Restaurant Review Sentiment and SWOT Analysis: using AWS and GPT-4 Large Language Models

Abstract

With the widespread use of the internet today, the emphasis on companies’ digital visibility and social media accounts has significantly increased the volume of reviews/feedback from end-users across various platforms. Accurately assessing users’ emotional states is of paramount importance for businesses in sustaining competitive advantage. This study conducted a sentiment analysis of Google Maps reviews for restaurants in Gaziantep, a city that stands out in gastronomy tourism, followed by a SWOT analysis based on the collected reviews. Initially, comments collected through web scraping techniques were processed in the preliminary phase. In the second phase, sentiment analysis was performed using machine learning methods frequently employed in the literature for sentiment analysis, such as logistic regression, support vector machine, and Gaussian naive Bayes, along with an ensemble learning method XGBoost and the deep learning method LSTM. Alongside these methods, large language models, such as AWS Comprehend and GPT-4, were integrated into our analysis using their development libraries. For a robust analysis, comments were analyzed in both Turkish and English, achieving success rates above 80% across all performance metrics for machine and deep learning methods and over 90% for AWS and GPT-4. While AWS does not support the Turkish language, GPT-4 has shown similar success rates in both the Turkish and English languages. A SWOT analysis was conducted in the final phase based on the aggregated comments. According to the analysis results, delicious meals, attentive staff, fast service, hygiene and cleanliness, and reasonable prices were identified as strengths, whereas overcrowding, noise, and delays in service were identified as weaknesses.

Keywords

• Machine Learning
• Deep Learning
• AWS Comprehend
• GPT-4
• Sentiment Analysis
• Gaziantep Restaurants

References

1. Adem, A., Çolak, A., & Dağdeviren, M. (2018). An integrated model using SWOT analysis and Hesitant fuzzy linguistic term set for evaluation occupational safety risks in life cycle of wind turbine. Safety Science, 106. google scholar
2. Agarwal, A., Xie, B., Vovsha, I., Rambow, O., & Passonneau, R. (2011). Sentiment Analysis of Twitter Data. LSM '11 Proceedings of the Workshop on Languages in Social Media, 30-38. google scholar
3. Agüero-Torales, M. M., Cobo, M. J., Herrera-Viedma, E., & López-Herrera, A. G. (2019). A cloud-based tool for sentiment analysis in reviews about restaurants on TripAdvisor. Procedia Computer Science, 162, 392-399. google scholar
4. Aksu, M. Ç., & Karaman, E. (2022). Turistik Mekanlara Yönelik Sosyal Medya Paylaşımlarının Yapay Zekâ Yöntemleriyle Değerlendirilmesi: Artvin İli Örneği. Journal of Tourism and Gastronomy Studies, 10(1), 505-524. google scholar
5. Asani, E., Vahdat-Nejad, H., & Sadri, J. (2021). Restaurant recommender system based on sentiment analysis. Machine Learning with Applications, 6 (100114), 1-10. https://doi.org/10.1016/j.mlwa.2021.100114 google scholar
6. AWS. (2024). Available, https://aws.amazon.com/tr/comprehend/, Accessed on, Mar. 01, 2024. google scholar
7. Benzaghta, M. A., Elwalda, A., Mousa, M. M., Erkan, I., & Rahman, M. (2021). SWOT analysis applications: An integrative literature review. Journal of Global Business Insights. 6, 1, 54-72. google scholar
8. Bird, S., Klein, E., & Loper, E. (2009). Natural Language Processing with Python: O'Reilly Media, Inc. google scholar

