Massive online reviews play a crucial role in mining customer requirements. However, existing research has three limitations: (1) the inadequate capture of contextual semantics in traditional text classification models, (2) the lack of sentiment analysis targeted at the product attribute level, and (3) the neglect of inter-attribute dependencies in requirement analysis. To address these gaps, this study proposed a requirement extraction and analysis method (REAM) that integrated multi-sentiment reviews. Specifically, a multi-domain adaptive BERT–BiLSTM–hierarchical position-aware network (HPANet) was developed for the fine-grained classification of reviews to automatically categorize them into nine key product attributes (for example, cost-performance ratio and appearance) that served as concrete manifestations of customer requirements. For requirements analysis, this method examined three dimensions: customer attention to product features, sentiment orientation toward specific attributes, and inter-attribute dependencies, thereby facilitating a comprehensive understanding of customer requirements. In the requirement extraction phase, the experimental results demonstrated that the proposed model achieved 1.2% higher classification accuracy than the conventional BERT model on a custom-built customer requirement dataset. To further verify the stability of the BERT–BiLSTM–HPANet model, additional validation was conducted on public datasets (CNews and ChnSentiCorp), revealing significant improvements in both the accuracy and F1-score compared with the baseline models.

1. [1] M. Zhang, L. Sun, G. A. Wang, Y. Li, and S. He, “Using neutral sentiment reviews to improve customer requirement identification and product design strategies,” Int. J. of Production Economics, Vol.254, Article No.108641, 2022. https://doi.org/10.1016/j.ijpe.2022.108641
2. [2] X. Yue and Y. Kodono, “Text mining analysis of user experience in C2C e-commerce based on reviews of the flea market on App Mercari,” J. Adv. Comput. Intell. Intell. Inform., Vol.29, No.3, pp. 500-507, 2025. https://doi.org/10.20965/jaciii.2025.p0500
3. [3] S. Guha and S. Kumar, “Emergence of big data research in operations management, information systems, and healthcare: Past contributions and future roadmap,” Production and Operations Management, Vol.27, No.9, pp. 1724-1735, 2018. https://doi.org/10.1111/poms.12833
4. [4] M. Mameli et al., “Deep learning approaches for fashion knowledge extraction from social media: A review,” IEEE Access, Vol.10, pp. 1545-1576, 2021. https://doi.org/10.1109/access.2021.3137893
5. [5] Y. Wang, L. Luo, and H. Liu, “Bridging the semantic gap between customer needs and design specifications using user-generated content,” IEEE Trans. on Engineering Management, Vol.69, No.4, pp. 1622-1634, 2022. https://doi.org/10.1109/tem.2020.3021698
6. [6] I. Brace, “Questionnaire Design: How to Plan, Structure and Write Survey Material for Effective Market Research,” 4th Edition, Kogan Page, 2018.
7. [7] S. Park and H. Kim, “Extracting product design guidance from online reviews: An explainable neural network-based approach,” Expert Systems with Applications, Vol.236, Article No.121357, 2024. https://doi.org/10.1016/j.eswa.2023.121357
8. [8] K. Park, S. Park, and J. Joung, “Contextual meaning-based approach to fine-grained online product review analysis for product design,” IEEE Access, Vol.12, pp. 4225-4238, 2024. https://doi.org/10.1109/access.2023.3343501
9. [9] X. Li, Y. Zhang, and L. Mei, “Analyzing online reviews of foreign tourists to destination attractions in china: A novel text mining approach,” Asia Pacific J. of Tourism Research, Vol.28, No.7, pp. 647-666, 2023. https://doi.org/10.1080/10941665.2023.2255315
10. [10] J.-W. Bi, Y. Liu, Z.-P. Fan, and J. Zhang, “Wisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews,” Tourism Management, Vol.70, pp. 460-478, 2019. https://doi.org/10.1016/j.tourman.2018.09.010
11. [11] J. Büschken and G. M. Allenby, “Sentence-based text analysis for customer reviews,” Marketing Science, Vol.35, No.6, pp. 953-975, 2016. https://doi.org/10.1287/mksc.2016.0993
12. [12] F. Fabiano and F. Martens, “Shifting towards smart, connected products: A business model innovation perspective,” Master’s thesis, Norwegian School of Economics, 2018.
