Türkçe Kozmetik Ürün Yorumlarının Duygu Analizi ile Değerlendirilmesi

Öz

Web temelli verilerin endüstriyi besleyen bir alan olması, bilgisayar bilimlerinin yanı sıra yönetim bilimlerinin araştırma konularına dahil olmasına neden olmuştur. İşletmelerin yeni ürünlerini piyasaya sürmesinde, yeniden şekillenmelerinde, stratejik kararlarında, pazarlama çalışmalarında yardımcı olan büyük veri, kurumların karar alma süreçlerinde oldukça etkilidir. Özellikle e-ticaret sitelerinde yer alan müşteri yorumları işletmeler ve markalar için kıymetli bilgileri içerisinde saklar. Denetimli makine öğrenme algoritmalarına istatiksel olarak dayanan duygu analizi, otomatik olarak bilgi çıkarımında fayda sağlayan önemli yöntemlerden biridir. Bu çalışmada, belirli bir kozmetik markasının trendyol.com e-ticaret sitesinde yer alan ürünlerine yönelik Türkçe müşteri değerlendirmeleri üzerinde duygu analizi gerçekleştirilmiştir. Veri seti pozitif, negatif ve nötr olarak sınıflandırılmış ve ardından K-En Yakın Komşular (K-NN), Destek Vektör Makinesi (SVM) ve Karar Ağacı (DT) algoritmaları kullanarak sınıflandırma performansları ölçülerek değerlendirilmiştir. Karşılaştırmalı analizler sonucunda her üç algoritma için değerlendirme metrikleri %85 oranının üzerinde sonuç vermiştir. Kullanılan algoritmalar içerisinde Destek Vektör Makinesi %91 doğruluk oranı ile en başarılı sonucu vermiştir.

Anahtar Kelimeler

• Duygu Analizi
• Makine Öğrenmesi
• Doğal Dil İşleme
• Python
• Metin Madenciliği

Evaluation of Turkish cosmetic product reviews with machine learning-based sentiment analysis

Öz

Since web-based data is an area that feeds the industry, it has been included in the research topics of management sciences as well as computer sciences. Big data, which helps businesses launch new products and reshape strategic decisions and marketing studies, is very effective in the decisions-making processes in organizations. Customer reviews, especially on e-commerce sites, contain valuable information for businesses and brands. Sentiment analysis, which is statistically based on supervised machine learning algorithms, is one of the important methods that provide benefits in automatic information extraction. In this study, sentiment analysis was performed on Turkish costumer reviews about the cosmetic brand on trendyol.com e-commerce site. The dataset was classified as positive, negative, and neutral, and the classification performances were measured using K-Nearest Neighbours (K-NN), Support Vector Machine (SVM), and Decision Tree (DT) algorithms. As a result of comparative analysis, the evaluation metrics for all three algorithms yielded results above 85%. Support Vector Machine gave the most successful result with a 91% accuracy rate among the algorithms used.

Anahtar Kelimeler

• Sentiment Analysis
• Machine Learning
• Natural Language Processing
• Python
• Text Mining

Kaynakça

1. Abirami, M. A. and Gayathri, V. (2016), A survey on sentiment analysis methods and approach, Eighth International Conference on Advanced Computing (ICoAC). 19-21 Januay, Chennai, India.
2. Ahuja, R., Chug, A., Kohli, S., Gupta, S. and Ahuja, P. (2019), The impact of features extraction on the sentiment analysis, Procedia Computer Science, 152, 341-348.
3. Aksu, M. Ç. and Karaman, E. (2020), FastText ve kelime çantası kelime temsil yöntemlerinin turistik mekanlar için yapılan Türkçe incelemeler kullanılarak karşılaştırılması, Avrupa Bilim ve Teknoloji Dergisi, 20, 311-320.
4. Al Amrani, Y., Lazaar, M. and El Kadiri, K. E. (2018), Random forest and support vector machine based hybrid approach to sentiment analysis, Procedia Computer Science,127, 511-520.
5. Alaparthi, S. and Mishra, M. (2021), BERT: a sentiment analysis odyssey, Journal of Marketing Analytics, 9, 118-126.
6. Alnahas, D., Aşık, F., Kanturvardar, A. and Ülkgün, A. M. (2022), Opinion mining using LSTM networks ensemble for multi-class sentiment analysis in e-commerce. IEEE, 3rd International Informatics and Software Engineering Conference (IISEC), 15-16 December, Ankara.
7. Altınel, B. and Ganiz, M. C. (2016), A new hybrid semi-supervised algorithm for text classification with class-based semantics, Knowledge-Based System, 108, 50-64.
8. Aman, S. and Szpakowicz, S. (2007), Identifying expressions of emotion in textç International Conference on Text, Speech and Dialogue, 196-205.

