Modeling the Link Between the Thematic Structure of User-Generated Content and the Quality of Reverse Logistics Decisions Using Topic Modeling and Sentiment Analysis
Keywords:
Reverse logistics, user, generated content, topic modeling, sentiment analysis, text mining, data, driven decision, makingAbstract
This study aims to model the relationship between the thematic structure of user-generated content and the quality of reverse logistics decisions using topic modeling and sentiment analysis techniques. This study employed a descriptive-analytical approach based on text mining techniques. The dataset consisted of 4,850 unstructured textual entries collected from social media platforms over a 90-day period, reflecting user opinions about a mobile phone brand. After preprocessing using natural language processing tools, Latent Dirichlet Allocation (LDA) was applied to extract thematic structures. Sentiment analysis was conducted using deep learning models, including LSTM, GRU, and transformer architectures. Model performance was evaluated using confusion matrices for both binary and multi-class classification, and the relationships among topics, sentiment polarity, and reverse logistics decision quality were analyzed. The results indicated that after-sales service, with the highest proportion of negative sentiment, significantly reduces the quality of reverse logistics decisions, whereas user experience contributes most positively to customer perception. The transformer model demonstrated superior performance compared to LSTM and GRU in sentiment classification tasks. The integrated analysis of topics and sentiments revealed that combining these approaches enhances the identification of key drivers of product returns and improves operational decision-making. The findings suggest that integrating topic modeling and sentiment analysis of user-generated content provides an effective framework for improving reverse logistics decision quality, enabling organizations to reduce return rates and enhance customer satisfaction.
Downloads
References
Aattouchi, I., Mounir, A. K., Mendili, S. E., & Elmendili, F. (2022). Financial Sentiment Analysis of Tweets Based on Deep Learning Approach. Indonesian Journal of Electrical Engineering and Computer Science, 25(3), 1759. https://doi.org/10.11591/ijeecs.v25.i3.pp1759-1770
Artar, M., Balcıoğlu, Y. S., & Erdil, O. (2025). Teleworking Sentiments on X: Navigating the Shift From the Digital Advancement Era to a Post-Covid World. Sage Open, 15(2). https://doi.org/10.1177/21582440251346548
Asgari, T., Daneshvar, A., Chobar, A. P., Ebrahimi, M., & Abrahamyan, S. (2022). Identifying Key Success Factors for Startups With Sentiment Analysis Using Text Data Mining. International Journal of Engineering Business Management, 14. https://doi.org/10.1177/18479790221131612
Balcıoğlu, Y. S. (2024). Assessing the Value of Black Friday Promotions: An Analysis of Instagram Users’ Sentiments and Behavioral Responses. Ekev Akademi Dergisi(97), 267-282. https://doi.org/10.17753/sosekev.1389245
Blank, C., McBurney, M., Morgan, M., & Seetan, R. (2021). A Survey of Big Data Techniques for Extracting Information From Social Media Data. Advances in Science Technology and Engineering Systems Journal, 6(3), 189-204. https://doi.org/10.25046/aj060322
Calderón-Fajardo, V., Puig-Cabrera, M., & Rodríguez‐Rodríguez, I. (2024). Deciphering Tourism’s Role in Antarctica’s Geosocial Concerns Through Data Mining Techniques. Land, 13(6), 843. https://doi.org/10.3390/land13060843