13. [13] S. Yin, Y. Wang, and S. Shafiee, “Ranking products through online reviews considering the mass assignment of features based on bert and q q-rung orthopair fuzzy set theory,” Expert Systems with Applications, Vol.213, Part C, Article No.119142, 2023. https://doi.org/10.1016/j.eswa.2022.119142
14. [14] J. Kim, S. Park, and H. M. Kim, “Analysis of dynamic changes in customer sentiment on product features after the outbreak of COVID-19 based on online reviews,” J. of Mechanical Design, Vol.144, No.2, Article No.024501, 2022. https://doi.org/10.1115/1.4052789
15. [15] A. S. Abrahams, J. Jiao, G. A. Wang, and W. Fan, “Vehicle defect discovery from social media,” Decision Support Systems, Vol.54, No.1, pp. 87-97, 2012. https://doi.org/10.1016/j.dss.2012.04.005
16. [16] J. Joung and H. M. Kim, “Automated keyword filtering in latent Dirichlet allocation for identifying product attributes from online reviews,” J. of Mechanical Design, Vol.143, No.8, Article No.084501, 2021. https://doi.org/10.1115/1.4048960
17. [17] M. Zhang, L. Sun, Y. Li, G. A. Wang, and Z. He, “Using supplementary reviews to improve customer requirement identification and product design development,” J. of Management Science and Engineering, Vol.8, No.4, pp. 584-597, 2023. https://doi.org/10.1016/j.jmse.2023.03.001
18. [18] A. Choudhary and A. Arora, “Assessment of bidirectional transformer encoder model and attention based bidirectional LSTM language models for fake news detection,” J. of Retailing and Consumer Services, Vol.76, Article No.103545, 2024. https://doi.org/10.1016/j.jretconser.2023.103545
19. [19] A. Griffin and J. R. Hauser, “The voice of the customer,” Marketing Science, Vol.12, No.1, pp. 1-27, 1993. https://doi.org/10.1287/mksc.12.1.1
20. [20] F. Zhou, J. Ayoub, Q. Xu, and X. J. Yang, “A machine learning approach to customer needs analysis for product ecosystems,” J. of Mechanical Design, Vol.142, No.1, Article No.011101, 2020. https://doi.org/10.1115/1.4044435
21. [21] T. Ferguson, M. Greene, F. Repetti, K. Lewis, and S. Behdad, “Combining anthropometric data and consumer review content to inform design for human variability,” ASME 2015 Int. Design Engineering Technical Conf. and Computers and Information in Engineering Conf., Article No.V02BT03A022, 2015. https://doi.org/10.1115/DETC2015-47640
22. [22] J. Liu, Y. Zhou, X. Jiang, and W. Zhang, “Consumers’ satisfaction factors mining and sentiment analysis of B2C online pharmacy reviews,” BMC Medical Informatics and Decision Making, Vol.20, Article No.194, 2020. https://doi.org/10.1186/s12911-020-01214-x
23. [23] Y. Guo, S. J. Barnes, and Q. Jia, “Mining meaning from online ratings and reviews: Tourist satisfaction analysis using latent Dirichlet allocation,” Tourism Management, Vol.59, pp. 467-483, 2017. https://doi.org/10.1016/j.tourman.2016.09.009
24. [24] M. Venugopalan and D. Gupta, “An enhanced guided LDA model augmented with BERT based semantic strength for aspect term extraction in sentiment analysis,” Knowledge-Based Systems, Vol.246, Article No.108668, 2022. https://doi.org/10.1016/j.knosys.2022.108668
25. [25] A. Timoshenko and J. R. Hauser, “Identifying customer needs from user-generated content,” Marketing Science, Vol.38, No.1, pp. 1-20, 2019. https://doi.org/10.1287/mksc.2018.1123
