融合Skip-gram与R-SOPMI的教育领域情感词典构建

doi:10.3969/j.issn.0255-8297.2023.05.012

摘要/Abstract

摘要： 提出一种基于特征融合的细粒度教育领域情感词典构建方法。首先构建了教育领域语料库，包含正式、非正式领域情绪特征；其次提出一种融合特征的领域情绪词典构建方法，在情绪划分基础上识别词的语言概率特征以及统计概率特征，改进情感倾向点互信息，提出用于情绪分类的情感倾向点互信息算法，实现共现多分类情绪划分；最后得到细粒度教育领域情感词典，词典扩充至39 138个情绪词。实验表明：使用所提出方法构建的教育领域情绪词典除情绪“怒”以外，各类别F1综合指标均高于78.09%，整体性能良好。与通用词典相比，宏平均准确率、宏召回率和宏F1分别提升了21.95%、2.50%和13.01%，表明该融合特征方法能有效提取领域特征进而完成细粒度领域词典构建。

关键词: 情感词典, 情绪分类, 词向量, 融合特征

Abstract: This paper presents a method for constructing a fine-grained Sentiment Lexicon in Education to address specific emotional issues in sentiment analysis of educational feedback texts. First, we construct an educational domain corpus, which contains emotional features in both formal and informal domains. Second, a fusion-based method is proposed to construct a domain Sentiment Lexicon by identifying linguistic probability features and statistical probability features of words through sentiment classification. The proposed repetitive semantic orientation pointwise mutual information (R-SOPMI) algorithm enhances SO-PMI for sentiment classification, enabling co-occurrence multi-category sentiment classification. Finally, a fine-grained Sentiment Lexicon in the field of education is obtained, and the dictionary expands to 39 138 emotional words. Experiment results show that except for “anger”, the F1 of the emotion category of the constructed educational field emotion dictionary is all higher than 78.09%. Compared with a general dictionary, the Macro_Precision, Macro_Recall and Macro_F1 increased by 21.95%, 2.50% and 13.01%, respectively. The fusion feature method effectively extracts domain features, facilitating the construction of a comprehensive fine-grained domain dictionary.

Key words: Sentiment Lexicon, sentiment classification, Word2vec, fusion features

中图分类号:

TP391

陈俊, 席宁丽, 李佳敏, 万晓容. 融合Skip-gram与R-SOPMI的教育领域情感词典构建[J]. 应用科学学报, 2023, 41(5): 870-880.

CHEN Jun, XI Ningli, LI Jiamin, WAN Xiaorong. Constructing Sentiment Lexicon in the Education Field by Integrating Skip-Gram and R-SOPMI[J]. Journal of Applied Sciences, 2023, 41(5): 870-880.

