基于THUCTC的金融语料情感分析模型优化

饶东宁; 黄思宏

doi:10.12052/gdutxb.180016

欢迎来到能源电力期刊网！

English Version 期刊登录

您当前的位置：

首页 >

文章列表页 >

基于THUCTC的金融语料情感分析模型优化

综合研究 | 更新时间：2026-05-27

- 基于THUCTC的金融语料情感分析模型优化
- Model Optimization of Financial Corpus Sentiment Analysis Based on THUCTC
- 广东工业大学学报 2018年35卷第3期页码：37-42
- 作者机构：
  
  广东工业大学　计算机学院,广东,广州,510006
- 作者简介：
  
  饶东宁(1977–)，男，副教授，博士，主要研究方向为金融智能、智能规划
  黄思宏(1993–)，男，硕士研究生，主要研究方向为金融智能. E-mail: 584654848@qq.com
- 基金信息：
  
  广东省自然科学基金资助项目(2016A030313084，2016A030313700)
- DOI：10.12052/gdutxb.180016
  中图分类号： TP181
- 纸质出版：2018
- 稿件说明：
移动端阅览
饶东宁, 黄思宏. 基于THUCTC的金融语料情感分析模型优化[J]. 广东工业大学学报, 2018, 35(3): 37-42.

Rao Dong-ning, Huang Si-hong. Model Optimization of Financial Corpus Sentiment Analysis Based on THUCTC[J]. 2018, 35(3): 37-42.
饶东宁, 黄思宏. 基于THUCTC的金融语料情感分析模型优化[J]. 广东工业大学学报, 2018, 35(3): 37-42. DOI： 10.12052/gdutxb.180016.

Rao Dong-ning, Huang Si-hong. Model Optimization of Financial Corpus Sentiment Analysis Based on THUCTC[J]. 2018, 35(3): 37-42. DOI： 10.12052/gdutxb.180016.

摘要

近几年

情感分析技术引起人们的兴趣

在金融应用上

可以作为投资者投资前的参考. 但是现有方法存在应用过于专一、数据偏差、结果过于笼统和不够精确的问题. 因此本文优化一个通用的中文文本分类器

用于对在线评论数据和股票新闻数据进行情感分析. 收集整理了2万条数据作为语料库

每条数据分别由3个人进行独立标注. 之后对THUCTC进行优化

具体从3个方面对中文文本分类器进行优化

首先是词语切分

使用词干词典方法结合不同的分词法

实验比较后得到二分法为最好的结果; 其次

为分类器选择最好的内核

发现Liblinear内核对即时性要求较高的投资人更好

另一方面Libsvm在提高准确率方面更有优势; 最后在金融导向的情绪字典方面

它由Chi-square和TF-IDF方法构建

可用在普通文本分类器上. 通过这种方式

本文的结果可以被推广且不会失去准确性.

Abstract

Sentiment analysis has attracted interest recently. In financial applications

it can be a reference for investors. However

existing approaches are either so specific as to cause data drift or too general to be precise. Therefore

a general Chinese text classifier for online reviews and news on stocks is optimized. A corpus with 20000 items is first collected. Then

each item is labeled by three persons as ground truth. After that

the THUCTC is optimized

thus optimizing a general Chinese text classifier in three aspects. First

by tokenization

the THUCTC is modified to a 2-gram with a stemming dictionary method and got better results. Second

the best kernel is selected for classifier. The Liblinear kernel is found to be better for people pressed for time. On the other hand

the Libsvm kernel is good at promoting accuracy. Third

a finance-oriented sentiment dictionary is set based on Chi-square and TF-IDF approach. It can be used by on-the-shelf general text classifiers. In this way

the result can be generalized without the loss of preciseness.

关键词

Keywords

references

SAIF H, HE Y, FERNANDEZ M, et al . Contextual semantics for sentiment analysis of Twitter [J ] . Information Processing Management, 2015, 52(1): 5-19.

QIN Z, CONG Y, WAN T. Topic modeling of Chinese language beyond a bag-of-words [J]. Computer Speech Language, 2016, 40: 60-78.

QIAN Q, HUANG M, LEI J, et al. Linguistically regularized LSTMs for Sentiment Classification[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Canada: ACL, 2017: 1679-1689.

LI J, SUN M S. Scalable term selection for text categorization[C]// Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.Prague: EMNLP-CoNLL, 2007: 774-782.

LI J Y, SUN M S, et al. A comparison and semi-quantitative analysis of words and character-bigrams as features in Chinese text categorization[C]//Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics. Sydney: ACL, 2006: 17-21.

SHI Y B, YU Q S. Key words extraction algorithm based on Chi-square value of co-concurrence words [J]. Computer Engineering, 2016, 42(6): 191-195.

ZHU J, WANG H, ZHU M, et al . Aspect-based opinion polling from customer reviews [J ] . IEEE Transactions on Affective Computing, 2011, 2(1): 37-49.

LI X D. Behavioral finance theory: Research system and prospects [J]. Journal of Financial Research, 2005(1): 175-190.

BEKAERT G, EHRMANN M, FRATZSCHER M, et al . The global crisis and equity market contagion [J ] . Journal of Finance, 2014, 69(6): 2597-2649.

GIANNETTI M, WANG T Y. Corporate scandals and household stock market participation [J]. Social Science Electronic Publishing, 2016, 71(6): 2591-2636.

AVDIS E. Information tradeoffs in dynamic financial markets [J]. Journal of Financial Economics, 2016, 122(3): 568-584.

EDELEN R M, INCE O S, KADLEC G B. Institutional investors and stock return anomalies [J]. Journal of Financial Economics, 2016, 119(3): 472-488.

CHANG T Y, HARTZMARK S M, SOLOMON D H, et al . Being surprised by the unsurprising: earnings seasonality and stock returns [J ] . Social Science Electronic Publishing, 2016, 30(8): 281-323.

RUAN X, WILSON S, MIHALCEA R. Finding optimists and pessimists on Twitter[C]// Meeting of the Association for Computational Linguistics. Berlin: ACL, 2016: 320-325.

ZHANG D. Internet stock analysts do affect the stock market trend_stock-based sentiment analysis perspective [J]. Modern Economic Information, 2015(1): 355-357.

JIANG T J, WANG C X, LIU D X, et al . Extracting target-opinion pairs based on semantic analysis [J ] . Chinese Journal of Computers, 2017, 40(3): 617-633.

RAO D N, WEN Y L, WEI L, et al . A weighted centrality algorithm for social networks based on Spark platform in different cultural environments [J ] . Journal of Guangdong University of Technology, 2017, 34(3): 15-20.

LIN S, ZHAO F. An application research of linear model in the advertising system based on Spark [J]. Journal of Guangdong University of Technology, 2016, 33(5): 28-33.

WANG H W, ZHENG L J, LIU Z Y, et al . Emotional feature selection of Chinese web comments [J ] . China Journal of Information Systems, 2012(1): 76-86.

CATAL C, GULDAN S. Product review management software based on multiple classifiers [J]. Iet Software, 2017, 11(3): 89-92.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于MABM的消费者情感倾向识别模型——以电影评论为例

短文本特征的组合加权方法

基于混合高斯分布伪样本生成的情感分析方法

面向汽车评论的细粒度情感分析方法研究

SCA-YOLO: 基于可变形卷积与上下文感知注意力的实时目标检测