Please wait a minute...
Advanced Search
数据分析与知识发现  2018, Vol. 2 Issue (6): 1-12     https://doi.org/10.11925/infotech.2096-3467.2017.1174
  研究论文 本期目录 | 过刊浏览 | 高级检索 |
网络股评“发布者-关注者”BSI与股票市场关联性研究*
张宁, 尹乐民(), 何立峰
青岛大学商学院 青岛 266071
Impacts of “Poster-Follower” Sentiment on Stock Market Performance
Zhang Ning, Yin Lemin(), He Lifeng
School of Business, Qingdao University, Qingdao 266071, China
全文: PDF (680 KB)   HTML ( 3
输出: BibTeX | EndNote (RIS)      
摘要 

目的】研究网络股评“发布者-关注者”BSI投资者情绪指标与股票市场的关联性。【方法】通过情感词典匹配方法对上证指数股评进行情感分类, 构造4种“发布者-关注者”情感倾向值SV, 并依此构建“发布者-关注者”BSI投资者情绪指标, 建立线性与非线性模型进行实证检验。【结果】文本挖掘构建的BSI指标与上证综指的价格和收益率显著相关, 并且BSI对市场收益率的预测能力强于对收盘价格的预测。【局限】仅考虑涨跌两种情绪极性, 未对情感强度进行深入分析。【结论】构造的BSI指标能够有效预测整体股票市场走势, 并且丰富了投资者情绪的测量体系。

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
张宁
尹乐民
何立峰
关键词 股票评论股评关注度文本挖掘投资者情绪    
Abstract

[Objective] The paper investigates the relationship between the “Bullish Sentiment Index” (BSI) of online reviews/following comments and the performance of stock market. [Methods] First, we conducted sentiment classification for comments on Shanghai Stock Exchange Composite Index using semantic analysis method. Then, we built the sentiment tendencies of these reviews and constructed their “Poster-Follower” BSI. Finally, we used linear and nonlinear models to examine the proposed method empirically. [Results] The BSI based on our proposed method (text mining) could effectively predict the stock market trend, especially on its returns. [Limitations] We only consider two emotional polarities and more research is needed to enhance the sentimental strength. [Conclusions] The Bullish Sentiment Index could effectively predict the overall stock market trend by measuring investors’ sentiment.

Key wordsStock Comment    Stock Comment Attention Rate    Text Mining    Investor Sentiment
收稿日期: 2017-11-22      出版日期: 2018-07-11
ZTFLH:  G35  
基金资助:*本文系国家自然科学基金项目“金融市场传闻与澄清公告的信息加工机制研究”(项目编号: 71403138)、山东省高等学校人文社会科学研究项目“多元视角下的网络口碑用户参与机制研究”(项目编号: J16YF15)和青岛市社会科学规划项目“消费者、商家、平台三方视角下的网络口碑用户参与机制研究”(项目编号: QDSKL1601077)的研究成果之一
引用本文:   
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.
Zhang Ning,Yin Lemin,He Lifeng. Impacts of “Poster-Follower” Sentiment on Stock Market Performance. Data Analysis and Knowledge Discovery, 2018, 2(6): 1-12.
链接本文:  
http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2017.1174      或      http://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2018/V2/I6/1
  投资者情绪指标构建过程
统计指标 均值 标准差 最大值 最小值
评论标题长度(字) 17.042 5.33 36 2
评论内容长度(字) 363.349 562.503 12875 2
评论关注度(万次) 1.583 13.232 653.984 0.012
每日发帖数量(条) 252.459 207.733 1373 3
每日关注数量(万次) 453.977 446.926 2972.288 7.217
  上证指数股票评论数据描述性统计
情感倾向 指标 分类效果
看涨 召回率 94.6%
准确率 90.6%
F值 92.7%
看跌 召回率 93.5%
准确率 89.6%
F值 91.5%
  情感词典匹配方法的分类效果
均值 标准差 最大值 最小值
每日看涨评论数量(条) 143.00 118.67 889 1
每日看跌评论数量(条) 108.98 111.44 635 2
  股票评论情感分类数据描述性统计
合成方法
调整方法
加法合成 乘法合成
对数调整 $S{{V}_{la}}=1+\ln (1+n)$ $S{{V}_{lm}}=1\times \ln (e+n)$
比值调整 $S{{V}_{ra}}=1+\frac{n}{\mathop{\sum }^{}n}$ $S{{V}_{rm}}=1\times \frac{n}{\mathop{\sum }^{}n}$