参考文献

[1] 龚少英, 韩雨丝, 王丽霞, 等. 任务价值和学业情绪与网络学习满意度的关系研究[J]. 电化教育研究, 2016, 37(3):72-77. Gong S Y, Han Y S, Wang L X, et al. The relationships among task value, academic emotions and online learning satisfaction[J]. E-Education Research, 2016, 37(3):72-77. (in Chinese)
[2] 王科, 夏睿. 情感词典自动构建方法综述[J]. 自动化学报, 2016, 42(4):495-511. Wang K, Xia R. A survey on automatical construction methods of sentiment lexicons[J]. Acta Automatica Sinica, 2016, 42(4):495-511. (in Chinese)
[3] Wang S, Lyu G, Mazumder S, et al. Detecting domain polarity-changes of words in a sentiment lexicon[DB/OL] [2022.07.09]. https://arxiv.org/abs/2004.14357.
[4] Pekrun R, Goetz T, Frenzel A C, et al. Measuring emotions in students' learning and performance:the achievement emotions questionnaire[J]. Contemporary Educational Psychology, 2011, 36(1):36-48.
[5] 何炎祥, 孙松涛, 牛菲菲, 等. 用于微博情感分析的一种情感语义增强的深度学习模型[J]. 计算机学报, 2017, 40(4):773-790. He Y X, Sun S T, Niu F F, et al. A deep learning model enhanced with emotion semantics for microblog sentiment analysis[J]. Chinese Journal of Computers, 2017, 40(4):773-790. (in Chinese)
[6] Bravo-Marquez F, Frank E, Pfahringer B. Building a Twitter opinion lexicon from automatically-annotated tweets[J]. Knowledge-Based Systems, 2016, 108:65-78.
[7] Tang J, Hao S, Qu W. Sentiment analysis of online Chinese comments based on statistical learning combining with pattern matching[J]. Concurrency and Computation:Practice and Experience, 2019, 31(10):e4765.1-e4765.7.
[8] 胡家珩, 岑咏华, 吴承尧. 基于深度学习的领域情感词典自动构建——以金融领域为例[J]. 数据分析与知识发现, 2018, 2(10):95-102. Hu J H, Cen Y H, Wu C Y. Constructing sentiment dictionary with deep learning:case study of financial data[J]. Data Analysis and Knowledge Discovery, 2018, 2(10):95-102. (in Chinese)
[9] 齐梦娜, 朱丽平, 李宁. 基于卷积神经网络与情感倾向点互信息算法的农产品情感词典构建[J]. 计算机应用, 2022, 42(S2):10-13. Qi M N, Zhu L P, Li N. Agricultural products sentiment dictionary construction based on convolutional neural network and semantic orientation pointwise mutual information algorithm[J]. Journal of Computer Applications, 2022, 42(S2):10-13. (in Chinese)
[10] Li W, Zhu L Y, Guo K, et al. Build a tourism-specific sentiment lexicon via Word2vec[J]. Annals of Data Science, 2018, 5(1):1-7.
[11] Tang D, Wei F, Bing Q, et al. Sentiment embeddings with applications to sentiment analysis[J]. IEEE Transactions on Knowledge and Data Engineering, 2015, 28(2):1.
[12] Zhang B, Xu D, Zhang H, et al. STCS Lexicon:spectral-clustering-based topic-specific Chinese sentiment lexicon construction for social networks[J]. IEEE Transactions on Computational Social Systems, 2019, 6(6):1180-1189.
[13] 叶霞, 曹军博, 许飞翔, 等. 中文领域情感词典自适应学习方法[J]. 计算机工程与设计, 2020, 41(8):2231-2237. Ye X, Cao J B, Xu F X, et al. Sentiment dictionary adaptive learning method in Chinese domain[J]. Computer Engineering and Design, 2020, 41(8):2231-2237. (in Chinese)
[14] 李慧. 面向学习体验文本的学习者情感分析模型研究[J]. 远程教育杂志, 2021, 39(1):94-103. Li H. Research on learners' emotion analysis model of learning experience texts[J]. Journal of Distance Education, 2021, 39(1):94-103. (in Chinese)
[15] 孙波, 陈玖冰, 刘永娜. 大数据背景下的学生情感词典构建方法[J]. 北京师范大学学报(自然科学版), 2015, 51(4):358-361. Sun B, Chen J B, Liu Y N. Construction of students' emotion lexion in big data[J]. Journal of Beijing Normal University (Natural Science), 2015, 51(4):358-361. (in Chinese)
[16] 冯翔, 邱龙辉, 郭晓然. 基于LSTM模型的学生反馈文本学业情绪识别方法[J]. 开放教育研究, 2019, 25(2):114-120. Feng X, Qiu L H, Guo X R. Recognition method for academic emotions of students' feedback texts based on LSTM model[J]. Open Education Research, 2019, 25(2):114-120. (in Chinese)
[17] 徐琳宏, 林鸿飞, 潘宇, 等. 情感词汇本体的构造[J]. 情报学报, 2008, 27(2):180-185. Xu L H, Lin H F, Pan Y, et al. Constructing the affective lexicon ontology[J]. Journal of the China Society for Scientific and Technical Information, 2008, 27(2):180-185. (in Chinese)
[18] Yan E, Zhu Y. Tracking word semantic change in biomedical literature[J]. International Journal of Medical Informatics, 2018, 109:76-86.
[19] 郭贤伟, 赖华, 余正涛, 等. 融合情绪知识的案件微博评论情绪分类[J]. 计算机学报, 2021, 44(3):564-578. Guo X W, Lai H, Yu Z T. Emotion classification of case-related microblog comments integrating emotional knowledge[J]. Chinese Journal of Computers, 2021, 44(3):564-578. (in Chinese)
[20] 颜明阳, 闫国梁, 李明兰. 领域特定情感词典扩展方法在情感分类中的应用[J]. 计算机应用与软件, 2022, 39(6):176-182. Yan M Y, Yan G L, Li M L. Domain specific emotion dictionary expansion method in sentiment classification[J]. Computer Applications and Software, 2022, 39(6):176-182. (in Chinese)