北京大学学报自然科学版 ›› 2025, Vol. 61 ›› Issue (3): 420-430.DOI: 10.13209/j.0479-8023.2025.002

上一篇    下一篇

融合显性知识和隐性知识的古诗情感分析

赵宇兰1, 万广文2, 刘忠宝2,†   

  1. 1. 山西工程科技职业大学信息工程学院, 晋中, 030619 2. 北京语言大学信息科学学院, 北京 100083
  • 收稿日期:2024-03-20 修回日期:2024-08-18 出版日期:2025-05-20 发布日期:2025-05-20
  • 通讯作者: 刘忠宝, E-mail: zbliu(at)blcu.edu.cn
  • 基金资助:
    国家社科基金重点项目(23AZD047)和 2022年山西省教育科学“十四五”规划课题(GH-220313)资助

Sentiment Analysis of Chinese Ancient Poetry by Fusing Explicit Knowledge and Implicit Knowledge

ZHAO Yulan1, WAN Guangwen2, LIU Zhongbao2,†   

  1. 1. Information Engineering Faculty, Shanxi Vocational University of Engineering Science and Technology, Jinzhong 030619 2. School of Information Science, Beijing Language and Culture University, Beijing 100083
  • Received:2024-03-20 Revised:2024-08-18 Online:2025-05-20 Published:2025-05-20
  • Contact: LIU Zhongbao, E-mail: zbliu(at)blcu.edu.cn

摘要:

充分利用古诗文本的语义特征和相关领域的知识特征, 提出融合显性知识和隐性知识的古诗情感分析模型SACAP。首先从古诗文本中抽取深层次语义特征, 然后在构建古诗知识库的基础上, 设计多维度注意力机制对古诗知识进行特征提取, 最后通过融合古诗文本特征和古诗知识特征, 对古诗情感进行识别。在开放古诗语料FSPC上的实验结果表明, SACAP模型具有比已有模型更优的性能, 并且显性知识比隐性知识具有更大的作用。

关键词: 情感分析, 注意力机制, 显性知识, 隐性知识, 中国古诗

Abstract:

By fully utilizing the features of poetry text and related knowledge, this paper proposes a model SACAP for sentiment analysis of Chinese ancient poems integrating explicit knowledge and implicit knowledge. On the one hand, the model extracts deep semantic features from poetry text, and on the other hand, on the basis of constructing a knowledge base of Chinese ancient poetry, it designs a multidimensional attention mechanism to extract features from Chinese ancient poetry knowledge. The sentiment of Chinese ancient poetry can be determined by taking both features into consideration. The experimental results show that the proposed model performs better than existing models and the explicit knowledge plays much more important role, compared with implicit knowledge.

Key words: sentiment analysis, attention mechanism, explicit knowledge, implicit knowledge, Chinese ancient poetry