  “发布者-关注者”综合情感倾向值SV计算方法
变量性质 变量名称 变量符号 变量描述
被解释变量 当日上证综合指数 CIt 上证综合指数的当日收盘价
当日上证指数收益率 Rt 上证综合指数的当日收益率
解释变量 当日投资者情绪指数 BSIt 基于文本挖掘的“发布者-关注者”当日综合情绪指标
前一日投资者情绪指数 BSIt-1 基于文本挖掘的“发布者-关注者”前一日综合情绪指标
控制变量 波动率 FR 上证市场一个交易日中股票收益的变化程度
换手率 TR 上证市场一个交易日中股票转手买卖的频率
前一日上证综合指数 CIt-1 上证综合指数的前一日收盘价
  变量设置
变量 M1 BSIla BSIlm BSIra BSIrm
M2 M3 M4 M2 M3 M4 M2 M3 M4 M2 M3 M4
系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数
(t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值)
BSI1t 123.018*** 124.322*** 165.589*** 59.520***
(9.352) (-9.415) (-12.013) (-6.263)
BSI1(t-1) -53.927*** -50.790*** -77.985*** -13.733
(-4.102) (-3.862) (-5.682) (-1.453)
BSI2t 20.055*** 20.661*** 35.956*** 30.154***
(8.104) (-8.26) (-11.506) (-5.69)
BSI2(t-1) -8.395*** -8.212*** -16.845*** -3.138
(3.370) (-3.270) (-5.397) (-0.583)
BSI3t 61.384*** 62.163*** 82.794*** 29.781***
(9.318) (-9.415) (-12.013) (-6.27)
BSI3(t-1) -26.990*** -25.397*** -38.992*** -6.894
(-4.099) (-3.862) (-5.682) (-1.460)
TR 26.038*** 21.900*** 22.794*** 21.784*** 21.702*** 22.785*** 21.703*** 19.940*** 19.532*** 19.940*** 21.871*** 22.477*** 21.871***
(5.323) (5.050) (5.117) (5.013) (-5.034) (-5.159) (-5.034) (-4.94) (-4.726) (-4.94) (-4.744) (-4.802) (-4.745)
FR -18.104*** -16.033*** -16.957*** -16.000*** -15.786*** -16.783*** -15.786*** -14.292*** -14.383*** -14.292*** -16.120*** -15.870*** -16.126***
(-7.202) (-7.269) (-7.486) (-7.241) (-7.161) (-7.440) (-7.161) (-6.974) (-6.868) (-6.974) (-6.775) (-6.496) (-6.780)
CIt-1 0.888*** 0.903*** 0.898*** 0.903*** 0.904*** 0.899*** 0.904*** 0.908*** 0.907*** 0.908*** 0.892*** 0.889*** 0.892***
(48.314) (57.627) (55.295) (57.564) (-57.791) (-55.599) (-57.791) (-62.967) (-61.919) (-62.967) (-52.028) (-51.123) (-52.041)
常数项 306.752*** 223.635*** 275.881*** 258.798*** 219.170*** 272.781*** 255.947*** 198.677*** 246.595*** 242.479*** 270.757*** 302.424*** 293.549***
(5.640) (4.717) (5.741) (5.571) (-4.621) (-5.702) (-5.526) (-4.575) (-5.684) (-5.678) (-5.339) (-5.882) (-5.798)
F 28.539*** 46.424*** 34.778*** 46.118*** 47.255*** 36.252*** 47.257*** 77.309*** 71.110*** 77.309*** 20.208*** 16.323*** 20.258***
R2 0.931 0.951 0.947 0.951 0.951 0.948 0.951 0.959 0.957 0.959 0.941 0.94 0.941
ΔR2 0.931*** 0.020*** 0.016*** 0.020*** 0.020*** 0.016*** 0.020*** 0.028*** 0.026*** 0.028*** 0.010*** 0.009*** 0.010***
  模型一回归分析结果(因变量为“上证综合指数”CI, 样本数量N=244)
变量 M1 BSIla BSIlm BSIra BSIrm
M2 M3 M4 M2 M3 M4 M2 M3 M4 M2 M3 M4
系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数 系数
(t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值) (t值)
BSI1t 4.421*** 4.475*** 5.858*** 2.040***
(9.330) (-9.455) (-11.779) (-5.923)
BSI1(t-1) -1.917*** -1.806*** -2.880*** -0.621
(-4.064) (-3.821) (-5.835) (-1.826)
BSI2t 0.713*** 0.736*** 1.272*** 1.013***
(7.995) (-8.173) (-11.281) (-5.267)
BSI2(t-1) -0.307*** -0.300*** -0.622*** -0.209
(-3.416) (-3.311) (-5.538) (-1.076)
BSI3t 2.205*** 2.237*** 2.929*** 1.021***
(9.370) (-9.455) (-11.779) (-5.932)
BSI3(t-1) -0.962*** -0.903*** -1.440*** -0.311
