Huawei Mate XT Mobile Phone Release Event Theme Mining and Sentiment Analysis

Yujia Wang; Xueli Yu; Haiyun Xu

doi:10.6981/FEM.202504_6(4).0022

Authors

Yujia Wang
Xueli Yu
Haiyun Xu

DOI:

https://doi.org/10.6981/FEM.202504_6(4).0022

Keywords:

Huawei Mobile Phone; LDA; SnowNLP; Theme Mining; Sentiment Analysis.

Abstract

Under the background of the rise of domestic products and technology autonomy, the release of Huawei Mate XT mobile phone has aroused high public attention to local scientific and technological innovation. Social media is the main front of public opinion, and its user comments provide core data for consumer cognition and emotion analysis. Based on a total of 2035 user comments on Weibo and rednote platform, this study integrates the LDA topic model and SnowNLP sentiment analysis technology to understand the public's concerns and emotional tendencies. The results show that the user comments focus on the two dimensions of technical characteristics and market response, and both show a positive dominant trend. Users highly recognized the three-fold screen form innovation and local technology breakthrough, but the durability and weight of the folding screen caused some concerns; Global marketing and the "extraordinary master" brand narrative effectively strengthen user identification, but the high-end pricing and Apple, millet comparison disputes remain high. In this regard, this paper puts forward suggestions such as strengthening independent technology innovation, optimizing tiered pricing strategy, and improving after-sales service system, so as to provide decision-making reference for Huawei to balance technological breakthrough and market demand.

Downloads

Download data is not yet available.

References

[1] Jesse Scotland, Alvin Thomas, Mengguo Jing,Public emotion and response immediately following the death of George Floyd: A sentiment analysis of social media comments,Telematics AndInformaticsReports, Volume14, 2024100, 143, https://doi.org/10.1016/j.teler.2024.100143.

[2] Nguyen, B. H., & Huynh, V. N. (2020). Textual analysis and corporate bankruptcy: A financial dictionary-based sentiment approach. Journal of the Operational Research Society, 73(1), 102-121. https://doi.org/10.1080/01605682.2020.1784049

[3] Felipe Viegas, Mario S. Alvim, Sergio Canuto, Thierson Rosa, Marcos Andre Goncalves, Leonardo Rocha,Exploiting semantic relationships for unsupervised expansion of sentiment lexicons, Information Systems, Volume 94202, 0101, 606, https://doi.org/10.1016/ j.is.2020.101 606.

[4] Munir Ahmad, Shabib Aftab, Muhammad Salman Bashir, Noureen Hameed, Iftikhar Ali and Zahid Nawaz, “SVM Optimization for Sentiment Analysis” International Journal of Advanced Computer Science and Applications(ijacsa), 9 (4), 2018. http://dx.doi.org/10.14569/IJACSA.2018.090455

[5] Dey, N., Rahman, M. S., Mredula, M. S., Hosen, A. S. M. S., & Ra, I.-H. (2021). Using Machine Learning to Detect Events on the Basis of Bengali and Banglish Facebook Posts. Electronics, (19) 10, 2367. https://doi.org/10.3390/electronics10192367

[6] Mohammad Azad, Mikhail Moshkov,Multi-stage optimization of decision and inhibitory trees for decision tables with many-valued decisions,European Journal of Operational Research,Volume 263, Issue 3201, Pages 910-921, https://doi.org/10.1016/j.ejor.2017.06.026.

[7] Hong Kuan Sok, Melanie Po-Leen Ooi, Ye Chow Kuang, Serge Demidenko,Multivariate alternating decision trees,Pattern Recognition,Volume 50,2016,Pages 195-209 ,https://doi.org/10.1016/j. patcog.2015.08.014.

[8] Fazeel Abid, Chen Li, Muhammad Alam,Multi-source social media data sentiment analysis using bidirectional recurrent convolutional neural networks,Computer Communications,Volume 157,2020,Pages 102-115, https://doi.org/10.1016/j.comcom.2020.04.002

[9] Ba te arslan, M., Kayaalp, F. Sentiment analysis using a deep ensemble learning model. Multimed Tools Appl 83, 42207-42231 (2024). https://doi.org/10.1007/s11042-023-17278-6

[10] Donghwa Kim, Pilsung Kang,Cross-modal distillation with audio–text fusion for fine-grained emotion classification using BERT and Wav2vec 2.0, Neurocomputing, Volume 2, 506202, Pages 168-183, https://doi.org/10.1016/j.neucom.2022.07.035.

[11] BLEI D M, NGY A, JORDAN M I. Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 1(3): 993-1022.

[12] Wu, X., Nguyen, T. & Luu, A.T. A survey on neural topic models: The methods, applications, and challenges. The Artif Intell Rev 57, 18 (2024). https://doi.org/10.1007/s10462-023-10661-7

[13] Hao Li, Yang Qian, Yuanchun Jiang, Yezheng Liu, Fan Zhou,A novel label-based multimodal topic model for social media analysis,Decision Support Systems,Volume 164,2023,113863 ,https://doi. org/10.1016/j.dss.2022.113863.