining the opinion specified in the content. In recent years, researchers haveconducted many successful sentiment analysis studies for the English language which consider many words and wordgroups that set emotion polarities arising from the English grammar structure, and then use datasets to test theirperformance. However, there are only a limited number of studies for the Turkish language, and these studies have lowerperformance results compared to those studies for English. The reasons for this can be incorrect translation of datasetsfrom English into Turkish and ignoring the special grammar structures in the latter. In this study, special Turkish wordsand linguistic constructs which affect the polarity of a sentence are determined with the aid of a Turkish linguist, and anappropriate lexicon-based polarity determination and calculation approach is introduced for this language. The proposedmethodology is tested using different datasets collected from Twitter, and the test results show that the proposed systemachieves better accuracy than the previously developed lexical-based sentiment analysis systems for Turkish. The authorsconclude that especially analysis of word groups increases the overall performance of the system significantly.

PDF

___

[1] Thelwall M, Buckley K, Paltoglou G, Cai D, Kappas A. Sentiment strength detection in short informal text. Journal of the American Society for Information Science and Technology 2010; 61: 2544-2558.
[2] Ravi K, Ravi V. A survey on opinion mining and sentiment analysis: tasks, approaches and applications. KnowledgeBased Systems 2015; 89: 14-46.
[3] Medhat W, Hassan A, Korashy H. Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal 2014; 5: 1093-1113.
[4] Mudinas A, Zhang D, Levene M. 2012. Combining lexicon and learning based approaches for concept-level sentiment analysis. In: the First Int. Workshop on Issues of Sentiment Discovery and Opinion Mining; 12-16 August 2012; Beijing, China: ACM. pp.1-8.
[5] Vural AG, Cambazoglu BB, Senkul P, Tokgoz ZO. A framework for sentiment analysis in Turkish: Application to polarity detection of movie reviews in Turkish. Computer and Information Sciences 2012; 3: 437-445.
[6] Türkmenoğlu C, Tantuğ AC. Sentiment analysis in Turkish media. In: Workshop on Issues of Sentiment Discovery and Opinion Mining; 25 June 2014; Beijing, China: IMLS. pp. 1-11.
[7] Dehkharghani R, Saygin Y, Yanikoglu B, Oflazer K. SentiTurkNet: a Turkish polarity lexicon for sentiment analysis. Language Resources and Evaluation 2016; 50: 667-685.
[8] Pang B, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques. In: the Conference on Empirical Methods in Natural Language Processing (EMNLP); July 2002; Philadelphia, PA, USA: ACL. pp. 79-86.
[9] Bai X. Predicting consumer sentiments from online text. Decision Support Systems 2011; 50: 732-742.
[10] Saleh MR, Martín-Valdivia MT, Montejo-Ráez A, Ureña-López LA. Experiments with SVM to classify opinions in different domains. Expert Systems with Applications 2011; 3: 14799-14804.
[11] Zhang Z, Ye Q, Zhang Z, Li Y. Sentiment classification of Internet restaurant reviews written in Cantonese. Expert Systems with Applications 2011; 38: 7674-7682.
[12] Lochter JV, Zanetti RF, Reller D. Short text opinion detection using ensemble of classifiers and semantic indexing. Expert Systems with Applications 2016; 62: 243-249.
[13] Kauer AU, Moreira VP. Using information retrieval for sentiment polarity prediction. Expert Systems with Applications 2016; 61: 282-289.
[14] Turney PD. Thumbs up or thumbs down? Semantic orientation applied to unsupervised classification of reviews. In: Proceedings of the 40th Annual Meeting on Association for Computational Linguistics; 7–12 July 2002; Philadelphia, PA, USA: ACL. pp. 417-424.
