The International Arab Journal of Information Technology (IAJIT)


Novel Turkish Sentiment Analysis System using ConvNet

Saed Alqaraleh,
In this paper, an efficient model for the Turkish language sentiment analysis has been introduced. As Turkish is an agglutinative language, which requires spatial processing, an efficient pre-processing model was also implemented and integrated as a part of the developed system. In addition, the Deep Convolutional Neural Networks (ConvNet) have been integrated to build an efficient system. Several experiments using the “Turkish movie reviews” dataset have been conducted, and it has been observed that the developed system has improved the sentiment analysis system that supports the Turkish language and significantly outperforms the existing state-of-the-art Turkish sentiment analysis systems.

[1] Alqaraleh S., Hafez A., and Tello A., “Dynamic Time Warping of Deep Features for Place Recognition in Visually Varying Conditions,” Arabian Journal for Science and Engineering, vol. 46, no. 4, pp. 3675-3689, 2021.

[2] Alqaraleh S. and IŞIK M., “Efficient Turkish Tweet Classification System for Crisis Response,” The Turkish Journal of Electrical Engineering and Computer Sciences, vol. 28, no. 6, pp. 3168-3182, 2020.

[3] Dehkharghani R., Yanikoglu B., Saygin Y., and Oflazer K., “Sentiment Analysis in Turkish at Different Granularity Levels,” Natural Language Engineering, vol. 23, no. 4, pp. 535- 559, 2017.

[4] Dehkharghani R., Saygin Y., Yanikoglu B., and Oflazer K., “Sentiturknet: A Turkish Polarity Lexicon for Sentiment Analysis,” Language Resources and Evaluation, vol. 50, no. 3, pp. 667-685, 2016.

[5] Demirci G., Keskin Ş., and Doğan G., “Sentiment Analysis in Turkish with Deep Learning,” in Proceedings of the IEEE International Conference on Big Data, Los Angeles, pp. 2215-2221, 2019.

[6] Demirtas E. and Pechenizkiy M., “Cross-Lingual Polarity Detection with Machine Translation,” in Proceedings of the 2nd International Workshop on Issues of Sentiment Discovery and Opinion Mining, New York, pp. 1-8, 2013.

[7] Eroğul U., Sentiment Analysis in Turkish, Middle East Technical University, 2009.

[8] Esuli A. and Sebastiani F., “Sentiwordnet: A Publicly Available Lexical Resource for Opinion Mining,” LREC, vol. 6, pp. 417-422, 2006.

[9] Gardner M., Grus J., Neumann M., Tafjord O., Dasigi P., Liu N., Peters M., Schmitz M., and Zettlemoyer L., “A Deep Semantic Natural Language Processing Platform,” arXiv preprint arXiv:1803.07640, 2017.

[10] Ghorbel H. and Jacot D., “Sentiment Analysis of French Movie Reviews,” Advances in Distributed Agent-Based Retrieval Tools, vol. 361, pp. 97-108, 2011.

[11] He K., Zhang X., Ren S., and Sun J., “Deep Residual Learning for Image Recognition,” in Proceedings of the IEEE Conference on Novel Turkish Sentiment Analysis System using ConvNet 561 Computer Vision and Pattern Recognition, Las Vegas, pp. 770-778, 2016.

[12] Hussein D., “A Survey on Sentiment Analysis Challenges,” Journal of King Saud University- Engineering Sciences, vol. 30, no. 4, pp. 330-338, 2018.

[13] Jaouedi N., Boujnah N., and Bouhlel M., “A Novel Recurrent Neural Networks Architecture for Behavior Analysis,” The International Arab Journal of Information Technology, vol. 18, no. 1, pp. 133-139, 2021.

[14] Johnson R. and Zhang T., “Convolutional Neural Networks for Text Categorization: Shallow Word- Level Vs. Deep Character-Level,” arXiv preprint arXiv:1609.00718, 2016.

[15] Kalchbrenner N., Grefenstette E., and Blunso P., “A Convolutional Neural Network for Modelling Sentences,” arXiv preprint arXiv:1404.2188, 2014.

[16] Kaya M., Fidan G., and Toroslu I., “Sentiment Analysis of Turkish Political News,” in Proceedings of the IEEE/WIC/ACM International Joint Conferences on Web Intelligence and Intelligent Agent Technology, Macau, pp. 174-180, 2012.

[17] Kaya M., Sentiment Analysis of Turkish Political Columns with Transfer Learning, Middle East Technical University, 2013.

[18] Korovkinas K., Danėnas P., and Garšva G., “SVM and Naïve Bayes Classification Ensemble Method for Sentiment Analysis,” Baltic Journal of Modern Computing, vol. 5, no. 4, pp. 398-409, 2017.

[19] Krizhevsky A., Sutskever I., and Hinto G., “Imagenet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, vol. 60, no. 6, pp. 1097-1105, 2012.

[20] Kurt F., “Investigating the Performance of Segmentation Methods with Deep Learning Models for Sentiment Analysis on Turkish Informal Texts,” Master's Thesis, Middle East Technical University, 2018.

[21] Mäntylä M., Graziotin D., and Kuutila M., “The Evolution of Sentiment Analysis-A Review of Research Topics, Venues, and Top Cited Papers,” Computer Science Review, vol. 27, pp. 16-32, 2018.

[22] Miller G., Beckwith R., Fellbaum C., Gross D., and Miller K., “Introduction To Wordnet: An On- Line Lexical Database,” The International Journal of Lexicography, vol. 3, no. 4, pp. 235- 244, 1990.

[23] Neviarouskaya A., Prendinger H., and Ishizuka M., “Attitude Sensing in Text Based on A Compositional Linguistic Approach,” Computational Intelligence, vol. 31, no. 2, pp. 256-300, 2015.

[24] Pradhan V., Vala J., and Balani P., “A Survey on Sentiment Analysis Algorithms for Opinion Mining,” International Journal of Computer Applications, vol. 133, no. 9, pp. 7-11, 2016.

[25] Simonyan K. and Zisserman A., “Very Deep Convolutional Networks for Large-Scale Image Recognition,” ArxivPreprinArxiv:1409.1556, 2014.

[26] Stelzner M., “Social Media Marketing Industry Report,” Social Media Examiner, 2019.

[27] Szegedy C., Liu W., Jia Y., Sermanet P., Reed S., Anguelov D., Erhan D., Vanhoucke V., and Rabinovich A., “Going Deeper with Convolutions,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, pp. 1-9, 2015.

[28] Türkmenoglu C. and Tantug A., “Sentiment Analysis in Turkish Media,” in Proceedings of Workshop on Issues of Sentiment Discovery and Opinion Mining, International Conference on Machine Learning, Beijing, pp. 1-9, 2014.

[29] Yıldırım E., Çetin F., Eryiğit G., and Temel T., “The Impact of NLP on Turkish Sentiment Analysis,” Türkiye Bilişim Vakfı Bilgisayar Bilimleri ve Mühendisliği Dergisi, vol. 7, no. 1, pp. 43-51, 2015.

[30] Zhang L. and Chen C., “Sentiment Classification with Convolutional Neural Networks: An Experimental Study on A Large-Scale Chinese Conversation Corpus,” in Proceedings of the 12th International Conference on Computational Intelligence and Security, Wuxi, pp. 165-169, 2016. Saed Alqaraleh is an Assistant Professor at Hasan Kalyoncu University, Gaziantep, Turkey. He completed his Ph.D. in Computer Engineering (2015) from Eastern Mediterranean University, Cyprus. His present areas of research include Information retrieval and security, Natural Language Processing, Visual Place Recognition, and Machine learning.