Uncovering the Voice of Consumers in New Media: A Comparative Sentiment Analysis of Anker Product Reviews on Xiaohongshu and Amazon_Vol. 3 No. 2 (JNME 2026)_Journal of New Media and Economics (ISSN: 3005-5725)

Home > Journal of New Media and Economics (ISSN: 3005-5725) > Vol. 3 No. 2 (JNME 2026) >

Uncovering the Voice of Consumers in New Media: A Comparative Sentiment Analysis of Anker Product Reviews on Xiaohongshu and Amazon

Download PDF

DOI: https://doi.org/10.62517/jnme.202610202

Author(s)

Mengyi Yang1,*, Feifei Luo2

Affiliation(s)

1College of Study Abroad, Jiangxi University of Finance and Economics, Nanchang, Jiangxi, China 2College of Finance and Economics, Jiangxi University of Software Professional Technology, Nanchang, Jiangxi, China *Corresponding Author

Abstract

In the context of the new media economy, user-generated content (UGC) on different digital platforms reflects distinct consumer sentiment structures and expression logic. This study conducts a comparative sentiment analysis of user reviews for Anker power banks on Xiaohongshu, a representative Chinese social commerce platform, and Amazon, a global centralized e-commerce platform. Using SnowNLP for Chinese text sentiment classification and TextBlob for English reviews, combined with a keyword-based thematic analysis, the study examines 600 valid user reviews (300 from each platform). The findings reveal that while both platforms show generally positive attitudes toward the product, significant differences exist in sentiment distribution and thematic focus. Xiaohongshu users exhibit an "inverted pyramid" sentiment structure, characterized by authentic, diverse, and emotionally expressive content, with a strong focus on product appearance and usage scenarios. In contrast, Amazon users demonstrate a polarized sentiment pattern dominated by neutral and positive reviews, emphasizing performance metrics and durability. Grounded in the Stimulus-Organism-Response (S-O-R) framework, this study interprets these differences as outcomes of platform-specific environmental stimuli shaping users’ internal emotional states and behavioral responses. The findings provide empirical support for cross-cultural marketing strategies and platform-specific brand communication, highlighting the need for aesthetic and scenario-oriented marketing on Xiaohongshu and function-driven, trust-based communication on Amazon.

Keywords

New Media Economy; Cross-Cultural Marketing; Consumer Sentiment; SnowNLP; Xiaohongshu; Amazon