9. Anreaja, L. J., Harefa, N. N., Negara, J. G. P., Pribyantara, V. N. H. and Prasetyo, A. B. (2022), Naive bayes and support vector machine algorithm for sentiment analysis opensea mobile application users in Indonesia. Jurnal Informatika dan Sains, 5(1), 62-68.
10. Baid, P., Gupta, A. and Chaplot, N. (2017), Sentiment analysis of movie reviews using machine learning techniques. International Journal of Computer Applications, 179(7), 45-49.
11. Bayhaqy, A., Sfenrianto, S., Nainggolan, K. and Kaburuan, E. R. (2018), Sentiment analysis about e-commerce from tweets using decision tree, k-nearest neighbor, and naïve bayes. International Conference on Orange Technologies (ICOT), 23-26 October, Nusa Dua, Bali, Indonesia.
12. Buschmeier, K., Cimiano, P. and Klinger, R. (2014), An impact analysis of features in a classification approach to irony detection in product reviews. Association for Computational Linguistics, 42-49.
13. Çabuk, M., Yücalar, F. and Toçoğlu, M. A. (2023), Makine öğrenmesi ile e-ticaret ürün yorumlarının otomatik analizi. Avrupa Bilim ve Teknoloji Dergisi, 52, 110121.
14. D'Andrea, A., Ferri, F., Grifoni, P. and Guzzo, T. (2015), Approaches, tools, and applications for sentiment analysis implementation. International Journal of Computer Applications, 125(3), 26-33.
15. Demircan, M., Seller, A., Abut, F. and Akay, M. F. (2021), Developing Turkish sentiment analysis models using machine learning and e-commerce data. International Journal of Cognitive Computing in Engineering, 2, 202-207.
16. Gautam, G. and Yadav, D. (2014), Sentiment analysis of twitter data using machine learning approaches and semantic analysis. Seventh International Conference on Contemporary Computing (IC3), Noida, India, 07-09 August.
17. Gupta, A., Tyagi, P., Choudhury, T. and Shamoon, M. (2019), Sentiment analysis using support vector machine. International Conference on contemporary Computing and Informatics (IC3I), 12-14 December, Singapore.
18. Güven, Z. A. (2021), Türkçe ürün yorumları için BERT, ELECTRA ve ALBERT dil modellerinin duygu analizine etkisi. IEEE, 15-17 Eylül, International Conference on Computer Science and Engineering (UBMK), Ankara, Turkiye.
19. Hall, M. A. and Smith, L. A. (1998), Practical feature subset selection for machine learning. C. McDonald (Ed.), In Computer Science ’98 Proceedings of the 21st Australasian Computer Science Conference ACSC’98. (pp.181-191). Berlin: Springer.
20. Hartmann, J., Heitmann, M., Siebert, C. and Schamp, C. (2023), More than a feeling: Accuracy and application of sentiment analysis, International Journal of Research in Marketing, 40, 75-87.
21. Jain, A. P. and Dandannavar, P. (2016), Application of machine learning techniques to sentiment analysis. 2nd International Conference on Applied and Theoretical Computing and Communication Technology (iCATccT), 21-23 July, Bangalore, India.
22. Jiménez-Zafra, S. M., Martín-Valdivia, M. T., Molina-González, D. M. and Ureña-López, L. A. (2019), How do we talk about doctors and drugs? Sentiment analysis in forums expressing opinions for medical domain, Artificial Intelligence in Medicine, 93, 50-57.
23. Jurafsky, D. and Martin, J. H. (2008), Speech and language processing an introduction to natural language processing, computational linguistics, and speech recognition. New Jersey: Pearson Prentice Hall