[15] Moreo A, Romero M, Castro JL, Zurita JM. Lexicon-based comments-oriented news sentiment analyzer system. Expert Systems with Applications 2012; 39: 66-80.
[16] Fernandez-Gavilanes M, Alvarez-Lopez T, Juncal-Martinez J, Costa-Montenegro E, González-Castaño FJ. Unsupervised method for sentiment analysis in online texts. Expert Systems with Applications 2016; 58: 57-75.
[17] 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; 4–7 December 2012; Macau, China: IEEE. pp. 174-180.
[18] Çetin M, Amasyalı MF. Supervised and traditional term weighting methods for sentiment analysis. In: 21st Signal Processing and Communications Applications Conference (SIU); 24–26 April 2013; Haspolat, Turkey: IEEE. pp.1-4.
[19] Balahur A, Turchi M, Steinberger R, Perea-Ortega JM, Jacquet G et al. Resource creation and evaluation for multilingual sentiment analysis in social media texts. In: The 9th edition of the Language Resources and Evaluation Conference (LREC); 26–31 May 2014; Reykjavik, Iceland: ELRA. pp. 4265-4269.
[20] Yıldırım E, Çetin FS, Eryiğit G, Temel T. The impact of NLP on Turkish sentiment analysis. TBV Journal of Computer Science and Engineering; 2014; 7: 43-51.
[21] Akba F, Uçan A, Sezer EA, Sever H. Assessment of feature selection metrics for sentiment analyses: Turkish movie reviews. In: The 8th European Conference on Data Mining; 15-17 July 2014; Lisbon, Portugal: pp. 180-184.
[22] Meral M, Diri B. Sentiment analysis on Twitter. In: 22nd Signal Processing and Communications Applications Conference; 23–25 April 2014; Trabzon, Turkey: IEEE. pp.690-693.
[23] Çoban O, Özyer B, Özyer GT. Sentiment analysis for Turkish Twitter feeds. In: 23rd Signal Processing and Communications Applications Conference; 16-19 May 2015; Malatya, Turkey: IEEE. pp. 2388-2391.
[24] Türkmen H, Omurca İO. An empirical study for Turkish sentiment analysis by machine learning methods. In: International Conference on Advanced Technology and Sciences; 12-15 August 2014; Antalya, Turkey: pp. 589-592.
[25] Akgül ES, Ertano C, Diri B. Twitter verileri ile duygu analizi. Pamukkale University Journal of Engineering Sciences 2016; 22: 106-110.
[26] Dehkharghani R, Yanikoglu B, Saygin Y, Oflazer K. Sentiment analysis in Turkish at different granularity levels. Natural Language Engineering 2017; 23: 535-559.
[27] Parlar T, Özel SA. A new feature selection method for sentiment analysis of Turkish reviews. In: International Symposium on Innovations in Intelligent SysTems and Applications (INISTA); 2-5 August 2016; Sinaia, Romania.
[28] Sağlam F, Sever H, Genç B. Developing Turkish sentiment lexicon for sentiment analysis using online news media. In: IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA), 29 November–2 December 2016; Agadir, Morocco: IEEE. pp. 1-5.
[29] Omurca İO, Ekinci E, Türkmen H. An annotated corpus for Turkish sentiment analysis at sentence level. In: International Artificial Intelligence and Data Processing Symposium (IDAP); 16-17 Sept. 2017; Malatya, Turkey: IEEE. pp. 1-5.
[30] Türkmen H, Omurca Sİ, Ekinci E. An aspect based sentiment analysis on Turkish hotel reviews. In: International Symposium on Engineering, Artificial Intelligence and Applications; 2015; Girne, Turkish Republic of Northern Cyprus. pp. 9-15.
[31] Kama B, Öztürk M, Karagöz P, Toroslu IH, Kalender M. Analyzing implicit aspects and aspect dependent sentiment polarity for aspect-based sentiment analysis on informal Turkish texts. In: Proceedings of the 9th International Conference on Management of Digital EcoSystems; 07-10 November 2017; Bangkok, Thailand: ACM. pp. 134-141.
[32] Akın AA, Akın MD. Zemberek, an open source NLP framework for Turkic Languages. Structure 2007; 10: 1-5.
[33] İlhan N, Kabadayı C. Türk Dilinde Olumsuzluk. İstanbul, Turkey: Kesit Yayınları, 2017 (in Turkish).