9. Büyükeke, A., Sökmen, A., & Gencer, C. (2020). Metin Madenciliği ve Duygu Analizi Yöntemleri ile Sosyal Medya Verilerinden Rekabetçi Avantaj Elde Etme: Turizm Sektöründe Bir Araştırma. Journal of Tourism and Gastronomy Studies, 8(1), 322-335. doi:10.21325/jotags.2020.550 google scholar
10. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. Paper presented at the KDD ’16, San Francisco, CA, USA. google scholar
11. Çekal, N., & Aktürk, H. (2019). Gaziantep mutfağına özgü çorbalara ilişkin müşteri değerlendirmelerinin incelenmesi. Journal of Tourism and Gastronomy Studies, 7(2), 1488–1498. https://doi.org/10.21325/jotags.2019.431 google scholar
12. Çevik, F., & Kilimci, Z. (2021). Derin öğrenme yöntemleri ve kelime yerleştirme modelleri kullanılarak Parkinson hastalığının duygu analiziyle değerlendirilmesi. Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi (PAJES), 27(2), 151–161. google scholar
13. Demirbilek, M., & Özulukale Demirbilek, S. (2023). Google Yorumları Üzerinden Makine Öğrenme Yöntemleri ve Amazon Comprehend ile Duygu Analizi: İç Anadoluda Bir Üniversite Örneği. Üniversite Araştırmaları Dergisi, 6(4), 452-461. https://doi.org/10.32329/uad.1383794 google scholar
14. Doaa Mohey El-Din Mohamed, H. (2018). A survey on sentiment analysis challenges. Journal of King Saud University - Engineering Sciences, 30(4), 330-338. https://doi.org/10.1016/j.jksues.2016.04.002 google scholar
15. Duarte Alonso, A., O'neill, M., Liu, Y., & O'shea, M. (2013). Factors driving consumer restaurant choice: An exploratory study from the Southeastern United States. Journal of Hospitality Marketing & Management, 22(5), 547-567. google scholar
16. Duman, E. (2022). Implementation of XGBoost Method for Healthcare Fraud Detection. Scientific Journal of Mehmet Akif Ersoy University, 5(2), 69-75. google scholar
17. Géron, A. (2022). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd Edition ed.): O'Reilly Media, Inc. google scholar
18. Gündüz, H. (2023). Derin Transformatörlerden Çift Yönlü Kodlayıcı Temsilleri ve Destek Vektör Makineleri ile Türkçe Film Yorumları Üzerine Duygu Analizi. KSÜ Mühendislik Bilimleri Dergisi, 26(2), 542-549. google scholar
19. Ha, J., & Jang, S. S. (2010). Effects of service quality and food quality: The moderating role of atmospherics in an ethnic restaurant segment. International Journal of Hospitality Management, 29(3), 520-529. google scholar
20. Hamad, M. M., Salih, M. A., & Jaleel, R. A. (2021). Sentiment analysis of restaurant reviews in social media using Naïve Bayes. Applications of Modelling and Simulation, 5, 166-172. google scholar
21. Hossain, N., Bhuiyan, M. R., Tumpa, Z. N., & Hossain, S. A. (2020, 1–3 July 2020). Sentiment analysis of restaurant reviews using combined CNN-LSTM. Paper presented at the 11th International Conference on Computing, Communication and Networking Technologies (ICCCNT), Kharagpur, India. google scholar
22. Instant Data Scraper. (2024). Available, https://chrome.google.com/webstore/detail/instant-data-scraper/ofaokhiedipichpaobibbnahnkdoiiah, Accessed on, Feb. 20, 2024. google scholar
23. Jonathan, B., Sihotang, J. I., & Martin, S. (2019, October). Sentiment analysis of customer reviews in zomato bangalore restaurants using random forest classifier. Paper presented at the International Scholars Conference. google scholar
24. Kang, H., Yoo, S. J., & Han, D. (2012). Senti-lexicon and improved Naïve Bayes algorithms for sentiment analysis of restaurant reviews. Expert Systems with Applications, 39(5), 6000-6010. google scholar
25. Kecman, V. (2005). Support vector machines: theory and applications: Springer Berlin Heidelberg. google scholar
26. Korkmaz, A., & Bulut, S. (2023). Social Media Sentiment Analysis for Solar Eclipse with Text Mining. Acta Infologica, 7(1). doi:https://doi.org/10.26650/acin.1207100 google scholar
27. Köksal, B., Erdem, G., Türkeli, C., & Kamışlı Öztürk, Z. (2021). Twitter’da Duygu Analizi Yöntemi Kullanılarak Bitcoin Değer Tahminlemesi. Düzce Üniversitesi Bilim ve Teknoloji Dergisi, 9, 280-297. doi:10.29130/dubited.792909 google scholar
28. Madsen, D. Ø. (2016). SWOT analysis: A management fashion perspective. International Journal of Business Research, 16(1), 39-56. google scholar
29. McIntyre‐Bhatty, Y. T. (2000). Neural network analysis and the characteristics of market sentiment in the financial markets. Expert Systems, 17(4), 191-198. google scholar
30. Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment Analysis Algorithms and Applications: A Survey. Ain Shams Engineering Journal, 5, 1093-1113. doi:http://dx.doi.org/10.1016/j.asej.2014.04.011 google scholar
31. NLTK. (2024). Available, https//www.nltk.org/, Accessed on, Feb. 20, 2024. google scholar
32. OpenAI. (2024). ChatGPT (Mar 14 version) [Large language model]. Available, [suspicious link removed], Accessed on, Apr. 15, 2024. google scholar
