Please wait a minute...
Advanced Search
现代图书情报技术  2016, Vol. 32 Issue (4): 64-71    DOI: 10.11925/infotech.1003-3513.2016.04.08
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
融合句法信息的金融论坛文本情感计算研究*
兰秋军(),刘文星,李卫康,胡星野
湖南大学工商管理学院 长沙 410082
Sentiment Analysis of Financial Forum Textual Message
Lan Qiujun(),Liu Wenxing,Li Weikang,Hu Xingye
Business School, Hunan University, Changsha 410082, China
全文: PDF(478 KB)   HTML ( 76
输出: BibTeX | EndNote (RIS)      
摘要 

目的】为了准确识别金融论坛文本的情感倾向, 提出一种基于依存句法的情感分析方法。【方法】以依存句法的分析结果为基础, 对句子进行情感主干抽取; 然后根据依存关系的不同类型和不同的词性搭配, 定义情感计算规则, 以此进行句子情感倾向性计算。【结果】实验结果表明, 该方法的整体准确率为84.46%; 看涨类的平均精确率和召回率分别为82.84%和87.14%, F值为84.94%; 看跌类的平均精确率和召回率分别为86.28%和81.74%, F值为83.95%。【局限】在情感计算时未充分考虑子句间的关联关系。【结论】使用依存句法能有效提高金融论坛文本情感计算的准确性。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
兰秋军
刘文星
李卫康
胡星野
关键词 情感分析依存句法金融论坛文本文本挖掘    
Abstract

[Objective] This paper aims to identify sentiment propensity accurately with the help of a new method based on dependency parsing. [Methods] First, we extracted the sentiment stems of the sentences. Second, we defined sentiment-computing rules. Finally, we calculated sentiment propensity of each sentence. [Results] The proposed method achieved an overall accuracy of 84.46%. The average precision rate and recall rate for bullish class were 82.84% and 87.14% respectively, with an F-measure of 84.94%. In the mean time, bearish class got a precision rate of 86.28%, a recall rate of 81.74% and an F-measure of 83.95%. [Limitations] The proposed method did not consider the relevance among clauses. [Conclusions] The dependency parsing can effectively improve the accuracy of sentiment analysis of textual message from financial forum.

Key wordsSentiment analysis    Dependency parsing    Financial forum text    Text mining
收稿日期: 2015-10-14     
基金资助:*本文系国家自然科学基金重点项目“高维度、非线性、非平稳及时变金融数据建模和应用”(项目编号: 71431008)和国家自然科学基金面上项目“基于网络留言的投资者情绪测度模型、系统及应用”(项目编号: 71171076)的研究成果之一
引用本文:   
兰秋军,刘文星,李卫康,胡星野. 融合句法信息的金融论坛文本情感计算研究*[J]. 现代图书情报技术, 2016, 32(4): 64-71.
Lan Qiujun,Liu Wenxing,Li Weikang,Hu Xingye. Sentiment Analysis of Financial Forum Textual Message. New Technology of Library and Information Service, DOI:10.11925/infotech.1003-3513.2016.04.08.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.1003-3513.2016.04.08
[1] Liu B.Sentiment Analysis and Opinion Mining[M]. California: Morgan and Claypool Publishers, 2012.
[2] Smailovi? J, Gr?ar M, Lavra? N, et al.Stream-based Active Learning for Sentiment Analysis in the Financial Domain[J]. Information Sciences, 2014, 285: 181-203.
[3] Van de Kauter M, Breesch D, Hoste V. Fine-grained Analysis of Explicit and Implicit Sentiment in Financial News Articles[J]. Expert Systems with Applications, 2015, 42(11): 4999-5010.
[4] Hagenau M, Liebmann M, Neumann D.Automated News Reading: Stock Price Prediction Based on Financial News Using Context-capturing Features[J]. Decision Support Systems, 2013, 55(3): 685-697.
[5] 胡勇军, 江嘉欣, 常会友. 基于LDA高频词扩展的中文短文本分类[J]. 现代图书情报技术, 2013(6): 42-48.
[5] (Hu Yongjun, Jiang Jiaxin, Chang Huiyou.A New Method of Keywords Extraction for Chinese Short-text Classification[J]. New Technology of Library and Information Service, 2013(6): 42-48.)
[6] Kiritchenko S, Zhu X, Mohammad S M.Sentiment Analysis of Short Informal Texts[J]. Journal of Artificial Intelligence Research, 2014, 50: 723-762.
[7] 段江娇, 刘红忠, 曾剑平. 投资者情绪指数、分析师推荐指数与股指收益率的影响研究——基于我国东方财富网股吧论坛、新浪网分析师个股评级数据[J]. 上海金融, 2014(11): 60-64.
