Analyzing Customer Sentiments and Trends in Turkish Mobile Banking Apps: A Text Mining Study

Öz

This study investigates customer satisfaction with mobile banking applications in Turkey through a comprehensive text mining analysis of user-generated reviews. Drawing from a large corpus of data across ten leading Turkish banks, including Ziraat Bank, İş Bank, Garanti BBVA, Akbank, Yapı Kredi Bank, Halkbank, Vakıfbank, DenizBank, QNB Finansbank, and Turkey Şekerbank, the alignment between user ratings and sentiments is explored to uncover the nuances of customer feedback. The dataset undergoes rigorous preprocessing, sentiment analysis, trend analysis, and Latent Dirichlet Allocation (LDA) topic modeling to identify prevailing themes and factors affecting user satisfaction. The methodology involves the classification of reviews into positive, negative, and neutral sentiments and the examination of trends over time to pinpoint periods of heightened dissatisfaction. The analysis is further augmented by the application of advanced machine learning algorithms, including Random Forest, Gradient Boosting Machine, and BERT, showcasing an accuracy range between 92% and 95% in sentiment classification. The results of the topic modeling are visualized through word clouds, providing a clear depiction of the dominant themes in user feedback. Trend analysis over time identifies critical periods where negative reviews surpass positive ones, often coinciding with app updates or changes in service features. The findings highlight the necessity for continuous improvement and testing of mobile banking applications to meet customer expectations effectively.

Anahtar Kelimeler

• Mobile banking satisfaction
• Sentiment analysis
• User experience trends
• Topic modeling
• Customer feedback analysis

Türkiye'deki Mobil Bankacılık Uygulamalarında Müşteri Duygularını ve Eğilimlerini Analiz Etme: Bir Metin Madenciliği Çalışması

Öz

BBu çalışma, Türkiye'deki mobil bankacılık uygulamalarına yönelik müşteri memnuniyetini, kullanıcı tarafından oluşturulan yorumların kapsamlı bir metin madenciliği analiziyle araştırmaktadır. Türkiye'nin önde gelen on Bankna ait geniş bir veri kümesinden yararlanarak, kullanıcı derecelendirmeleri ve duyguları arasındaki uyumu inceleyerek müşteri geri bildirimlerinin inceliklerini ortaya çıkarmayı amaçlamaktadır. Ziraat Bankası, İş Bankası, Garanti BBVA, Akbankası, Yapı Kredi Bankası, Halkbankası, Vakıfbank, Denizbank, QNB Finansbank ve Türkiye Şekerbankası’ndan toplanan yorumları içeren veri seti, kullanıcı memnuniyetini etkileyen hâkim temaları ve faktörleri belirlemek için titiz ön işleme, duygu analizi, eğilim analizi ve Latent Dirichlet Allocation (LDA) konu modellemesine tabi tutulmuştur. Metodolojimiz, yorumların olumlu, olumsuz ve nötr duygulara sınıflandırılmasını ve zaman içinde eğilimleri inceleyerek memnuniyetsizliğin arttığı dönemleri belirleme işlemi içermektedir. Analiz, Random Forest, Gradient Boosting Machine ve BERT gibi gelişmiş makine öğrenimi algoritmalarının uygulanmasıyla daha da geliştirilmiş ve bu algoritmalar, duygu sınıflandırmasında %92 ile %95 arasında değişen bir doğruluk oranı sergilemektedir. Çalışma, verilen derecelendirme ile duyguların uyumlu olmadığı önemli bir yorum oranını ortaya çıkarmıştır ve bu durum, sadece derecelendirmelerle ifade edilmeyen kullanıcı deneyimlerindeki karmaşıklıkları göstermektedir. Zaman içinde yapılan eğilim analizi, olumsuz yorumların olumlu olanları aştığı kritik dönemleri belirlemiş, bunlar genellikle uygulama güncellemeleri veya hizmet özelliklerindeki değişikliklerle çakışmaktadır. Bulgularımız, müşteri beklentilerini etkili bir şekilde karşılamak için mobil bankacılık uygulamalarının sürekli iyileştirilmesi ve test edilmesi gerekliliğini vurgulamaktadır.

Anahtar Kelimeler

• Mobil bankacılık tatmini
• Duygu analizi
• Kullanıcı deneyimleri
• Konu modelleme
• Müşteri deneyimi analizi