33. Özel, M., & Çetinkaya Bozkurt, Ö. (2024). Sentiment Analysis on GPT-4 with Comparative Models Using Twitter Data. Acta Infologica, 8(1), 23-33. https://doi.org/10.26650/acin.1418834 google scholar
34. Özen, İ. A. (2021). Yerel Restoranların Değerlendirilmesinde Fikir Madenciliği: Gaziantep Örneği (Opinion Mining in the Evaluation of Local Restaurants: The Case of Gaziantep). Journal of Tourism & Gastronomy Studies, 9(1), 377-391. google scholar
35. Öztürk, S. (2022). Bipolar Bozukluk Manik Atak Tanılı Hastaların Atak Şiddetinin Video Tabanlı Duygu Analizi ile Değerlendirilmesi. (Doktora Tezi), Trakya Üniversitesi Edirne. google scholar
36. Peters, C. M. (2024). The Power of Google Reviews for Restaurant Marketing. Available, https://restaurantsmarketing.com.au/blog/the-power-of-google-reviews-for-restaurant-marketing/#:~:text=Google%20reviews%20are%20extremely%20important,to%20rank%20in%20search%20results, Accessed on, Jan. 31, 2024. google scholar
37. Pisner, D. A., & Schnyer, D. M. (2020). Chapter 6 - Support vector machine. In A. Mechelli & S. Vieira (Eds.), Machine learning (pp. 101-121). google scholar
38. Ponnam, A., & Balaji, M. S. (2014). Matching visitation-motives and restaurant attributes in casual dining restaurants. International journal of hospitality management, 37, 47-57. google scholar
39. Renganathan, V., & Upadhya, A. (2021). Dubai restaurants: A sentiment analysis of tourist reviews. Academica Turistica - Tourism and Innovation Journal, 14(2). doi:https://doi.org/10.26493/2335-4194.14.165-174 google scholar
40. Rita, P., Vong, C., Pinheiro, F., & Mimoso, J. (2023). A sentiment analysis of Michelin-starred restaurants. European Journal of Management and Business Economics, 32(3), 276-295. google scholar
41. Rozmi, A. N. A., Nordin, A., & Bakar, M. I. A. (2018). The perception of ICT adoption in small medium enterprise: A SWOT analysis. International Journal of Innovation Business Strategy, 19(1), 69-79. google scholar
42. Scikit-learn (2025). Available, https://scikit-learn.org/stable/supervised_learning.html, Accessed on, May. 25, 2025 google scholar
43. Shin, B., Ryu, S., Kim, Y., & Kim, D. (2022). Analysis on Review Data of Restaurants in Google Maps through Text Mining: Focusing on Sentiment Analysis Journal of Multimedia Information System, 9(1), 61-68. google scholar
44. Singgalen, Y. A. (2022). Sentiment Analysis on Customer Perception towards Products and Services of Restaurant in Labuan Bajo Journal of Information Systems and Informatics, 4(3), 511-523. google scholar
45. Tuna, M. F. (2022). Mobil Uygulama Müşteri Geri Bildirimindeki Duyguların Makine Öğrenmesi Yöntemleriyle Sınıflandırılması. Journal of Business and Communication Studies, 1(1), 83-103. http://dx.doi.org/10.29228/jobacs.63080 google scholar
46. Uçuk, C., & Kayran, M. (2020). Gaziantep mutfağının tarihsel gelişimi: Milli mücadele döneminde Gaziantep’te yeme içme faaliyetleri. Safran Kültür ve Turizm Araştırmaları Dergisi, 3(2), 258–272. google scholar
47. Ustabulut, M. Y. (2021). SWOT Analysis for the Distance Education Process of Lecturers Teaching Turkish as a Foreign Language. Educational Policy Analysis and Strategic Research, 16(1), 139-152. https://doi.org/10.29329/epasr.2020.334.8 google scholar
48. Uyaroğlu Akdeniz, F. N., & Cebeci, H. İ. (2021). Belediye Hizmetlerin Değerlendirilmesinde Duygu Analizi Yaklaşımı: Sakarya İli Örneği. Zeki Sistemler Teori ve Uygulamaları Dergisi, 4(2), 127-135. doi:10.38016/jista.932762 google scholar
49. Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731-5780. doi:https://doi.org/10.1007/s10462-022-10144-1 google scholar
50. Web of Science (2024), https://www.webofscience.com/, Accessed on, Feb. 20, 2024. google scholar
51. XGBoost. (2025, May 25). XGBoost Python Package Python Package Introduction. https://xgboost.readthedocs.io/en/stable/python/python_intro.html google scholar
52. Ylimaki, E. (2024). Why Google Restaurant Reviews Are a Must, Available https://trustmary.com/reviews/why-google-restaurant-reviews-are-a-must/, Accessed on, Jan. 31, 2024. google scholar
53. Yu, B., Zhou, J., Zhang, Y., & Cao, Y. (2017). Identifying restaurant features via sentiment analysis on yelp reviews. arXiv preprint arXiv:1709.08698, 1-6. google scholar
54. Yu, T., Rita, P., Moro, S., & Oliveira, C. (2022). Insights from sentiment analysis to leverage local tourism business in restaurants. International Journal of Culture, Tourism and Hospitality Research, 16(1), 321-336. google scholar
55. Yüksel, A. S., & Tan, F. G. (2018). Metin Madenciliği Teknikleri ile Sosyal Ağlarda Bilgi Keşfi. Mühendislik Bilimleri ve Tasarım Dergisi, 6(2), 324-333. https://doi.org/10.21923/jesd.384791 google scholar
56. Zeng, B. (2013). Social Media in Tourism. J Tourism Hospit 2(1), 1-2. http://dx.doi.org/10.4172/2167-0269.1000e125 google scholar
57. Zhou, X., Wan, X., & Xiao, J. (2016, November 1-5, 2016). Attention-based LSTM network for cross-lingual sentiment classification, Austin, Texas. google scholar