A Sentiment Analysis–Based Recommender System for Online Retail Stores Using Customer Social Media Data
Keywords:
Sentiment analysis, recommender systems, online retail, social media analytics, customer behavior, emotional intelligence, digital marketingAbstract
This study aimed to design and empirically evaluate a sentiment analysis–based recommender system and to examine its effects on recommendation quality, customer trust, satisfaction, and repurchase intention in online retail environments. The study employed an applied mixed-methods design combining computational modeling with behavioral analysis. Social media data were collected from major online retail brands in Tehran, yielding approximately 1.8 million text records. A sample of 360 active online shoppers and 60 domain experts participated in system evaluation. Natural language processing techniques, including deep learning–based sentiment classification models, were used to extract emotional information from user-generated content. The recommender system integrated sentiment scores with transactional and behavioral data through a hybrid recommendation framework. System performance and behavioral effects were assessed using standard recommendation metrics and survey-based instruments. The sentiment-based recommender system significantly outperformed conventional collaborative filtering and content-based models in precision, recall, F1-score, normalized discounted cumulative gain, and click-through rate. Regression analysis revealed that recommendation quality had significant positive effects on customer trust (β = 0.62, p < 0.001) and satisfaction (β = 0.58, p < 0.001). Trust (β = 0.54, p < 0.001) and satisfaction (β = 0.47, p < 0.001) both significantly predicted repurchase intention. Post-implementation measures indicated significant increases in purchase intention, customer satisfaction, platform trust, and average order value (p < 0.001). Integrating social media sentiment analysis into recommender systems substantially enhances system performance, customer engagement, and commercial outcomes, demonstrating the strategic value of emotionally intelligent personalization in online retail.
Downloads
References
Abubakar, B. U., & Uppin, C. (2021). A Natural Language Processing Approach to Determine the Polarity and Subjectivity of Iphone 12 Twitter Feeds Using Textblob. Open Journal of Physical Science (Issn 2734-2123), 2(2), 10-17. https://doi.org/10.52417/ojps.v2i2.276
Annisa, T., Kusumahadi, K., & Nurhazizah, E. (2022). Website Quality for E-Commerce Using Sentiment Analysis (Case Studies in Tokopedia and Shopee). https://doi.org/10.46254/eu05.20220462
Azizah, N. (2025). Effect Service Quality, Discount, Social Media Marketing Interactivity on Shoppers’loyalty With Online Trust as Intervening Variable User Reny Swalayan-Ku Surabaya. Green Inflation, 2(3), 138-150. https://doi.org/10.61132/greeninflation.v2i3.536
Banjarnahor, A. R., Setyawati, S. M., & Anggraeni, A. I. (2024). Staying Competitive in the Era of Digital Technology: The Importance of Using Social Media. Corporate Governance and Organizational Behavior Review, 8(2, special issue), 308-320. https://doi.org/10.22495/cgobrv8i2sip6
Baskar, T. (2021). Social Media Communication and Customer Loyalty With the Mediating Role of Social Customer Relationship in Retail Chain Stores in Sri Lanka. Ejbm. https://doi.org/10.7176/ejbm/13-14-09
Gunaningrat, R., Purwandari, S., Suyatno, A., & Hastuti, I. (2021). Consumer Shopping Preferences and Social Media Use During Covid-19 Pandemic. Jurnal Bisnisman Riset Bisnis Dan Manajemen, 3(2), 01-15. https://doi.org/10.52005/bisnisman.v3i2.42
Happ, E., Scholl‐Grissemann, U., Peters, M., & Schnitzer, M. (2020). Insights Into Customer Experience in Sports Retail Stores. International Journal of Sports Marketing and Sponsorship, 22(2), 312-329. https://doi.org/10.1108/ijsms-12-2019-0137
Hiriyannaiah, S., Siddesh, G. M., & Srinivasa, K. G. (2020). Real-Time Streaming Data Analysis Using a Three-Way Classification Method for Sentimental Analysis. 1377-1390. https://doi.org/10.4018/978-1-7998-2460-2.ch069
Ibrahim, N. F., & Wang, X. (2019). A Text Analytics Approach for Online Retailing Service Improvement: Evidence From Twitter. Decision Support Systems, 121, 37-50. https://doi.org/10.1016/j.dss.2019.03.002
Jones, E. C., Rodriguez, D., Gimeno, D., Kurian, A., & Tsai, J. (2023). The Role of Location in the Spread of SARS-CoV-2: Examination of Cases and Exposed Contacts in South Texas, Using Social Network Analysis. Disaster Medicine and Public Health Preparedness, 17. https://doi.org/10.1017/dmp.2023.189
Kalpana, B. (2022). Twitter and Instagram Sentiment Analysis of Covid. Journal of University of Shanghai for Science and Technology, 24(02), 349-351. https://doi.org/10.51201/jusst/22/0248