Kaynakça

1. Afjal, M. (2023). Bridging the financial divide: a bibliometric analysis on the role of digital financial services within FinTech in enhancing financial inclusion and economic development. Humanities and Social Sciences Communications, 10(1), 1-27.
2. Ahmad, O., & Rahim, M. K. I. A. (2023). The effect of innovation and trust ın microfınance institution repayment performance in malaysia. Journal of Global Business and Social Entrepreneurship (GBSE), 9(27).
3. Al-Abbadey, M., Fong, M. M., Wilde, L. J., Ingham, R., & Ghio, D. (2021). Mobile health apps: An exploration of user-generated reviews in Google Play Store on a physical activity application. Digital Health, 7, 20552076211014988.
4. Allioui, H., & Mourdi, Y. (2023). Exploring the Full Potentials of IoT for Better Financial Growth and Stability: A Comprehensive Survey. Sensors, 23(19), 8015.
5. Barnes, S. J., & Corbitt, B. (2003). Mobile banking: concept and potential. International Journal of Mobile Communications, 1(3), 273-288.
6. Cheng, L. C., & Sharmayne, L. R. (2020, December). Analysing digital banking reviews using text mining. In 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM) (pp. 914-918). IEEE.
7. Dey, M., Islam, M. Z., & Rana, T. (2023). Applying Text Mining to Understand Customer Perception of Mobile Banking App. In Handbook of Big Data and Analytics in Accounting and Auditing (pp. 309-333). Singapore: Springer Nature Singapore.
8. Gruber, T., Szmigin, I., & Voss, R. (2009). Handling customer complaints effectively: A comparison of the value maps of female and male complainants. Managing Service Quality: An International Journal, 19(6), 636-656.

9. Ha, K. H., Canedoli, A., Baur, A. W., & Bick, M. (2012). Mobile banking—insights on its increasing relevance and most common drivers of adoption. Electronic Markets, 22, 217-227.
10. Hirsh-Pasek, K., Zosh, J. M., Golinkoff, R. M., Gray, J. H., Robb, M. B., & Kaufman, J. (2015). Putting education in “educational” apps: Lessons from the science of learning. Psychological Science in the Public Interest, 16(1), 3-34.
11. Hussain, A., Hannan, A., & Shafiq, M. (2023). Exploring mobile banking service quality dimensions in Pakistan: a text mining approach. International Journal of Bank Marketing, 41(3), 601-618.
12. Kazan, E., Tan, C. W., Lim, E. T., Sørensen, C., & Damsgaard, J. (2018). Disentangling digital platform competition: The case of UK mobile payment platforms. Journal of Management Information Systems, 35(1), 180-219.
13. Kocakoyun, S., & Bicen, H. (2017). Development and Evaluation of Educational Android Application. Cypriot Journal of Educational Sciences, 12(2), 58-68.
14. Koenig‐Lewis, N., Palmer, A., & Moll, A. (2010). Predicting young consumers' take up of mobile banking services. International Journal of Bank Marketing, 28(5), 410-432.
15. Kumar, R. R., Israel, D., & Malik, G. (2018). Explaining customer’s continuance intention to use mobile banking apps with an integrative perspective of ECT and Self-determination theory. Pacific Asia Journal of the Association for Information Systems, 10(2), 5.
16. Leem, B. H., & Eum, S. W. (2021). Using text mining to measure mobile banking service quality. Industrial Management & Data Systems, 121(5), 993-1007.
17. Lee, K. C., & Chung, N. (2009). Understanding factors affecting trust in and satisfaction with mobile banking in Korea: A modified DeLone and McLean’s model perspective. Interacting with Computers, 21(5-6), 385-392.
18. Lule, I., Omwansa, T. K., & Waema, T. M. (2012). Application of technology acceptance model (TAM) in m-banking adoption in Kenya. International Journal of Computing & ICT Research, 6(1).
19. Mahmud, M. S., Bonny, A. J., Saha, U., Jahan, M., Tuna, Z. F., & Al Marouf, A. (2022, March). Sentiment analysis from user-generated reviews of ride-sharing mobile applications. In 2022 6th International Conference on Computing Methodologies and Communication (ICCMC) (pp. 738-744). IEEE.
20. Mittal, D., & Agrawal, S. R. (2022). Determining banking service attributes from online reviews: text mining and sentiment analysis. International Journal of Bank Marketing, 40(3), 558-577.
21. Oh, Y. K., & Kim, J. M. (2022). What improves customer satisfaction in mobile banking apps? An application of text mining analysis. Asia Marketing Journal, 23(4), 3.
22. Omotosho, B. S. (2021). Analysing user experience of mobile banking applications in Nigeria: A text mining approach. CBN Journal of Applied Statistics, 12(1), 77-108.
23. Orencia, A. J. (2023). Digital Banking Revolution in the Philippines and its Drivers, Impacts, and Challenges: A Multifaceted Analysis. International Journal of Open-Access, Interdisciplinary & New Educational Discoveries of ETCOR Educational Research Center (2023).
24. Sarin, P., Kar, A. K., & Ilavarasan, V. P. (2021). Exploring engagement among mobile app developers–Insights from mining big data in user generated content. Journal of Advances in Management Research, 18(4), 585-608.
25. Shaikh, A. A., & Karjaluoto, H. (2015). Mobile banking adoption: A literature review. Telematics and Informatics, 32(1), 129-142.
26. Shankar, A., Tiwari, A. K., & Gupta, M. (2022). Sustainable mobile banking application: a text mining approach to explore critical success factors. Journal of Enterprise Information Management, 35(2), 414-428.
27. Sulaiman, A., Jaafar, N. I., & Mohezar, S. (2007). An overview of mobile banking adoption among the urban community. International Journal of Mobile Communications, 5(2), 157-168.
28. Tam, C., & Oliveira, T. (2017). Literature review of mobile banking and individual performance. International Journal of Bank Marketing, 35(7), 1044-1067.