[7] (Duan Jiangjiao, Liu Hongzhong, Zeng Jianping.A Study of the Influence Between Investor Sentiment Index, Analyst Recommendation Index and Stock Index Return —— Based on Eastmoney.com and Sina Analyst Shares Rating Data[J]. Shanghai Finance, 2014 (11): 60-64.)
[8] 林炳灿. 基于投资者情绪的网络舆论对股票价格影响的统计研究[D]. 成都: 西南财经大学, 2013.
[8] (Lin Bingcan.Statistical Studies of Network Public Opinion’s Investor Sentiment’s Impact on the Stock Price[D]. Chengdu: Southwestern University of Finance and Economics, 2013.)
[9] 陈江鹏. 基于网络舆论的我国股票市场有效性检验研究[D]. 成都: 西南财经大学, 2013.
[9] (Chen Jiangpeng.A Study of China’s Stock Market Effectiveness Testing Based on the Network Public Opinion [D]. Chengdu: Southwestern University of Finance and Economics, 2013.)
[10] 刘定平. 突发事件环境下投资者情绪对股票价格波动影响的实证研究[D]. 成都: 西南财经大学, 2014.
[10] (Liu Dingping.Empirical Research on the Volatility of Stock Price Brought by Investor’s Sentiment in the Emergency Environment[D]. Chengdu: Southwestern University of Finance and Economics, 2014.)
[11] 张世军, 程国胜, 蔡吉花, 等. 基于网络舆情支持向量机的股票价格预测研究[J]. 数学的实践与认识, 2013, 43(24): 33-40.
[11] (Zhang Shijun, Cheng Guosheng, Cai Jihua, et al.Stock Price Prediction Base on Network Public Opinion and Support Vector Machine[J]. Mathematics in Practice and Theory, 2013, 43(24): 33-40.)
[12] 宋敏晶. 基于情感分析的股票预测模型研究[D]. 哈尔滨: 哈尔滨工业大学, 2013.
[12] (Song Minjing.Stock Prediction Model Based on Sentiment Analysis Research[D]. Harbin: Harbin Institute of Technology, 2013.)
[13] 金雪军, 祝宇, 杨晓兰. 网络媒体对股票市场的影响——以东方财富网股吧为例的实证研究[J]. 新闻与传播研究, 2013(12): 36-51.
[13] (Jin Xuejun, Zhu Yu, Yang Xiaolan.Effects of Online Media on Stock Market: An Empirical Study on Eastmoney.com[J]. Journalism & Communication, 2013(12): 36-51.)
[14] 沈翰彬. 投资者本地关注对股票收益率的影响——基于网络论坛文本挖掘的实证研究[D]. 杭州: 浙江大学, 2014.
[14] (Shen Hanbin.The Effect of Investor Home Attention on Stock Return - A Study Based on Stock Message Boards with Text Mining Techniques [D]. Hangzhou: Zhejiang University, 2014.)
[15] 夏梦南, 杜永萍, 左本欣. 基于依存分析与特征组合的微博情感分析[J]. 山东大学学报: 理学版, 2014, 49(11): 22-30.
[15] (Xia Mengnan, Du Yongping, Zuo Benxin.Micro-blog Opinion Analysis Based on Syntactic Dependency and Feature Combination[J]. Journal of Shandong University: Natural Science, 2014, 49(11): 22-30.)
[16] 张庆庆, 刘西林. 基于依存句法关系的文本情感分类研究[J]. 计算机工程与应用, 2015, 51(22): 28-32.
[16] (Zhang Qingqing, Liu Xilin.Sentiment Analysis Based on Dependency Syntactic Relation[J]. Computer Engineering and Applications, 2015, 51(22): 28-32.)
[17] Nakagawa T, Inui K, Kurohashi S.Dependency Tree-based Sentiment Classification Using CRFs with Hidden Variables [C]. In: Proceedings of the 11th Annual Conference of the North American Chapter of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2010: 786-794.
[18] 肖红, 许少华. 基于句法分析和情感词典的网络舆情倾向性分析研究[J]. 小型微型计算机系统, 2014, 35(4): 811-813.
[18] (Xiao Hong, Xu Shaohua.Analysis on Web Public Opinion Orientation Based on Syntactic Parsing and Emotional Dictionary[J]. Journal of Chinese Computer Systems, 2014, 35(4): 811-813.)
[19] Turney P D, Littman M L.Measuring Praise and Criticism: Inference of Semantic Orientation from Association[J]. ACM Transactions on Information Systems, 2003, 21(4): 315-346.