24. Kalaivani, P. and Shunmuganathan, D. K. (2013), Sentiment classification of movie reviews by supervised machine learning approaches, Indian Journal of Computer Science and Engineering (IJCSE), 4(4), 285-292.
25. Karagöz, P., Kama, B., Öztürk, M., Toroslu, I. H. and Cantürk, D. (2019), A framework for aspect based sentiment analysis on Turkish informal texts, Journal of Intelligent Information Systems, 53, 431-451.
26. Kaur, S., Sikka, G. and Awasthi, L. K. (2018), Sentiment analysis approach based on n-gram and knn classifier. First International Conference on Secure Cyber Computing and Communication (ICSCCC), IEEE,15-17 December, Jalandhar, India.
27. Kenyon-Dean, K., Ahmed, E., Fujimoto, S., Georges-Filteau, J., Glas, C., Kaur, B., Lalande, A., Bhanderi, S., Belfer, R., Kanagasabai, N., Sarrazingendron, R., Verma, R. and Ruths, D. (2018), Sentiment analysis: It’s complicated!, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 1, 1886-1895.
28. Kılıçer, S. and Samli, R. (2023), E-ticaret sitelerindeki Türkçe ürün yorumları üzerine makine öğrenmesi algoritmaları ile duygu analizi. Veri Bilimi Dergisi, 6(2), 15-23.
29. Kusnanda, D. and Permana, A. A. (2023), Implementation of naive bayes classifier (nbc) forsentiment analysis on twitter in mobile legends, International Journal of Science, Technology and Management, 4(5), 1132-1138.
30. Liu, H., Chen, X. and Liu, X. (2022), A study of the application of weight distributing method combining sentiment dictionary and tf-idf for text sentiment analysis, IEEE Access, 10, 32280-32289.
31. M. C., Ganiz (2016), Semi‐supervised learning using higher‐order co‐occurrence paths to overcome the complexity of data representation. IEEE International Conference on Systems, Man, and Cybernetics (SMC), 9-12 October, Budapest, Hungary.
32. Mouthami, K., Devi, K. N. and Bhaskaran, V. M. (2013), Sentiment analysis and classification based on textual reviews. International Conference on Information Communication and Embedded Systems (ICICES), IEEE, 21-22 February, Chennai, India.
33. Naresh, A. and Krishna, P. V. (2021), An efficient approach for sentiment analysis using machine learning algorithm, Evolutionary Intelligence, 14, 725-731.
34. Özmen, C. G. and Gündüz, S. (2023), Duygu analizi ve çeşitli işletme uygulamaları. In İşletmelerde Güncel Paradigmalar (Ed. F. N. İplik). 61-95, Akademisyen Kitabevi, Ankara.
35. Parlar, T. and Özel, S. A. (2016), A new feature selection method for sentiment analysis of Turkish reviews. International Symposium on INnovations in Intelligent Systems and Applications (INISTA), 2-5 August, Sinaia, Romania.
36. Peng, W. and Park, D. H. (2011), Generate adjective sentiment dictionary for social media sentiment analysis using constrained nonnegative matrix factorization. Fifth International AAAI Conference on Weblogs and Social Media, 5(1), 273-180.
37. Pervan, N. and Keleş, H. Y. (2017). Sentiment analysis using a random forest classifier on Turkish web comments. Communications Faculty of Sciences University of Ankara Series A2-A3: Physical Sciences and Engineering, 59(2), 69-79.
38. Ramadhon, M. I., Arini, A., Mintarsih, F. and Matin, I. M. M. (2021), N-gram and k-nearest neighbor algorithm for sentiment analysis on capital relocation. 9th International Conference on Cyber and IT Service Management (CITSM), Bengkulu, Indonesia 22-23 September, Bengkulu, Indonesia, 1-6.
