Mobil Uygulama Kullanıcı Yorumları Üzerinde Metin Madenciliği ve Müşteri Memnuniyeti Analizi: E-Ticaret Markası Örneği

Öz

Müşteri memnuniyeti, bir şirketin sunduğu ürün ve hizmetlerin kullanıcı beklentilerini ne ölçüde karşıladığını ifade eder. Bu çalışmanın amacı, Trendyol markasının müşteri memnuniyetini kullanıcı yorumları üzerinden değerlendirmektir. Veri seti, Google Play’de son bir ayda Trendyol mobil uygulaması hakkında yapılan yorumlardan elde edilmiştir. Python kullanılarak gerçekleştirilen analizde, duygu analizi, metin madenciliği ve konu modelleme yöntemleri uygulanmıştır. Duygu analizi, yorumları olumlu, olumsuz veya nötr olarak sınıflandırırken, metin madenciliği ve konu modelleme ise yorumlarda öne çıkan kelimeleri ve temaları belirlemiştir. Analiz sonuçları, Trendyol’un müşteri memnuniyetini etkileyen faktörleri ortaya koymuştur. Olumlu yorumlarda ürün çeşitliliği, hızlı teslimat ve müşteri hizmetleri ön plana çıkarken, olumsuz yorumlarda ürün kalitesi, gecikmeli teslimatlar ve iade süreçleri ile ilgili şikayetler dikkat çekmiştir. Çalışmanın bulguları, Trendyol’un müşteri memnuniyetini artırmak için iyileştirilmesi gereken alanları işaret etmektedir. Bu çalışma, mobil uygulama kullanıcı yorumlarının analiz edilerek müşteri memnuniyetinin değerlendirilebileceğini ve bu yaklaşımın diğer markalar için de önemli olduğunu göstermektedir

Anahtar Kelimeler

• Müşteri memnuniyeti
• Trendyol
• mobil uygulama
• duygu analizi
• metin madenciliği
• konu modelleme
• LDA
• TextBlob

Text Mining and Customer Satisfaction Analysis on Mobile Application User Reviews: An E-Commerce Brand Case Study

Öz

Customer satisfaction refers to the extent to which the products and services offered by a company meet user expectations. The purpose of this study is to evaluate customer satisfaction of the Trendyol brand through user reviews. The dataset was obtained from the comments about Trendyol mobile applications on Google Play in the last month. Sentiment analysis, text mining, and topic modelling methods were applied in the analysis using Python. Sentiment analysis categorized the comments as positive, negative, or neutral, while text mining and topic modelling identified the prominent words and themes in the comments. The results of the analysis revealed the factors affecting Trendyol's customer satisfaction. Positive comments emphasized product variety, fast delivery, and customer service, while negative comments highlighted complaints about product quality, delayed deliveries, and return processes. The findings of the study point to areas where Trendyol needs to improve to increase customer satisfaction. This study shows that customer satisfaction can be assessed by analyzing mobile app user reviews and that this approach is also important for other brands.

Anahtar Kelimeler

• Customer satisfaction
• Trendyol
• mobile application
• sentiment analysis
• text mining
• topic modelling
• LDA
• TextBlob

Kaynakça

1. Boyraz C, Gençoğlu ÇN, Türüt P. Marka sadakati ile bağlanma stilleri arasındaki ilişki: Türk Sivil Havacılık sektörü üzerine bir araştırma modeli önerisi. Hum Factors Aviat Aerosp 2024; 1(1): 42-55. https://doi.org/10.26650/hfaa.2024.1468721
2. Akkan MM. Pazarlama ve lojistik ilişkisine yönelik kavramsal bir inceleme: pazarlama lojistiği. J Econ Financ Res 2022; 4(2): 201-229. https://doi.org/10.56668/jefr.1120235
3. Kim HB, Kim WG, An JA. The effect of consumer-based brand equity on firms’ financial performance. J Consum Mark 2003; 20(4): 335-351. https://doi.org/10.1108/07363760310483694
4. Sun H, Zafar MZ, Hasan N. Employing natural language processing as artificial intelligence for analysing consumer opinion toward advertisement. Front Psychol 2022; 13: 856663. https://doi.org/10.3389/fpsyg.2022.856663
5. Wankhade M, Rao ACS, Kulkarni C. A survey on sentiment analysis methods, applications, and challenges. Artif Intell Rev 2022; 55(7): 5731-5780. https://doi.org/10.1007/s10462-022-10144-1
6. Lghaouch EM, et al. Enhancing sentiment analysis through topic modelling: comprehensive overview. In: Industry 5.0 and Emerging Technologies: Transformation Through Technology and Innovations. 2024. pp. 161-179. https://doi.org/10.1007/978-3-031-70996-8_8
7. Anderson EW, Fornell C, Lehmann DR. Customer satisfaction, market share, and profitability: Findings from Sweden. J Mark 1994; 58(3): 53-66. https://doi.org/10.1177/002224299405800304
8. Hennig-Thurau T, et al. Electronic word-of-mouth via consumer-opinion platforms: what motivates consumers to articulate themselves on the internet? J Interact Mark 2004; 18(1): 38-52. https://doi.org/10.1002/dir.10073

