Turkish Sentiment Analysis on Social Media

Year 2021, , 629 - 638, 30.06.2021

Nazan Kemaloğlu , Ecir Küçüksille , Muhammed Özgünsür

https://doi.org/10.16984/saufenbilder.872227

Cited By: 5

Abstract

The number of social media users has increased significantly as internet access and internet usage has grown all over the world. As it is the case in any other field, raw data collected from social media platforms are now being transformed into information. Millions of pieces of content are posted every day on platforms such as Twitter, Facebook, and Instagram. Moreover, the ability to extract meaningful information from such content has become an important field of research. This study reports a system for sentiment analysis, based on the data made available on Facebook, Twitter, Instagram, YouTube along with RSS data. Logistic Regression, Random Forest and deep learning algorithm such as Long Short-Term Memory (LSTM) are used to develop the classification model used in the system built as part of this study. Dataset is a new dataset that included data collected from Twitter, used was created and labeled by us. It was found that LSTM model provided the highest accuracy among the models generated using the training dataset. The final version of the model was tested on five different social media platforms and results are communicated.

Keywords

Artificial Neural Network, Turkish Natural Language Processing, Social Media Analysis, Sentiment Analysis

References

• [1] Smartinsigh.com, https://www.smartinsights.com/socialmedi-marketing/social-mediastrategy/newglobal social-media-research/, Access Date: 21.04.2019.
• [2] Ozger, Z.B., Diri, B., “Classification Based Turkish Question Perception”, Innovations and Applications in Smart Systems, ASYU, İzmir, (2014).
• [3] Kayahan, D., Sergin, A., Diri, B.,” Determination of TV Programme Ratings by Twitter", IEEE 21st Signal Processing and Communication Applications. 1-4, (2013).
• [4] Bollen J, Mao H, Zeng X., “Twitter mood predicts the stock market", Journal of Computational Science, 2(1): 1-8, (2011).
• [5] Bian, J., Topaloglu, U., Yu, F., “Towards large-scale twitter mining for drug-related adverse events", In Proceedings of the 2012 international workshop on Smart health and wellbeing, 25-32, (2012, October).
• [6] Eliaçik, A. B., Erdogan, N., “User Weighted Sentiment Analysis Method for Financial Communities in Twitter", In 11th International Conference on Innovations in Information Technology (IIT), 46-51, (2015).
• [7] Ayata, D., Saraçlar, M., Özgür, A.,”Turkish tweet sentiment analysis with word embedding and machine learning", In 2017 25th Signal Processing and Communications Applications Conference, 1-4, (2017, May).
• [8] Çoban, Ö., Özyer, B., Özyer, G. T., “Sentiment analysis for Turkish Twitter feeds", In 2015 23nd Signal Processing and Communications Applications Conference, 2388-239, (2015, May).
• [9] Onan, A., “Sentiment Analysis On Twitter Messages Based On Machine Learning Methods", Journal of Management Information Systems, 3(2): 1-14 (2017).
• [10] Meral, M., Diri, B., “Sentiment analysis for Turkish Twitter feeds", IEEE 22nd Signal Processing and Communication Applications, 23-2, (2014).
• [11] Çetin, M., Amasyalı, M. F., “Supervised and Traditional Term Weighting Methods for Sentiment Analysis", In Proceedings of Signal Processing and Communications Applications Conference, 1-4, (2013).
• [12] Akgül, E. S., Ertano, C., Diri, B., “Sentiment analysis with Twitter", Pamukkale University Journal of Engineering Sciences, 22(2): 106-110, (2016).
• [13] Türkmen, A. C., Cemgil, A. T., “Political interest and tendency prediction from microblog data", In 2014 22nd Signal Processing and Communications Applications Conference (SIU), 1327-1330, (2014, April).
• [14] Catal, C., Nangir, M., “A sentiment classification model based on multiple classifiers", Applied Soft Computing, 50: 135-141, (2017).
• [15] Ciftci, B., Apaydin, M. S., “A Deep Learning Approach to Sentiment Analysis in Turkish", In 2018 International Conference on Artificial Intelligence and Data Processing (IDAP), 1-5, (2018, September).
• [16] Kurt, F., Investigating the Effect of Segmentation Methods on Neural Model based Sentiment Analysis on Informal Short Texts in Turkish, Master's thesis, Middle East Technical University, Ankara, (2018).
• [17] Ayata, D., Saraçlar, M., Özgür, A., “Political opinion/sentiment prediction via long short term memory recurrent neural networks on Twitter", In 2017 25th Signal Processing and Communications Applications Conference, 1-4, (2017, May).
• [18] Akın, A. A., Akın, M. D., “Zemberek, An Open Source Nlp Framework For Turkic Languages." Structure, 10: 1-5, (2007).
• [19] Bengio, Y., Ducharme, R., Vincent, P. , Jauvin, C., “A Neural Probabilistic Language Model", Journal of Machine Learning Research, 1137{1155, (2003).
• [20] Şahin, G., “Turkish document classification based on Word2Vec and SVM classifier", In 2017 25th Signal Processing and Communications Applications Conference, 1-4, (2017, May).
• [21] Doğan, S., Diri, B., “A new N-gram based classification (Ng-ind) for Turkish documents: author, genre and gender", TBV Journal of Computer Science and Engineering, 3(1): 11- 19, (2010).
• [22] GitHub.com, http://colah.github.io/posts/2015-08- Understanding-LSTMs/ Access Date: 21.04.2019.
• [23] Kim, T., Wright, S. J., “PMU placement for line outage identification via multinomial logistic regression", IEEE Transactions on Smart Grid, 9(1): 122-131, (2018).
• [24] Li, J., Bioucas-Dias, J. M., Plaza, A., “Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning", IEEE Transactions on Geoscience and Remote Sensing, 48(11): 4085-4098, (2010).
• [25] Moraes, R., Valiati, J. F., Neto, W. P. G., “Document-level sentiment classification: An empirical comparison between SVM and ANN", Expert Systems with Applications, 40(2): 621-633, (2013).
• [26] Ho, T., “Random decision forest", 3rd International Conf. on Document Analysis and Recognition, August 14{18, Montreal, Canada, 278{282, (1995).
• [27] Amit, Y., Geman, D., “Shape quantization and recognition with randomized trees", Neural Comput. 9: 1545{1588, (1997).
• [28] Breiman, L., “Random forests", Mach. Learn. 45(1): 5{32, (2001).
• [29] Azar, A. T., Elshazly, H. I., Hassanien, A. E., Elkorany, A. M., “A random forest classifier for lymph diseases", Computer methods and programs in biomedicine, 113(2): 465-473, (2014).
• [30] Çevik,K.K., Berber, F.S., Küçüksille, E.U., “Mapping location of a suspect by using forensic images taken with their own mobile phone", International Conference on Engineering Technologies (ICENTE'18), 93-96, (2018)
• [31] Şeker, A., Diri, B., Balık, H. H., “A Review about Deep Learning Methods and Applications", Gazi Journal of Engineering Sciences (GJES), 3(3): 47-64, (2017) .
• [32] Kızrak, M. A., Bolat, B., “A Comprehensive Survey of Deep Learning in Crowd Analysis", International Journal of Informatics Technologies, 11(3): 263-286, (2018).