References

[1] Zhang Y F, Li H, Zhai Q, et al. A Study on the Ranking and Filtering Model of Online Review Usefulness Based on Fuzzy TOPSIS Analysis. Library and Information Work, 2016, 60 (13): 109-117, 125 [2] Sun J, Deng X X. A Comparative Study of Centralized E-commerce Platforms and Independent Websites: An Analysis Based on Amazon and SHEIN. Northern Economics and Trade, 2025 (8): 51-57. [3] Zhu J. “The Influencer Economy” and “Emotional Labor”: A Perspective on Understanding “Xiaohongshu”. Literary Theory and Criticism, 2021 (1): 77-88 [4] Jiang J H, Pang Y H. Aligning Value Creation and Value Capture on Content Platforms: A Longitudinal Case Study of Xiaohongshu, 2013–2023. Foreign Economics and Management, 2025, 47 (9): 24–46. [5] Mehrabian A, Russell J A. An approach to environmental psychology. Cambridge: The MIT Press, 1974. [6] Kabian L, Vafaei-Zadeh A & Hanifah H, et al. Investigating the determinants of individual's intention to use social commerce: a stimulus-organism-response (SOR) approach. Information Discovery and Delivery, 2025, 53(2): 123-135. [7] Sun J, Deng X L. A Comparative Study of Centralized E-commerce Platforms and Independent Websites: An Analysis Based on Amazon and SHEIN. Northern Economics and Trade, 2025 (8):51-57. [8] Yu L P, Xia Z J, Wang B B. A Study on the Influence of Online Reviews on Consumers’ Willingness to Purchase Online. Modern Intelligence, 2014, 34 (11): 34–38. [9] Zhu J. “Influencer Economy” and “Emotional Labor”: A Perspective on Understanding “Xiaohongshu”. Literary Theory and Criticism, 2021 (1):77-88. [10] Zhang Y F, Li H, Zhai Q, et al. A Study on the Ranking and Filtering Model of Online Review Usefulness Based on Fuzzy TOPSIS Analysis. Library and Information Work, 2016, 60 (13): 109-117, 125. [11] Aslam W, Luna I R D. The relationship between brand Facebook page characteristics, perceived value, and customer engagement behavior: An application of Stimulus-Organism-Response (SOR). Revista Brasileira de Gestão de Negócios, 2021: 43-62. [12] Kabian L, Vafaei-zadeh A, Hanifah H, et al. Investigating the determinants of individual’s intention to use social commerce: a stimulus-organism-response (SOR) approach. Information Discovery and Delivery, 2025: 1-19. [13] Zhang L, Chen M, Zamil A M A. Live stream marketing and consumers’ purchase intention: An IT affordance perspective using the SOR paradigm. Frontiers in Psychology, 2023, 14: 1069050. [14] Kaur J, Gupta I, Singh T. Social media marketing and consumer engagement: A SOR perspective in the luxury fashion sector. Journal of Retailing and Consumer Services, 2025, 82: 103769. [15] Ding X, Jiang Y S, Chen J, et al. A Study on Factors Influencing the Usefulness of Online Reviews in User Community Contexts: A Case Study of Xiaohongshu. Journal of Management, 2023, 20 (5):750-760. [16] Rahman Z, Asadullah J, Dodul D H, et al. Literature review on the SOR model from the perspective of social media. Pakistan Journal of Life & Social Sciences, 2024, 22(2). [17] Jayadi J, Putra E I, Murwani I A. The implementation of the SOR framework (stimulus, organism, and response) in analyzing user behavior toward Instagram shop features and its impact on purchase intention. Scholars Journal of Engineering and Technology, 2022, 10(4): 42-53. [18] Lee S H. How do online reviews affect purchasing intention? African Journal of Business Management, 2009, 3(10): 576. [19] Zeng, Q. (2025). Sentiment Analysis of Online Movie Reviews and Research on Online Marketing Strategies. E-Commerce Review, 14(7), 2049–2057. [20] Wei, D. (2024). Analysis of Co-branded Food Product Reviews Based on BERTopic and SnowNLP. Academic Journal of Computing & Information Science, 7(7), 105-112. [21] Wang Y, Li M. A Study on Factors Influencing Consumer Satisfaction with Pre-cooked Meals Based on Online Reviews. China Business Review, 2024, 33(21): 89-93. [22] Xing Y Q, Yang C. Deep Web Crawling and Data Analysis Based on Reverse Engineering Techniques. Software Engineering, 2023, 26(12): 41-45. [23] Bai J, Hong X J. Text Mining and Sentiment Analysis of Online Public Opinion Based on Danmu. Software Engineering, 2022, 25(11): 44-48. [24] Arbide A C. Emotion-aware cyber-physical systems. Universidad Politécnica de Madrid, 2019. [25] Sharma, Prashant, and Vijaya R S. “Weighted Ensemble LSTM Model with Word Embedding Attention for E-Commerce Product Recommendation.” Journal of Communications Software and Systems 19.4 (2023): 299-307. [26] Min, Wan Nur Syahirah Wan, and Nur Zareen Zulkarnain. “Comparative evaluation of lexicons in performing sentiment analysis.” Journal of Advanced Computing Technology and Application (JACTA) 2.1 (2020): 1-8. [27] Hutto C, Gilbert E. Vader: A parsimonious rule-based model for sentiment analysis of social media text//Proceedings of the International AAAI Conference on Web and Social Media. 2014, 8(1): 216-225. [28] Bravo G, Grimaldo F, López-Iñesta E, et al. The effect of publishing peer review reports on referee behavior in five scholarly journals. Nature Communications, 2019, 10(1): 322. [29] Aljedaani, Wajdi, et al. “Sentiment analysis on Twitter data integrating TextBlob and deep learning models: The case of the US airline industry.” Knowledge-Based Systems 255 (2022): 109780. [30] Gujjar P, Kumar H R P. Opinion mining for customer feedback using textbooks. International Journal of Scientific Research in Computer Science, Engineering, Information, and Technology, 2020, 72: 76.