[20] 姚天防, 娄德成. 汉语语句主题语义倾向分析方法的研究[J]. 中文信息学报, 2007, 21(5): 73-79.
[20] (Yao Tianfang, Lou Decheng.Research on Semantic Orientation Analysis for Topics in Chinese Sentences[J]. Journal of Chinese Information Processing, 2007, 21(5): 73-79.)
[21] Che W X, Li Z H, Liu T.LTP: A Chinese Language Technology Platform [C]. In: Proceedings of the 23rd International Conference on Computational Linguistics (COLING 2010), Beijing, China.2010: 13-16.
[22] 刘挺, 马金山. 汉语自动句法分析的理论与方法[J]. 当代语言学, 2009, 11(2): 100-112.
[22] (Liu Ting, Ma Jinshan.Theories and Methods of Chinese Automatic Syntactic Parsing: A Critical Survey[J]. Contemporary Linguistics, 2009, 11(2): 100-112.)
[23] 万常选, 江腾蛟, 钟敏娟, 等. 基于词性标注和依存句法的Web金融信息情感计算[J]. 计算机研究与发展, 2013, 50(12): 2554-2569.
[23] (Wan Changxuan, Jiang Tengjiao, Zhong Minjuan, et al.Sentiment Computing of Web Financial Information Based on the Part-of-Speech Tagging and Dependency Parsing[J]. Journal of Computer Research and Development, 2013, 50(12): 2554-2569.)
[24] NLPIR/ICTCLAS 汉语分词系统[EB/OL]. [2013-07-02]. .
[24] (NLPIR/ICTCLAS Chinese Segmentation System [EB/OL]. [2013-07-02].
[25] Cui H, Mittal V, Datar M.Comparative Experiments on Sentiment Classification for Online Product Reviews[C]. In: Proceedings of the 21st National Conference on Artificial Intelligence. Menlo Park: AAAI Press, 2006: 1265-1270.
[1] 尤众喜,华薇娜,潘雪莲. 中文分词器对图书评论和情感词典匹配程度的影响 *[J]. 数据分析与知识发现, 2019, 3(7): 23-33.
[2] 杨亚楠,赵文辉,张健,谭珅,张贝贝. 基于多视图协同的政策文本可视化研究*[J]. 数据分析与知识发现, 2019, 3(6): 30-41.
[3] 张梦吉,杜婉钰,郑楠. 引入新闻短文本的个股走势预测模型[J]. 数据分析与知识发现, 2019, 3(5): 11-18.
[4] 蒋翠清,郭轶博,刘尧. 基于中文社交媒体文本的领域情感词典构建方法研究*[J]. 数据分析与知识发现, 2019, 3(2): 98-107.
[5] 余本功,张培行,许庆堂. 基于F-BiGRU情感分析的产品选择方法*[J]. 数据分析与知识发现, 2018, 2(9): 22-30.
[6] 曾子明,杨倩雯. 基于LDA和AdaBoost多特征组合的微博情感分析*[J]. 数据分析与知识发现, 2018, 2(8): 51-59.
[7] 张宁,尹乐民,何立峰. 网络股评“发布者-关注者”BSI与股票市场关联性研究*[J]. 数据分析与知识发现, 2018, 2(6): 1-12.
[8] 王秀芳,盛姝,路燕. 一种基于话题聚类及情感强度的微博舆情分析模型*[J]. 数据分析与知识发现, 2018, 2(6): 37-47.
[9] 李琳,李辉. 一种基于概念向量空间的文本相似度计算方法[J]. 数据分析与知识发现, 2018, 2(5): 48-58.
[10] 杨斯楠,徐健,叶萍萍. 网络评论情感可视化技术方法及工具研究*[J]. 数据分析与知识发现, 2018, 2(5): 77-87.
[11] 王婷婷,王凯平,戚桂杰. 基于情感分析的开放式创新平台创意采纳研究: 以Salesforce为例*[J]. 数据分析与知识发现, 2018, 2(4): 38-47.
[12] 范馨月,崔雷. 基于文本挖掘的药物副作用知识发现研究[J]. 数据分析与知识发现, 2018, 2(3): 79-86.
[13] 赵杨,李齐齐,陈雨涵,曹文航. 基于在线评论情感分析的海淘APP用户满意度研究*[J]. 数据分析与知识发现, 2018, 2(11): 19-27.
[14] 何跃,朱灿. 基于微博的意见领袖网情感特征分析*——以“非法疫苗”事件为例[J]. 数据分析与知识发现, 2017, 1(9): 65-73.
[15] 张红丽,刘济郢,杨斯楠,徐健. 基于网络用户评论的评分预测模型研究*[J]. 数据分析与知识发现, 2017, 1(8): 48-58.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn