数据与计算发展前沿 ›› 2026, Vol. 8 ›› Issue (1): 91-102.

CSTR: 32002.14.jfdc.CN10-1649/TP.2026.01.008

doi: 10.11871/jfdc.issn.2096-742X.2026.01.008

• 技术与应用 • 上一篇    下一篇

一种基于情感分析的网络舆论倾向性检测方法

邓绎如1,2(),何洪波1,*(),王英1,王闰强1   

  1. 1.中国科学院计算机网络信息中心，北京 100083
    2.中国科学院大学，北京 100049
  • 收稿日期:2025-02-25 出版日期:2026-02-20 发布日期:2026-02-02
  • 通讯作者: 何洪波
  • 作者简介:邓绎如，中国科学院计算机网络信息中心，硕士研究生，主要研究方向为新媒体技术应用、自然语言处理。
    本文中负责提出模型框架，设计实验，论文撰写等。
    DENG Yiru is a master’s student at the Computer Network Information Center, Chinese Academy of Sciences. His main research interests include new media technology applications and natural language processing.
    In this paper, he is responsible for proposing the model framework, designing experiments, and writing the paper.
    E-mail: yrdeng@cnic.cn|何洪波，中国科学院计算机网络信息中心，高级工程师，硕士生导师，主要研究方向为新媒体技术应用、互联网数据挖掘和信息推荐。
    本文中负责思路解析和把握文章逻辑与框架，写作指导，论文修订等。
    HE Hongbo is a senior engineer and master’s supervisor at the Computer Network Information Center, Chinese Academy of Sciences. His primary research interests include new media technology applications, internet data mining, and information recommendation.
    In this paper, he is responsible for analyzing the core concepts, designing its logical framework, providing writing guidance, revising the paper.
    E-mail: hhb@cnic.cn
  • 基金资助:
    中国科学院网络安全和信息化专项(CAS-WX2022GC-0304)

Network Public Opinion Tendency Detection Method Based on Sentiment Analysis

DENG Yiru1,2(),HE Hongbo1,*(),WANG Ying1,WANG Runqiang1   

  1. 1. Computer Network Information Center, Chinese Academy of Sciences, Beijing 100083, China
    2. University of Chinese Academy of Sciences, Beijing 100049, China
  • Received:2025-02-25 Online:2026-02-20 Published:2026-02-02
  • Contact: HE Hongbo

RichHTML

1

PDF

0

摘要：

【应用背景】随着网络社交媒体的蓬勃发展，网络争议性舆论频发，给社会带来了诸多潜在风险与挑战。情感分析作为一种有效判断舆论倾向性的方法，在网络舆论研究中具有重要地位。【方法】本文提出了一种基于BERT的舆论倾向性检测方法，该方法设计了深度学习分类器进行情感倾向性分析，同时结合对比学习策略。【结论】加深了模型对两极化争议的表征，显著提高了负面舆论倾向性检测性能，同时提升了检测舆论两极化的能力。此研究为检测网络舆论风险提供了一种切实可行的技术方法，有助于及时发现并应对潜在的负面舆论和两极化争议，维护网络环境的健康与稳定。

关键词: 情感分析, 深度学习, 对比学习, 舆论分析, 两极化争议

Abstract:

[Application Background] With the vigorous development of online social media, controversial online public opinions occur frequently, bringing numerous potential risks and challenges to society. As an effective approach for determining public opinion trends, sentiment analysis holds significant importance in the study of online public opinion. [Method] This paper presents an opinion tendency detection method based on BERT. This method devises a deep learning classifier for sentiment tendency analysis and, simultaneously, incorporates the contrastive learning strategy. [Conclusion] The proposed method deepens the model's representation of polarized disputes, remarkably improves the performance of negative public opinion tendency detection, and enhances the ability to detect public opinion polarization. This research offers a practical technical solution for detecting online public opinion risks, facilitating the timely identification and response to potential negative public opinions and polarized disputes, thus safeguarding the health and stability of the online environment.

Key words: sentiment analysis, deep learning, contrastive learning, public opinion analysis, polarized disputes