9. Hu M, Liu B. Mining and summarizing customer reviews. In: Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2004. https://doi.org/10.1145/1014052.1014073
10. Pang B, Lee L. Opinion mining and sentiment analysis. Found Trends Inf Retr 2008; 2(1-2): 1-135. https://doi.org/10.1561/1500000011
11. Blei DM, Ng AY, Jordan MI. Latent Dirichlet Allocation. J Mach Learn Res 2003; 3: 993-1022.
12. Boyd-Graber J, Hu Y, Mimno D. Applications of topic models. Found Trends Inf Retr 2017; 11(2-3): 143-296. https://doi.org/10.1561/1500000030
13. Schivinski B, Dabrowski D. The effect of social media communication on consumer perceptions of brands. J Mark Commun 2016; 22(2): 189-214. https://doi.org/10.1080/13527266.2013.871323
14. He W, Zha S, Li L. Social media competitive analysis and text mining: A case study in the pizza industry. Int J Inf Manage 2013; 33(3): 464-472. https://doi.org/10.1016/j.ijinfomgt.2013.01.001
15. Liu B. Sentiment analysis: Mining opinions, sentiments, and emotions. Cham, Switzerland: Nota, 2022.
16. Karamanli E. Makine öğrenmesi algoritmaları kullanarak, metin madenciliği ve duygu analizi ile müşteri deneyiminin geliştirilmesi. MSc, Sosyal Bilimler Enstitüsü, 2019.
17. Sezgin M, Duman A. Elektronik ağızdan ağıza pazarlama kapsamında konaklama işletmelerine yönelik çevrimiçi yorumların duygu analizi yöntemiyle incelenmesi: Alanya örneği. Turk Turizm Arastirmalari Derg 2023; 7(2): 244-265. https://doi.org/10.26677/TR1010.2023.1240
18. Demirbilek M, Demirbilek SÖ. Google yorumları üzerinden makine öğrenme yöntemleri ve amazon comprehend ile duygu analizi: İç Anadolu’da bir üniversite örneği. Univ Arastirmalari Derg 2023; 6(4): 452-461. https://doi.org/10.32329/uad.1383794
19. Tuzcu S. Çevrimiçi kullanıcı yorumlarının duygu analizi ile sınıflandırılması. ETDUAM Bilisim Derg 2020; 1(2): 1-5.
20. Kılıçer S, Şamlı R. E-ticaret sitelerindeki Türkçe ürün yorumları üzerine makine öğrenmesi algoritmaları ile duygu analizi. Veri Bilimi 2023; 6(2): 15-23.
21. Yılmaz F, Adalı GK. Metin Madenciliği yaklaşımı ile e-ticaret sitesi uygulamalarının müşteri yorumlarına yönelik duygu analizi. Fenerbahçe Univ Sos Bilim Derg 2024; 4(2): 57-75. https://doi.org/10.58620/fbujoss.1558727
22. Trendyol. Biz Kimiz. 2024 [cited 2024 15.10.2024]; Available from: https://www.trendyol.com/aboutus
23. GooglePlay. Yorumlar. 2024 [cited 2024 16.06.2024]; Available from: https://play.google.com/store/search?q=trendyol&c=apps
24. Talib R, et al. Text mining: techniques, applications and issues. Int J Adv Comput Sci Appl 2016; 7(11): 414-418. https://doi.org/10.14569/IJACSA.2016.071153
25. Kayakuş M, Yiğit Açıkgöz F. Classification of news texts by categories using machine learning methods. Alphanumeric J 2022; 10(2): 155-166. https://doi.org/10.17093/alphanumeric.1149753
26. Joshi AK. Natural language processing. Science 1991; 253(5025): 1242-1249. https://doi.org/10.1126/science.253.5025.1242
27. Doğuc O. Twitter verisi ile doğal afet müdahale süreci için karar destek uygulaması. Afet Risk Derg 2022; 5(2): 408-419. https://doi.org/10.35341/afet.1144350
28. Pant VK, Sharma R, Kundu S. An overview of stemming and lemmatization techniques. Adv Netw Intell Comput 2024: 308-321. https://doi.org/10.1201/9781003430421-31
29. Şahin H, et al. Sağlık kuruluşlarının kurumsal itibarının metin madenciliği ve duygu analizi ile değerlendirilmesi. Mehmet Akif Ersoy Univ J Soc Sci Inst 2024; 40: 91-104. https://doi.org/10.20875/makusobed.1500054
30. Alhawarat M, Hegazi M. Revisiting k-means and topic modelling, a comparison study to cluster Arabic documents. IEEE Access 2018; 6: 42740-42749. https://doi.org/10.1109/ACCESS.2018.2852648
31. Kayan F, et al. Analysing sustainability and green energy with artificial intelligence: A Turkish English social media perspective. Sustainability 2025; 17(5). https://doi.org/10.3390/su17051882
32. Kayakuş M, Yiğit Açıkgöz F. Twitter’da makine öğrenmesi yöntemleriyle sahte haber tespiti. Abant Sos Bilim Derg 2023; 23(2): 1017-1027. https://doi.org/10.11616/asbi.1266179
33. Adnan K, Akbar R. An analytical study of information extraction from unstructured and multidimensional big data. J Big Data 2019; 6(1): 1-38. https://doi.org/10.1186/s40537-019-0254-8
34. Gupta S, Gupta S. Natural language processing in mining unstructured data from software repositories: A review. Sādhanā 2019; 44(12): 244. https://doi.org/10.1007/s12046-019-1223-9
35. Hemmatian F, Sohrabi MK. A survey on classification techniques for opinion mining and sentiment analysis. Artif Intell Rev 2019; 52(3): 1495-1545. https://doi.org/10.1007/s10462-017-9599-6
36. Sharma S, Jain A. Role of sentiment analysis in social media security and analytics. Wiley Interdiscip Rev Data Min Knowl Discov 2020; 10(5): e1366. https://doi.org/10.1002/widm.1366
37. Grljević O, Bošnjak Z. Sentiment analysis of customer data. Strateg Manag 2018; 23(3). https://doi.org/10.5937/StraMan1803038G
38. Kauffmann E, et al. Managing marketing decision-making with sentiment analysis: An evaluation of the main product features using text data mining. Sustainability 2019; 11(15): 4235. https://doi.org/10.3390/su11154235
39. Sohangir S, et al. Big Data: Deep Learning for financial sentiment analysis. J Big Data 2018; 5(1): 1-25. https://doi.org/10.1186/s40537-017-0111-6
40. Asghar MZ, et al. RIFT: A rule induction framework for Twitter sentiment analysis. Arab J Sci Eng 2018; 43(2): 857-877. https://doi.org/10.1007/s13369-017-2770-1
41. Yenkikar A, Babu N, Sangve S. R-SA: A Rule-based Expert System for Sentiment Analysis. In: IEEE Pune Section Int Conf (PuneCon); 2019. IEEE. https://doi.org/10.1109/PuneCon46936.2019.9105682
42. Kabir M, et al. An empirical research on sentiment analysis using machine learning approaches. Int J Comput Appl 2021; 43(10): 1011-1019. https://doi.org/10.1080/1206212X.2019.1643584
43. Liu Q, Hagenmeyer V, Keller HB. A review of rule learning-based intrusion detection systems and their prospects in smart grids. IEEE Access 2021; 9: 57542-57564. https://doi.org/10.1109/ACCESS.2021.3071263
44. Fadhli I, Hlaoua L, Omri MN. Sentiment analysis csam model to discover pertinent conversations in twitter microblogs. Int J Comput Netw Inf Secur 2022; 10(5): 28. https://doi.org/10.5815/ijcnis.2022.05.03
45. Kaur G, et al. Sentiment polarity analysis of love letters: evaluation of TextBlob, Vader, flair, and hugging face transformer. Comput Sci Inf Syst 2024; 40-40.
46. Murshed BAH, et al. Short text topic modelling approaches in the context of big data: taxonomy, survey, and analysis. Artif Intell Rev 2023; 56(6): 5133-5260. https://doi.org/10.1007/s10462-022-10254-w
47. Lee H, Kang P. Identifying core topics in technology and innovation management studies: A topic model approach. J Technol Transf 2018; 43: 1291-1317. https://doi.org/10.1007/s10961-017-9561-4
48. Jelodar H, et al. Latent Dirichlet allocation (LDA) and topic modelling: models, applications, a survey. Multimed Tools Appl 2019; 78: 15169-15211. https://doi.org/10.1007/s11042-018-6894-4
49. Bastani K, Namavari H, Shaffer J. Latent Dirichlet Allocation (LDA) for topic modelling of the CFPB consumer complaints. Expert Syst Appl 2019; 127: 256-271. https://doi.org/10.1016/j.eswa.2019.03.001
50. Onan A, Korukoglu S, Bulut H. LDA-based topic modelling in text sentiment classification: An empirical analysis. Int J Comput Linguist Appl 2016; 7(1): 101-119.
51. Maier D, et al. Applying LDA topic modelling in communication research: Toward a valid and reliable methodology. In: Computational Methods for Communication Science. Routledge, 2021. pp. 13-38.
