Home > Computer Science > Data Processing > Volume-10 > Issue-5 > Sentiment Classification and Trend Analysis of Chinese Basketball Online Public Opinion Based on Machine Learning - A Case Study of the Chinese Men's National Basketball Team

Sentiment Classification and Trend Analysis of Chinese Basketball Online Public Opinion Based on Machine Learning - A Case Study of the Chinese Men's National Basketball Team

Call for Papers

Volume-10 | Issue-6

Last date : 27-Dec-2026

Best International Journal
Open Access | Peer Reviewed | Best International Journal | Indexing & IF | 24*7 Support | Dedicated Qualified Team | Rapid Publication Process | International Editor, Reviewer Board | Attractive User Interface with Easy Navigation

Journal Type : Open Access

First Update : Within 7 Days after submittion

Submit Paper Online

For Author

Research Area


Sentiment Classification and Trend Analysis of Chinese Basketball Online Public Opinion Based on Machine Learning - A Case Study of the Chinese Men's National Basketball Team


Chen Guanlin | Cao Jingxuan | Hu Yilin



Chen Guanlin | Cao Jingxuan | Hu Yilin "Sentiment Classification and Trend Analysis of Chinese Basketball Online Public Opinion Based on Machine Learning - A Case Study of the Chinese Men's National Basketball Team" Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-10 | Issue-5, October 2026, pp.99-117, URL: https://www.ijtsrd.com/papers/ijtsrd142207.pdf

Sports-event online public opinion is characterized by strong event-driven dynamics, rapid emotional fluctuations, and frequent use of community slang and sarcasm. Taking the five official games of the Chinese men's basketball team at the 2023 FIBA Basketball World Cup as the event thread, this paper studies the sentiment classification of basketball online public opinion and its changes across match milestones. Considering the limited scale of basketball texts that can be traced back one by one and uniformly manually reviewed, this paper separates the machine-learning experiments from the event-application analysis: first, the public ASAP Chinese review dataset is used to compare five traditional models (KNN, Decision Tree, linear SVM, Bagging, and AdaBoost) and to select a benchmark model suitable for preliminary three-class screening of texts; the better-performing SVM is then applied to the auxiliary preliminary screening of 28 Hupu World Cup event-text units, and the final manual review is completed by combining basketball-domain terms with the original page context. To expand the scope of case evidence, this study further builds a cross-platform public-source index, organizing 39 Zhihu answer entries, 19 Hupu public pages or entries, and 13 Weibo historical trending-topic records directly related to the five games for issue-level cross-verification; indexed records for which complete Chinese source texts are unavailable are not countedas training samples or in the sentiment index. In the benchmark experiment, SVM achieves an Accuracy of 0.6688 and a Macro-F1 of 0.5531; its direct preliminary-screening accuracy on the 28 Hupu event texts is 46.43%, indicating that the generic model can only serve as an auxiliary tool. Based on the manually reviewed results, the sentiment indices of the five games are -0.667, -0.500, -1.000, 0.600, and -0.833 in sequence; sentiment clearly turns positive after the win over Angola and turns negative again after the loss to the Philippines. The correlation coefficient between point margin and sentiment index across the five games is about 0.741, but the sample size is small and the correlation result is treated as descriptive analysis only. Issue induction shows that discussion gradually extends from single-game outcomes and player performance to coach rotation, fundamentals, CBA competitive intensity, and youth training. The study shows that traditional machine learning can improve the preliminary-screening efficiency of sports public-opinion texts, but basketball slang, sarcasm, and multi-object evaluation still require manual calibration in combination with specific match contexts. This paper also provides an empirical basis for the subsequent construction of a multi-platform basketball-specific corpus, domain sentiment models, and automated public-opinion systems.

Chinese men's basketball team; online public opinion; machine learning; sentiment analysis; sports events; cross-platform retrieval; manual review.


IJTSRD142207
Volume-10 | Issue-5, October 2026
99-117
IJTSRD | www.ijtsrd.com | E-ISSN 2456-6470
Copyright © 2019 by author(s) and International Journal of Trend in Scientific Research and Development Journal. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0) (http://creativecommons.org/licenses/by/4.0)

International Journal of Trend in Scientific Research and Development - IJTSRD having online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International Journal which provides rapid publication of your research articles and aims to promote the theory and practice along with knowledge sharing between researchers, developers, engineers, students, and practitioners working in and around the world in many areas like Sciences, Technology, Innovation, Engineering, Agriculture, Management and many more and it is recommended by all Universities, review articles and short communications in all subjects. IJTSRD running an International Journal who are proving quality publication of peer reviewed and refereed international journals from diverse fields that emphasizes new research, development and their applications. IJTSRD provides an online access to exchange your research work, technical notes & surveying results among professionals throughout the world in e-journals. IJTSRD is a fastest growing and dynamic professional organization. The aim of this organization is to provide access not only to world class research resources, but through its professionals aim to bring in a significant transformation in the real of open access journals and online publishing.

Thomson Reuters
Google Scholer
Academia.edu

ResearchBib
Scribd.com
archive

PdfSR
issuu
Slideshare

WorldJournalAlerts
Twitter
Linkedin