Academic Journal of Computing & Information Science, 2024, 7(7); doi: 10.25236/AJCIS.2024.070714.
Dai Wei
School of Computer and Information Engineering, Hubei University, Wuhan, Hubei, 430062, China
In 2023, the scale of the co-branding economy in China surpassed 100 billion yuan, demonstrating a rapid growth trend, with more than half of the popular co-branded products belonging to the catering industry. However, alongside the apparent rapid development of the co-branding economy, many negative consumer reviews have also gradually surfaced, raising the issue of how to sustain high-quality development in the co-branding economy as a critical concern today. This paper addresses this issue by using Python's weibopy library to crawl comments from Sina Weibo, selecting comments on four popular co-branded products, including Luckin Coffee × Jackson Yee. To delve deeply into the themes within the comments, the BERTopic topic model is used to extract seven representative co-branding themes, revealing that packaging and celebrities are of significant concern to consumers. Finally, SnowNLP sentiment analysis is applied to understand consumer sentiment in four of these themes, leading to suggestions that co-branded products should consider addressing negative feedback regarding taste.
Web scraping; BERTopic; SnowNLP; Sentiment analysis; Catering co-branding
Dai Wei. Analysis of Co-branded Food Product Reviews Based on BERTopic and SnowNLP. Academic Journal of Computing & Information Science (2024), Vol. 7, Issue 7: 105-112. https://doi.org/10.25236/AJCIS.2024.070714.
[1] Rao J, Wang X. Analysis of brand crossover co-branding marketing strategies[C]. 2022 4th International Conference on Literature, Art and Human Development (ICLAHD 2022). Atlantis Press, 2023: 949-955.
[2] Wang M. Analysis of the Impact of Crossover Brand Co-branding on Consumer Purchasing Behavior[C]. Proceedings of the 6th International Conference on Economic Management and Green Development. Singapore: Springer Nature Singapore, 2023: 271-283.
[3] Yutong L. Hostility between men and women on Chinese social media: a content analysis of Sina Weibo with word frequency analysis and topic modeling. PsyArXiv, 11 Apr, 2023.
[4] Egger R, Yu J. A topic modeling comparison between lda, nmf, top2vec, and bertopic to demystify twitter posts[J]. Frontiers in sociology, 2022, 7: 886498.
[5] GROOTENDORST, Maarten. BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv preprint arXiv:2203.05794, 2022.
[6] Wang Z, Chen J, Chen J, et al. Identifying interdisciplinary topics and their evolution based on BERTopic[J]. Scientometrics, 2023: 1-26.
[7] Bhuvaneswari A, Kumudha M. Topic Modeling Based Clustering of Disaster Tweets Using BERTopic[C].2024 MIT Art, Design and Technology School of Computing International Conference (MITADTSoCiCon). IEEE, 2024: 1-6.
[8] Zhou B, Zhu Y, Mao X. Sentiment Analysis on Power Rationing Micro Blog Comments Based on SnowNLP-SVM-LDA Model[J]. Highlights in Science, Engineering and Technology, 2022, 4: 179-185.
[9] Hu N. Sentiment analysis of texts on public health emergencies based on social media data mining[J]. Computational and mathematical methods in medicine, 2022, 2022(1): 3964473.
[10] Xiong W, Zuo Y, Zhang M, et al. Research on Sentiment Analysis of E-commerce Live Comments based on Text Mining[J]. Frontiers in Computing and Intelligent Systems, 2023, 6(3): 34-36.