26. [26] C. S. Tucker and H. M. Kim, “Trending mining for predictive product design,” J. of Mechanical Design, Vol.133, No.11, Article No.111008, 2011. https://doi.org/10.1115/1.4004987
27. [27] M. Long, M. Erickson, and E. F. MacDonald, “Consideration-constrained engineering design for strategic insights,” J. of Mechanical Design, Vol.141, No.6, Article No.064501, 2019. https://doi.org/10.1115/1.4041916
28. [28] Y. Zhan, R. Han, M. Tse, M. H. Ali, and J. Hu, “A social media analytic framework for improving operations and service management: A study of the retail pharmacy industry,” Technological Forecasting and Social Change, Vol.163, Article No.120504, 2021. https://doi.org/10.1016/j.techfore.2020.120504
29. [29] M. Zhang, B. Fan, N. Zhang, W. Wang, and W. Fan, “Mining product innovation ideas from online reviews,” Information Processing & Management, Vol.58, No.1, Article No.102389, 2021. https://doi.org/10.1016/j.ipm.2020.102389
30. [30] Q. Fan, H. Huang, J. Guan, and R. He, “Rethinking local perception in lightweight vision transformer,” arXiv:2303.17803, 2023. https://doi.org/10.48550/arXiv.2303.17803
31. [31] H. Wang et al., “TokenFormer: Rethinking transformer scaling with tokenized model parameters,” arXiv:2410.23168, 2024. https://doi.org/10.48550/arXiv.2410.23168
32. [32] K. Ertürk, F. Altınışık, İ. Sarıaltın, and Ö. N. Gerek, “TSLFormer: A lightweight transformer model for Turkish sign language recognition using skeletal landmarks,” arXiv:2505.07890, 2025. https://doi.org/10.48550/arXiv.2505.07890
33. [33] D. Zhang, Z. Shen, and Y. Li, “Requirement analysis and service optimization of multiple category fresh products in online retailing using importance-Kano analysis,” J. of Retailing and Consumer Services, Vol.72, Article No.103253, 2023. https://doi.org/10.1016/j.jretconser.2022.103253
34. [34] J.-W. Bi, Y. Liu, Z.-P. Fan, and E. Cambria, “Modelling customer satisfaction from online reviews using ensemble neural network and effect-based Kano model,” Int. J. of Production Research, Vol.57, No.22, pp. 7068-7088, 2019. https://doi.org/10.1080/00207543.2019.1574989
35. [35] H. Sun, W. Guo, L. Wang, and B. Rong, “An analysis method of dynamic requirement change in product design,” Computers & Industrial Engineering, Vol.171, Article No.108477, 2022. https://doi.org/10.1016/j.cie.2022.108477
36. [36] Q. Meng and J. Dong, “Future direction and visual analysis of Kano model: A literature review,” J. of Service Science and Management, Vol.11, No.4, pp. 399-413, 2018. https://doi.org/10.4236/jssm.2018.114028
37. [37] Y. Huang et al., “Combining deep learning with knowledge graph for design knowledge acquisition in conceptual product design,” CMES – Computer Modeling in Engineering and Sciences, Vol.138, No.1, pp. 167-200, 2023. https://doi.org/10.32604/cmes.2023.028268
38. [38] A. Liu, D. Zhang, Y. Wang, and X. Xu, “Knowledge graph with machine learning for product design,” CIRP Annals, Vol.71, No.1, pp. 117-120, 2022. https://doi.org/10.1016/j.cirp.2022.03.025
39. [39] S. Sarica, J. Luo, and K. L. Wood, “TechNet: Technology semantic network based on patent data,” Expert Systems with Applications, Vol.142, Article No.112995, 2020. https://doi.org/10.1016/j.eswa.2019.112995