39. Rani, S. and Singh, J. (2017), Sentiment analysis of tweets using support vector machine. International Journal of Computer Science and Mobile Applications, 5(10), 83-91.
40. Rathor, A. S., Agarwal, A. and Dimri, P. (2018), Comparative study of machine learning approaches for amazon reviews, Procedia Computer Science, 132, 1552-1561.
41. Rumelli, M., Akuuş, D., Kart, Ö. and Işık, Z. (2019), Sentiment analysis in Turkish text with machine learning algorithms. Innovations in Intelligent Systems and Applications Conference (ASYU). 31 Ekim- 2 November, Izmir, Turkiye.
42. Santur, Y. (2019), Sentiment analysis based on gated recurrent unit. IEEE, International Artificial Intelligence and Data Processing Symposium (IDAP). 21-22 September. Malatya, Turkiye.
43. Shamantha, R. B., Shetty, S. M. and Rai, P. (2019), Sentiment analysis using machine learning classifiers: Evaluation of performance. IEEE 4th International Conference on Computer and Communication Systems (ICCCS), 23-25 February, Singapore.
44. Sharef, N. M., Zin, H. M. and Nadali, S. (2016), Overview and future opportunities of sentiment analysis approaches for big data, Journal of Computer Sciences, 12(3), 153-168.
45. Shivaprasad, T. K. and Shetty, J. (2017), Sentiment analysis of product reviews: A review. International Conference on Inventive Communication and Computational Technologies (ICICCT 2017), 10-11 March, Coimbatore, India. Silva, N.F.F., Hruschka, E. R. and Hruschka Jr., E. R. (2014), Tweet sentiment analysis with classifier ensembles, Decision Support Systems, 66, 170-179.
46. Sohrabi, M. K. and Karimi, F. (2018), A feature selection approach to detect spam in the facebook social network, Arabian Journal for Science and Engineering, 43, 949-958.
47. Thavareesan, S. and Mahesan, S. (2021), Sentiment analysis in Tamil texts using k-means and k-nearest neighbour. 10th International Conference on Information and Automation for Sustainability (ICIAfS), 11-13 August, Negambo, Sri Lanka.
48. Toprak, B. M. and Güney, S. (2023). Classification of Turkish e-commerce product reviews. IEEE, 46th International Conference on Telecommunications and Signal Processing (TSP), 12-14 July, Prague, Czech Republic, 29-32.
49. Umarani, V., Julian, A. and Deepa, J. (2021), Sentiment analysis using various machine learning and deeplearning techniques, J. Nig. Soc. Phys. Sci., 3, 385–394.
50. Usha, M.S. and Indra Devi, M. (2013), Analysis of sentiments using unsupervised learning techniques. International Conference on Information Communication and Embedded Systems, 21-22 February, Tamilnadu, India, 241–245.
51. Vohra, S. M. and Teraiya, J. B. (2013), A comparatıve study of sentiment analysis techniques. Journal Of Information, Knowledge and Research in Computer Engineering, 2(2), 313-317.
52. Wankhade, M., Rao, A. C. S. and Kulkarni, C. (2022), A survey on sentiment analysis methods, applications, and challenges, Artifcial Intelligence Review, 55, 5731-5780.
53. Xia, R., Zong, C. and Li, S. (2011), Ensemble of feature sets and classification algorithms for sentiment classification, Information Sciences, 181, 1138-1152.
54. Zhang, S. (2010), KNN-CF approach: Incorporating certainty factor to kNN classification, The IEEE intelligent informatics bulletin, 11(1), 24-33.