52. Vangara R, et al. Finding the number of latent topics with semantic non-negative matrix factorization. IEEE Access 2021; 9: 117217-117231. https://doi.org/10.1109/ACCESS.2021.3106879
53. Tripathy BK, Sundareswaran A, Ghela S. Unsupervised learning approaches for dimensionality reduction and data visualization. Boca Raton, FL, USA: CRC Press, 2021. https://doi.org/10.1201/9781003190554
54. Khyani D, et al. An interpretation of lemmatization and stemming in natural language processing. J Univ Shanghai Sci Technol 2021; 22(10): 350-357.
55. Chai CP. Comparison of text preprocessing methods. Nat Lang Eng 2023; 29(3): 509-553. https://doi.org/10.1017/S1351324922000213
56. Angiani G, et al. A comparison between preprocessing techniques for sentiment analysis in Twitter. KDWeb 2016; 1748: 1-11.
57. Sarica S, Luo J. Stopwords in technical language processing. PLoS One 2021; 16(8): e0254937. https://doi.org/10.1371/journal.pone.0254937
58. Raut P, et al. Sentiment Analysis of Twitter. Int J Res Appl Sci Eng Technol 2022; 10(12): 621-627. https://doi.org/10.22214/ijraset.2022.47954
59. Abubakar B, Uppin C. A natural language processing approach to determine the polarity and subjectivity of iPhone 12 twitter feeds using TextBlob. Open J Phys Sci 2021; 2(2): 10-17. https://doi.org/10.52417/ojps.v2i2.276
60. Shirakawa M, Hara T, Nishio S. IDF for word n-grams. ACM Trans Inf Syst 2017; 36(1): 1-38. https://doi.org/10.1145/3052775
61. Ojo O, et al. Performance study of n-grams in the analysis of sentiments. J Niger Soc Phys Sci 2021: 477-483. https://doi.org/10.46481/jnsps.2021.201
62. Ahuja R, et al. The impact of features extraction on the sentiment analysis. Procedia Comput Sci 2019; 152: 341-348. https://doi.org/10.1016/j.procs.2019.05.008
63. Qaiser S, Ali R. Text mining: use of TF-IDF to examine the relevance of words to documents. Int J Comput Appl 2018; 181(1): 25-29. https://doi.org/10.5120/ijca2018917395
64. Mendez KM, et al. Toward collaborative open data science in metabolomics using Jupyter Notebooks and cloud computing. Metabolomics 2019; 15: 1-16. https://doi.org/10.1007/s11306-019-1588-0
65. Villarroel Ordenes F, Zhang S. From words to pixels: text and image mining methods for service research. J Serv Manag 2019; 30(5): 593-620. https://doi.org/10.1108/JOSM-08-2019-0254
66. Çaylak PÇ, et al. Analysing online reviews consumers’ experiences of mobile travel applications with sentiment analysis and topic modelling: The example of Booking and Expedia. Appl Sci 2024; 14(24): 11800.https://doi.org/10.3390/app142411800
67. Newman D, et al. Automatic evaluation of topic coherence. In: Human Language Technologies: NAACL 2010. 2010.
68. Aletras N, Stevenson M. Evaluating topic coherence using distributional semantics. In: Proc 10th Int Conf Comput Semantics (IWCS 2013). 2013.
69. Smith CA, et al. Beyond readability: Investigating coherence of clinical text for consumers. J Med Internet Res 2011; 13(4): e1842. https://doi.org/10.2196/jmir.1842
70. Lu Y, Mei Q, Zhai C. Investigating task performance of probabilistic topic models: an empirical study of PLSA and LDA. Inf Retr 2011; 14: 178-203. https://doi.org/10.1007/s10791-010-9141-9
71. Liu B. Sentiment analysis and opinion mining. Cham, Switzerland: Springer, 2022.
72. Wang Y, et al. How does social support promote consumers’ engagement in the social commerce community? The mediating effect of consumer involvement. Inf Process Manag 2020; 57(5): 102272. https://doi.org/10.1016/j.ipm.2020.102272
73. Hu N, Zhang J, Pavlou PA. Overcoming the J-shaped distribution of product reviews. Commun ACM 2009; 52(10): 144-147. https://doi.org/10.1145/1562764.1562803