基于用户评价的自动评分方法

J4 ›› 2014, Vol. 36 ›› Issue (06): 1177-1183.

基于用户评价的自动评分方法

程传鹏1,吴婷1,胡恩良2

(1.中原工学院计算机学院,河南郑州 450007;2.云南师范大学数学学院,云南昆明 650092)

收稿日期:2013-01-28 修回日期:2013-04-02 出版日期:2014-06-25 发布日期:2014-06-25
基金资助:
河南省教育厅自然科学项目（2008B520046）；云南省科技计划项目（2011FZ074）

Research on automatic
scoring method based on user evaluation

CHENG Chuanpeng1,WU Ting1,HU Enliang2

(1.School of Computer Science,Zhongyuan Institute of Technology,Zhengzhou 450007;
2.School of Mathematics,Yunnan Normal University,Kunming 650092,China)

Received:2013-01-28 Revised:2013-04-02 Online:2014-06-25 Published:2014-06-25

摘要/Abstract

摘要：

提出了一种基于用户评价内容的自动评分方法；分析了常见词语相似度计算方法在情感倾向判断中的不足，并提出了相应的解决方法；分析了情感修饰词对情感倾向的影响，利用社会网络分析中的仿真软件UNICET选择出基准词。实验表明，该自动评分方法与用户实际的评分非常接近，具有一定的合理性。

关键词: 用户评价, 自动评分, 情感倾向, 语义相似度, 修饰词

Abstract:

An automatic scoring method based on evaluation content is proposed. The shortcoming of traditional words similarity computing methods is insufficient in sentiment orientation judgement is analyzed, and hence a solution method is proposed. The impact of sentiment modifier on sentiment orientation is discussed, and standard words are selected with the help of UNICET,which is a simulated software in social network. The experimental results show that the proposed automatic scoring method is more approximate to manual scoring, thus having certain reasonableness.

Key words: user evaluation;automatic scoring;sentiment orientation;semantic similarity;sentiment modifier

程传鹏1,吴婷1,胡恩良2. 基于用户评价的自动评分方法[J]. J4, 2014, 36(06): 1177-1183.

CHENG Chuanpeng1,WU Ting1,HU Enliang2. Research on automatic
scoring method based on user evaluation [J]. J4, 2014, 36(06): 1177-1183.