Karunarathne, P. D. A. I., & Wanninayake, W. M. C. B. (2025). Impact of Social Media Marketing on Brand Loyalty in Online Fashion Retail Industry in Sri Lanka (SDG 09): The Mediating Role of Brand Consciousness. JLSDGR, 5(8), e6049. https://doi.org/10.47172/2965-730x.sdgsreview.v5.n08.pe06049
Kim, C.-G., Hwang, Y.-J., & Kamyod, C. (2022). A Study of Profanity Effect in Sentiment Analysis on Natural Language Processing Using ANN. Journal of Web Engineering. https://doi.org/10.13052/jwe1540-9589.2139
Lappeman, J., Franco, M., Warner, V., & Sierra-Rubia, L. (2022). What Social Media Sentiment Tells Us About Why Customers Churn. Journal of Consumer Marketing, 39(5), 385-403. https://doi.org/10.1108/jcm-12-2019-3540
Li, B., Liu, X., & Zhang, R. (2024). Employing the BERT Model for Sentiment Analysis of Online Commentary. Applied and Computational Engineering, 32(1), 241-247. https://doi.org/10.54254/2755-2721/32/20230218
Li, Y., Tan, R., & Gong, X. (2022). How Omnichannel Integration Promotes Customer Word-of-Mouth Behaviors: The Mediating Roles of Perceived Personal Preference Fit and Perceived Social Relatedness. Information Technology and People, 36(4), 1726-1753. https://doi.org/10.1108/itp-06-2021-0440
Lim, J.-Y., & Anitsal, M. (2019). Retail Customer Sentiment Analysis: Customers' Reviews of Top Ten U.S. Retailers' Performance. Glob J MGMT MKTG, 3(1), 124-150. https://doi.org/10.47177/gjmm.03.01.2019.124
Liniņa, I., & Vēvere, V. (2020). Enhancement of Retail Consumer Loyalty in Latvia by Means of Social Media Communication. European Integration Studies, 1(14), 80-89. https://doi.org/10.5755/j01.eis.1.14.26829
Mukasheva, А. (2021). Tasks and Methods of Text Sentiment Analysis. Scientific Journal of Astana IT University(7), 55-62. https://doi.org/10.37943/aitu.2021.57.68.005
Safeer, A. A. (2024). Harnessing the Power of Brand Social Media Marketing on Consumer Online Impulse Buying Intentions: A Stimulus-Organism-Response Framework. Journal of Product & Brand Management, 33(5), 533-544. https://doi.org/10.1108/jpbm-07-2023-4619
Solanki, M. P. (2022). A Study on Emotion Detection &Amp; Classification From Text Using Machine Learning. Journal of Artificial Intelligence Machine Learning and Neural Network(22), 40-46. https://doi.org/10.55529/jaimlnn.22.40.46
Thallapalli, R., Narasimha, G., Kumar, P. P., Srinivas, K., & Pallavi, P. (2020). Sentiment Analysis for Multi-Attribute Data in OSNs Using Hybrid Approach. Iop Conference Series Materials Science and Engineering, 981(2), 022050. https://doi.org/10.1088/1757-899x/981/2/022050
Tiufany, B., & Lina, L. (2024). The Influence of Store Image, Store Atmosphere and Social Media Marketing on Purchase Decisions at Smartphone Retail Stores in Pekanbaru. Ijaeb, 2(1), 2832-2841. https://doi.org/10.24912/ijaeb.v2i1.2832-2841
Wahyudi, D., & Sibaroni, Y. (2022). Deep Learning for Multi-Aspect Sentiment Analysis of TikTok App Using the RNN-LSTM Method. Building of Informatics Technology and Science (Bits), 4(1). https://doi.org/10.47065/bits.v4i1.1665
Waltenrath, A., Brenner, C., & Hinz, O. (2022). Some Interactions Are More Equal Than Others: The Effect of Influencer Endorsements in Social Media Brand Posts on Engagement and Online Store Performance. Journal of Interactive Marketing, 57(4), 541-560. https://doi.org/10.1177/10949968221096591
Wang, L., Isomura, S., Ptaszyński, M., Dybała, P., Urabe, Y., Rzepka, R., & Masui, F. (2024). The Limits of Words: Expanding a Word-Based Emotion Analysis System With Multiple Emotion Dictionaries and the Automatic Extraction of Emotive Expressions. Applied Sciences, 14(11), 4439. https://doi.org/10.3390/app14114439
Weinandy, T. J., Chen, K., Pozo, S., & Ryan, M. J. (2023). Twitter-Patter: How Social Media Drives Foot Traffic to Retail Stores. Journal of Marketing Analytics, 12(3), 551-569. https://doi.org/10.1057/s41270-023-00209-7
White, B. M., Melton, C., Zareie, P., Davis, R. L., Bednarczyk, R. A., & Shaban‐Nejad, A. (2023). Exploring Celebrity Influence on Public Attitude Towards the COVID-19 Pandemic: Social Media Shared Sentiment Analysis. BMJ Health & Care Informatics, 30(1), e100665. https://doi.org/10.1136/bmjhci-2022-100665
Zavala-Huerta, A. (2023). Implementation of an E-Commerce Sales Channel for Small and Medium- Sized Businesses. Journal of Administration and Finance, 6-13. https://doi.org/10.35429/jaf.2023.27.10.6.13
Zhou, L., Zhang, Z., Zhao, L., & Yang, P. (2022). Microblog Sentiment Analysis Based on Deep Memory Network With Structural Attention. Complex & Intelligent Systems, 9(3), 3071-3083. https://doi.org/10.1007/s40747-022-00904-5
Zhou, S., & Hudin, N. S. (2025). How Does in-Store and Online Shopping Experiences Influence Repurchase Intentions in Shandong, China? Roles of Perceived Value, Brand Trust, and Customer Satisfaction. PLoS One, 20(8), e0321485. https://doi.org/10.1371/journal.pone.0321485
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2026 Amir Vaziry (Corresponding author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