Chen, H., & Zhu, Y. (2023). Improved TF-IDF-Based LDA Topic Clustering Model for Specific Commodity Contexts and Different Sentiment Tendencies. https://doi.org/10.3233/faia230934
Chen, Q., Liu, R., Jiang, Q., & Xu, S. (2024). Exploring Cross-Cultural Disparities in Tourists' Perceived Images: A Text Mining and Sentiment Analysis Study Using LDA and BERT-BILSTM Models. Data Technologies and Applications, 58(4), 669-690. https://doi.org/10.1108/dta-10-2023-0645
Dang, D. T. (2024). Utilizing Large Datasets: Evaluating Tourists' Views on Sustainable Tourism in the Mekong Delta via Tripadvisor Feedback. Contaduría y administración, 70(1), 485. https://doi.org/10.22201/fca.24488410e.2025.5227
Dash, S. B., & Jain, A. (2022). Experience From E-Government Services: A Topic Model Approach. IIM Kozhikode Society & Management Review, 14(1), 61-74. https://doi.org/10.1177/22779752221126571
Gourisaria, M. K., Chandra, S., Das, H., Patra, S. S., Sahni, M., León‐Castro, E., Singh, V., & Kumar, S. (2022). Semantic Analysis and Topic Modelling of Web-Scrapped COVID-19 Tweet Corpora Through Data Mining Methodologies. Healthcare, 10(5), 881. https://doi.org/10.3390/healthcare10050881
Guerreiro, J., & Loureiro, S. M. C. (2022). Unraveling E-Wom Patterns Using Text Mining and Sentiment Analysis. 433-445. https://doi.org/10.4018/978-1-6684-6303-1.ch024
Hussain, J., Azhar, Z., Ahmad, H. F., Afzal, M., Raza, M., & Lee, S. (2022). User Experience Quantification Model From Online User Reviews. Applied Sciences, 12(13), 6700. https://doi.org/10.3390/app12136700
Kar, A. K., Kumar, S., & Ilavarasan, P. V. (2021). Modelling the Service Experience Encounters Using User-Generated Content: A Text Mining Approach. Global Journal of Flexible Systems Management, 22(4), 267-288. https://doi.org/10.1007/s40171-021-00279-5
Khanam, Z. (2023). Sentiment Analysis of User Reviews in an Online Learning Environment: Analyzing the Methods and Future Prospects. European Journal of Education and Pedagogy, 4(2), 209-217. https://doi.org/10.24018/ejedu.2023.4.2.531
Li, S., Liu, F., Zhang, Y., Zhu, B., Zhu, H., & Yu, Z. (2022). Text Mining of User-Generated Content (UGC) for Business Applications in E-Commerce: A Systematic Review. Mathematics, 10(19), 3554. https://doi.org/10.3390/math10193554
Liu, Y., Zhang, D., Wan, Q., & Lin, Z. (2025). Innovative Mining of User Requirements Through Combined Topic Modeling and Sentiment Analysis: An Automotive Case Study. Sensors, 25(6), 1731. https://doi.org/10.3390/s25061731
Mahadevan, A., & Arock, M. (2020). Integrated Topic Modeling and Sentiment Analysis: A Review Rating Prediction Approach for Recommender Systems. Turkish Journal of Electrical Engineering & Computer Sciences, 28(1), 107-123. https://doi.org/10.3906/elk-1905-114
Mishra, M. (2021). Customer Experience: Extracting Topics From Tweets. International Journal of Market Research, 64(3), 334-353. https://doi.org/10.1177/14707853211047515
Mohamed, A., Al-Feel, H., & Taie, S. A. (2023). Food Interests Analysis (FIA) Model to Extract the Food Preferences and Interests of Twitter Users. Labyrinth Fayoum Journal of Science and Interdisciplinary Studies, 1(1), 31-48. https://doi.org/10.21608/ifjsis.2023.204964.1010
Ong, S. Q., Pauzi, M. B. M., & Gan, K. H. (2022). Text Mining and Determinants of Sentiments Towards the COVID-19 Vaccine Booster of Twitter Users in Malaysia. Healthcare, 10(6), 994. https://doi.org/10.3390/healthcare10060994