参考文献

［1］Yao Tianfang, Nie Qingyang, Li Jianchao, et al. An opinion mining system for Chinese automobile reviews［C］∥Proc of the 50th Anniversary Conference of Chinese Information Society,2006:260281.(in Chinese)
［2］Chaovalit P, Zhou L. Movie review mining:A comparison between supervised and unsupervised classification approaches［C］∥Proc of the 38th Annual Hawaii International Conference on System Sciences, 2005:112.
［3］Pang B, Lee L. A sentimental education sentiment analysis using subjectivity summarization based onminimum cuts［C］∥Proc of the 42nd Meeting of the Association for Computational Languages, 2004:271278.
［4］Ye Q, Shi W, Li Y J. Sentiment classification for reviews:Comparison between SVM and semantic approaches［C］ ∥Proc of the 4th International Conference on Machine and Cybernetics, 2005:341346.
［5］Ye Q, Shi W, Li Y J. Sentiment classification for movie reviews in Chinese by improved semantic oriented approach［C］∥Proc of the 39th Hawaii International Conference on System Sciences, 2006:5360.
［6］Cai Jianping,Wang linlin, Lin shiping．Analysis of words and sentence polarity based on machine learning ［C］ ∥Proc of the 12th Academic Annual Meeting of Chinese Association for Artificial Intelligence：the first part, 2007:829833．(in Chinese)
［7］Bai Ge, Zuo Wanli, Zhao Qiankun, et al. Sentiment classification for Chinese reviews with machine learning［J］. Journal of Jilin University，2009,47(6):12601263.(in Chinese)
［8］Tang Huifeng,Tan Songbo,Cheng Xueqi.Research on sentiment classification of Chinese reviews based on supervised machine learning techniques［J］.Journal of Chinese Information Processing, 2007,21(6):5594．(in Chinese)
［9］Whitelaw C，Garg N, Argamon S．Using appraisal groups for sentiment analysis［C］∥Proc of the 14th ACM International Conference on Information and Knowledge Management, 2005:625631．
［10］Li Yihong, Jiang Xiufeng. Opinion analysis of the Chinese sentence［J］. Journal of Fuzhou University，2010,38(4):504508.(in Chinese)
［11］Zhu Yanlan, Min Jin, Zhou Yaqian, et al. Semantic orientation computing based on HowNet［J］. Journal of Chinese Information Processing, 2006,20(1):1420.(in Chinese)
［12］Dang Lei, Zhang Lei. Method of discriminant for Chinese sentence sentiment orientation based on HowNet［J］. Application Research of Computers，2010,27(4):13701372.(in Chinese)
［13］Liu Qun,Li Sujian.Semantic similarity calculation of words based on hownet［C］∥Proc of the 3rd Chinese Lexical Semantics Symposium, 2002:1.(in Chinese)
［14］Dong Zhendong, Dong Qiang．Hownet［DB/OL］ .［20130315］.http://www.keenage.com.(in Chinese)
［15］Ping liang, Zong Liyong. Research on microblog information dissemination based on SNA centrality analysis［J］. Document,Informaiton & Knowledge，2010(6):9297.(in Chinese)
附中文参考文献:
［1］姚天防，聂青阳，李建超,等.一个用于汉语汽车评论的意见挖掘系统［C］∥中国中文信息学会25周年学术会议,2006:260281.
［6］蔡健平,王琳琳,林世平.基于机器学习的词语和句子极性分析［C］∥中国人工智能学会第12届全国学术年会论文集:上集，2007:829833.
［7］白鸽，左万利, 赵乾坤,等.使用机器学习对汉语评论进行情感分类［J］.吉林大学学报，2009,47（6）:12601263.
［8］唐慧丰，谭松波，程学旗．基于监督学习的中文情感分类技术比较研究［J］.中文信息学报,2007,21(6):5594．
［10］李艺红,蒋秀凤.中文句子倾向性分析［J］.福州大学学报,2010,38(4):504508.
［11］朱嫣岚,闵锦,周雅倩,等.基于HowNet的词汇语义倾向计算［J］.中文信息学报, 2006, 20(1): 1420.
［12］党蕾，张蕾.一种基于知网的中文句子情感倾向判别方法［J］.计算机应用研究，2010,27(4):13701372.
［13］刘群,李素建．基于《知网》的词汇语义相似度的计算［C］∥第三届汉语词汇语义学研讨会,2002：1.
［14］董振东,董强.知网［DB/OL］.［20130315］.http: ∥www.keenage.com.
［15］平亮,宗利永．基于社会网络中心性分析的微博信息传播研究［J］.图书情报知识，2010（6）:9297．

[1]	吴晓崇, 段跃兴, 张月琴, 闫雄. 基于CNN和深层语义匹配的中文实体链接模型[J]. 计算机工程与科学, 2020, 42(08): 1514-1520.
[2]	郭竞知, 刘玮, 徐龙龙, 陈灯 . Agent能力承诺协作的自适应图规划协议生成算法[J]. 计算机工程与科学, 2020, 42(07): 1208-1214.
[3]	赵谦1，荆琪1，李爱萍1，2，段利国1. 一种基于语义与句法结构的短文本相似度计算方法[J]. 计算机工程与科学, 2018, 40(07): 1287-1294.
[4]	张思琪，邢薇薇,蔡圆媛. 一种基于WordNet的混合式语义相似度计算方法[J]. 计算机工程与科学, 2017, 39(05): 971-977.
[5]	熊晶1，钟珞2，王爱民1,2. 甲骨文知识图谱构建中的实体关系发现研究[J]. J4, 2015, 37(11): 2188-2194.
[6]	熊芳1，3 ，黄宏斌2，黄玉成1，3 ，胡建中3. 基于带QoS能力模型的资源匹配方法[J]. J4, 2014, 36(10): 1911-1918.
[7]	熊芳1，黄宏斌2，黄玉成1，冯嵩1，胡建中1. 一种基于语义相似度的信息资源语义聚类算法[J]. J4, 2012, 34(11): 175-179.
[8]	黄果周竹荣周亭. 基于领域本体的语义相似度计算研究[J]. J4, 2007, 29(5): 112-117.