40. [40] Q. Zhou, Z. Xu, and N. Y. Yen, “User sentiment analysis based on social network information and its application in consumer reconstruction intention,” Computers in Human Behavior, Vol.100, pp. 177-183, 2019. https://doi.org/10.1016/j.chb.2018.07.006
41. [41] Y. Wang, X. Lu, and Y. Tan, “Impact of product attributes on customer satisfaction: An analysis of online reviews for washing machines,” Electronic Commerce Research and Applications, Vol.29, pp. 1-11, 2018. https://doi.org/10.1016/j.elerap.2018.03.003
42. [42] M. S. Farooq, M. Salam, A. Fayolle, N. Jaafar, and K. Ayupp, “Impact of service quality on customer satisfaction in Malaysia airlines: A PLS-SEM approach,” J. of Air Transport Management, Vol.67, pp. 169-180, 2018. https://doi.org/10.1016/j.jairtraman.2017.12.008
43. [43] A. Ahmad, L. Dey, and S. M. Halawani, “A rule-based method for identifying the factor structure in customer satisfaction,” Information Sciences, Vol.198, pp. 118-129, 2012. https://doi.org/10.1016/j.ins.2012.02.056
44. [44] M. N. Imtiaz and M. K. B. Islam, “Identifying significance of product features on customer satisfaction recognizing public sentiment polarity: Analysis of smart phone industry using machine-learning approaches,” Applied Artificial Intelligence, Vol.34, No.11, pp. 832-848, 2020. https://doi.org/10.1080/08839514.2020.1787676
45. [45] Q. Zhao, W. Zhao, X. Guo, K. Zhang, and M. Yu, “A dynamic customer requirement mining method for continuous product improvement,” Autonomous Intelligent Systems, Vol.2, No.1, Article No.14, 2022. https://doi.org/10.1007/s43684-022-00032-4
46. [46] X. Li, Y. Lei, and S. Ji, “BERT- and BiLSTM-based sentiment analysis of online Chinese buzzwords,” Future Internet, Vol.14, No.11, Article No.332, 2022. https://doi.org/10.3390/fi14110332
47. [47] M. M. Rahman, A. I. Shiplu, Y. Watanobe, and M. A. Alam, “RoBERTa-BiLSTM: A context-aware hybrid model for sentiment analysis,” IEEE Trans. on Emerging Topics in Computational Intelligence, Vol.9, No.6, pp. 3788-3805, 2025. https://doi.org/10.1109/TETCI.2025.3572150
48. [48] Z. Li, X. Yang, L. Zhou, H. Jia, and W. Li, “Text matching in insurance question-answering community based on an integrated BiLSTM-TextCNN model fusing multi-feature,” Entropy, Vol.25, No.4, Article No.639, 2023. https://doi.org/10.3390/e25040639
49. [49] J. Deng, L. Cheng, and Z. Wang, “Attention-based BiLSTM fused CNN with gating mechanism model for Chinese long text classification,” Computer Speech & Language, Vol.68, Article No.101182, 2021. https://doi.org/10.1016/j.csl.2020.101182
50. [50] J. Hu, L. Shen, and G. Sun, “Squeeze-and-excitation networks,” 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition, pp. 7132-7141, 2018. https://doi.org/10.1109/CVPR.2018.00745
51. [51] B. Peng, K. Han, L. Zhong, S. Wu, and T. Zhang, “A head-to-head attention with prompt text augmentation for text classification,” Neurocomputing, Vol.595, Article No.127815, 2024. https://doi.org/10.1016/j.neucom.2024.127815
52. [52] J. Zhang et al., “Fengshenbang 1.0: Being the foundation of Chinese cognitive intelligence,” arXiv:2209.02970, 2022. https://doi.org/10.48550/arXiv.2209.02970