[1]付鹏斌,刘 曼,杨惠荣.结合学科情感分析与依存关系的相似度评分[J].计算机技术与发展,2022,32(02):32-38.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 005]
　FU Peng-bin,LIU Man,YANG Hui-rong.Similarity Score Combining Subject Sentiment Analysis and Dependency Relationship[J].,2022,32(02):32-38.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 005]
点击复制

结合学科情感分析与依存关系的相似度评分()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年02期
页码:
32-38
栏目:
大数据分析与挖掘
出版日期:
2022-02-10

文章信息/Info

Title:
Similarity Score Combining Subject Sentiment Analysis and Dependency Relationship
文章编号:
1673-629X(2022)02-0032-07
作者:
付鹏斌; 刘 曼; 杨惠荣
北京工业大学 信息学部,北京 100124
Author(s):
FU Peng-bin; LIU Man; YANG Hui-rong
Faculty of Information Technology,Beijing University of Technology,Beijing 100124,China
关键词:
主观题; 自动评分; 情感分析; 依存关系; 语义相似度
Keywords:
subjective question; automatic scoring; sentiment analysis; dependency relationship; semantic similarity
分类号:
TP181
DOI:
10. 3969 / j. issn. 1673-629X. 2022. 02. 005
摘要:
通过对语文古诗文阅读类主观题的分析,提出了结合学科情感分析与依存关系的相似度评分算法,并将其应用于高中语文古诗文阅读类主观题的评分中。 首先,以中文维基百科语料为基础,增加了与评分相关的古诗文语料 81 927 条,通过文本向量化算法 Word2vec 进行词向量训练,完成了对古诗文语料库的构建;基于学科评分特性建立了对应的古诗文过滤词表,提出了基于词性的关键词提取及词向量的相似度计算方法;之后,针对情感分析模型对古诗文语句分析不准确的问题,结合同义词词林,建立了古诗文情感词库;并构建了学科情感分析模型,实现了基于学科情感分析的相似度计算方法;最后,通过关键词、学科情感分析以及依存句法分析,从多个维度计算学生答案与标准答案文本之间的加权语义相似度。 并将构建的古诗文语料库、古诗文情感词库和学科情感分析模型,用于相似度综合评分算法,以此实现了结合学科情感分析与依存关系的相似度评分算法。 实验表明,该算法的平均评分准确率达到了 89. 42% 。
Abstract:
Through the analysis of the subjective questions of ancient Chinese poetry reading,a similarity scoring algorithm combiningsubject sentiment analysis and dependency relationship is proposed and applied to the scoring of the subjective questions of ancientChinese poetry reading in high school. First of all,based on the Chinese Wikipedia corpus,81 927 pieces of? ? ? ancient poetry corpus relatedto scoring are added,and word vector training is carried out through the text vectorization algorithm Word2vec,and the construction of theancient poetry? ? ? ?corpus is completed. Based on the subject scoring characteristics,the corresponding ancient poetry filter vocabulary is established,and a method of keyword extraction based on part of speech and the similarity calculation method of word vectors is proposed.After that,in order to solve the problem of inaccurate analysis of ancient poetry sentences by the sentiment analysis model,combined withthe synonym word forest,the ancient poetry sentiment word library is established,and a subject sentiment analysis model is constructed torealize the similarity calculation method based on subject sentiment analysis. Finally,the weighted semantic similarity between students’ answers and standard answer texts is calculated from multiple dimensions through keywords,subject sentiment analysis and dependency analysis. And the constructed ancient poetry corpus,ancient poetry sentiment vocabulary and subject sentiment analysis model are used inthe similarity comprehensive scoring algorithm,so as to realize the similarity scoring algorithm combining subject sentiment analysis anddependency relationship. Experiments show that the average scoring accuracy of the algorithm reaches 89. 42% .

相似文献/References:

[1]冷强奎,刘雨晴,秦玉平.基于二元模糊匹配的编程题智能评分方法[J].计算机技术与发展,2020,30(02):71.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 015]
　LENG Qiang-kui,LIU Yu-qing,QIN Yu-ping.Intelligent Scoring Method for Programming Problems Based on Binary Fuzzy Matching[J].,2020,30(02):71.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 015]
[2]史浩杰,李 幸,贾俊铖,等.基于认知诊断和神经网络的试题得分预测[J].计算机技术与发展,2022,32(02):39.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 006]
　SHI Hao-jie,LI Xing,JIA Jun-cheng,et al.Prediction of Question Score Based on Cognitive Diagnosis Model andNeural Network[J].,2022,32(02):39.[doi:10. 3969 / j. issn. 1673-629X. 2022. 02. 006]

更新日期/Last Update: 2022-02-10