Pan, X., & Xu, Y. (2023). Advancements of Artificial Intelligence Techniques in the Realm About Library and Information Subject—A Case Survey of Latent Dirichlet Allocation Method. IEEE Access, 11, 132627-132640. https://doi.org/10.1109/access.2023.3334619
Regitz, D., Höpken, W., & Fuchs, M. (2024). UGC-Based Factors Influencing Customer Satisfaction Pre and Post COVID-19: The Case of Lake Constance. 373-384. https://doi.org/10.1007/978-3-031-58839-6_39
Reyes-Menéndez, A., Saura, J. R., & Filipe, A. (2020). Marketing Challenges in the #MeToo Era: Gaining Business Insights Using an Exploratory Sentiment Analysis. Heliyon, 6(3), e03626. https://doi.org/10.1016/j.heliyon.2020.e03626
Saranya, S., & Usha, G. (2023). A Machine Learning-Based Technique With Intelligent WordNet Lemmatize for Twitter Sentiment Analysis. Intelligent Automation & Soft Computing, 36(1), 339-352. https://doi.org/10.32604/iasc.2023.031987
Saura, J. R., Palacios‐Marqués, D., & Soriano, D. R. (2023). Leveraging SMEs Technologies Adoption in the Covid-19 Pandemic: A Case Study on Twitter-Based User-Generated Content. The Journal of Technology Transfer, 48(5), 1696-1722. https://doi.org/10.1007/s10961-023-10023-z
Saura, J. R., Reyes-Menéndez, A., Matos, N., & Correia, M. B. (2021). Identifying Startups Business Opportunities From UGC on Twitter Chatting: An Exploratory Analysis. Journal of Theoretical and Applied Electronic Commerce Research, 16(6), 1929-1944. https://doi.org/10.3390/jtaer16060108
Shokouhyar, S., Shokoohyar, S., & Mirzaei, S. (2023). Stakeholders' Engagement Through Social Media Analytics in Promoting Sustainable Development Practices in the Mobile Supply Chain: A Cross‐country Analysis. Business Strategy and the Environment, 32(8), 5807-5820. https://doi.org/10.1002/bse.3449
Skeen, S. J., Jones, S. S., Cruse, C. M., & Horvath, K. J. (2022a). Integrating Natural Language Processing and Interpretive Thematic Analyses to Gain Human-Centered Design Insights on HIV Mobile Health: Proof-of-Concept Analysis. JMIR human factors, 9(3), e37350. https://doi.org/10.2196/37350
Skeen, S. J., Jones, S. S., Cruse, C. M., & Horvath, K. J. (2022b). Integrating Natural Language Processing and Interpretive Thematic Analyses to Gain Human-Centered Design Insights on HIV Mobile Health: Proof-of-Concept Analysis (Preprint). https://doi.org/10.2196/preprints.37350
Tounsi, A., & Temimi, M. (2023). A Systematic Review of Natural Language Processing Applications for Hydrometeorological Hazards Assessment. Natural Hazards, 116(3), 2819-2870. https://doi.org/10.1007/s11069-023-05842-0
Vigneshwaran, P., Nithiyanandam, P., Manickavasagam, S., Islabudeen, M., Jaganathan, R., & Balasubramanian, M. K. (2022). A Comprehensive Analysis of Consumer Decisions on Twitter Dataset Using Machine Learning Algorithms. Iaes International Journal of Artificial Intelligence (Ij-Ai), 11(3), 1085. https://doi.org/10.11591/ijai.v11.i3.pp1085-1093
Wang, Y., Wei, M., Wang, P., Gao, Y., Tian, Y., Meng, N., Liu, H., Zhang, X., Wang, K., & Wu, Q. (2025). Insight Into Public Sentiment and Demand in China’s Public Health Emergency Response: A Weibo Data Analysis. BMC public health, 25(1). https://doi.org/10.1186/s12889-025-22553-2
Zeng, S., Gao, L., Wu, J., Mao, M., & Peng, B. (2025). Employer Branding Multi-Criteria Comprehensive Evaluation Framework Based on Online Reviews and Intuitionistic Fuzzy Topsis-Lda-Kano Model. International Journal of Fuzzy System Applications, 14(1), 1-34. https://doi.org/10.4018/ijfsa.387385
Zhang, B. (2023). A BERT-CNN Based Approach on Movie Review Sentiment Analysis. SHS Web of Conferences, 163, 04007. https://doi.org/10.1051/shsconf/202316304007