(-4.055) (-3.822) (-5.835) (-1.832)
TR 0.554*** 0.446** 0.469** 0.442** 0.440** 0.469** 0.440** 0.404** 0.387** 0.404** 0.431** 0.451** 0.431**
(3.286) (2.937) (3.031) (2.971) (-2.953) (-3.066) (-2.953) (-2.859) (-2.677) (-2.859) (-2.683) (-2.756) (-2.684)
FR -0.391*** -0.342*** -0.369*** -0.341*** -0.334*** -0.363*** -0.334*** -0.295*** -0.297*** -0.295*** -0.336*** -0.328*** -0.336***
(-4.631) (-4.582) (-4.809) (-4.607) (-4.505) (-4.765) (-4.505) (-4.230) (-4.162) (-4.230) (-4.145) (-3.914) (-4.150)
常数项 -0.593 -2.008*** -0.691* -0.748** -2.120*** -0.724* -0.786** -2.307*** -0.760** -0.818** -1.341*** -0.628* -0.632*
(-1.777) (-2.634) (-2.341) (-4.768) (-4.897) (-2.464) (-2.773) (-5.548) (-2.861) (-3.127) (-3.271) (-1.982) (-2.018)
F 11.980*** 46.563*** 34.081*** 46.238*** 47.615*** 35.709*** 47.615*** 75.529*** 69.446*** 75.529*** 18.659*** 14.390*** 18.718***
R2 0.093 0.353 0.299 0.351 0.357 0.306 0.357 0.451 0.433 0.451 0.219 0.193 0.219
ΔR2 0.093*** 0.260*** 0.206*** 0.259*** 0.264*** 0.214*** 0.264*** 0.358*** 0.340*** 0.358*** 0.126*** 0.100*** 0.126***
  模型二回归分析结果(因变量为“上证综指收益率”R, 样本数量N=244)
变量 模型三(因变量为CI) 模型四(因变量为R)
M1(PBSI1) M2(PBSI2) M3(PBSI3) M4(PBSI4) M5(PBSI5) M6(PBSI6)
系数
(t值)
系数
(t值)
系数
(t值)
系数
(t值)
系数
(t值)
系数
(t值)
PBSI1t 145.850***
(7.315)
5.297***
(7.452)
PBSI1(t-1) -90.081***
(-4.609)
-3.211***
(-4.587)
PBSI1t×ATTt 0.059*
(2.007)
0.002*
(2.188)
PBSI1(t-1)×ATTt-1 -0.004
(-0.131)
0.000
(0.084)
PBSI2t 30.313***
(6.683)
1.107***
(6.771)
PBSI2(t-1) -20.523***
(-4.596)
-0.732***
(-4.523)
PBSI2t×ATTt 0.016*
(2.419)
0.001**
(2.584)
PBSI2(t-1)×ATTt-1 -0.001
(-0.188)
0.000
(0.074)
PBSI3t 71.315***
(7.182)
2.633***
(7.383)
PBSI3(t-1) -47.989***
(-4.932)
-1.697***
(-4.821)
PBSI3t×ATTt 0.032*
(2.204)
0.001*
(2.293)
PBSI3(t-1)×ATTt-1 0.000
(0.032)
0.000
(0.253)
ATTt-1 -0.007
(-0.364)
-0.010?
(-1.653)
-0.011?
(-1.756)
-0.000
(-0.136)
-0.000
(-0.335)
-0.000
(-0.414)
ATTt -0.031?
(-1.683)
-0.007
(-1.102)
-0.005
(-0.771)
-0.001
(-1.511)
0.000
(0.048)
0.000
(0.425)
TR 21.023***
(4.926)
21.168***
(4.932)
21.322***
(5.062)
0.376*
(2.609)
0.353*
(2.408)
0.363*
(2.534)
FR -14.154***
(-6.931)
-13.471***
(-6.478)
-13.351***
(-6.515)
-0.316***
(-4.523)
-0.294***
(-4.035)
-0.293***
(-4.076)
CIt-1 0.907***
(57.510)
0.897***
(56.140)
0.899***
(56.860)
常数项 223.208***
(4.454)
282.514***
(5.920)
275.968***
(5.836)
-1.789**
(-2.867)
-0.614*
(-2.151)
-0.690*
(-2.442)
F 2.017? 2.927? 2.436? 2.408? 3.371* 2.689?
R2 0.960 0.959 0.960 0.496 0.486 0.500
  投资者情绪与关注度交互作用分析(样本数量N=244)
预测模型 输出变量 输入变量 MSE
SVM _CI _Base 上证综合指数CIt 控制变量(CIt-1TRFR) 480.38
SVM _CI _BSI1 控制变量、BSI1tBSI1(t-1) 421.45
SVM _CI _ BSI2 控制变量、BSI2t、BSI2(t-1) 437.28
SVM _CI _ BSI3 控制变量、BSI3t、BSI3(t-1) 440.15
SVM _R _Base 上证综指收益率Rt 控制变量(TRFR) 0.58
SVM _R _ BSI1 控制变量、BSI1tBSI1(t-1) 0.45
SVM _R _BSI2 控制变量、BSI2t、BSI2(t-1) 0.43
SVM _R _BSI3 控制变量、BSI3t、BSI3(t-1) 0.47
RF _CI _Base 上证综合指数CIt 控制变量(CIt-1TRFR) 2633.16
RF _CI _BSI1 控制变量、BSI1tBSI1(t-1) 2034.15
RF _CI _BSI2 控制变量、BSI2tBSI2(t-1) 2126.18
RF _CI _BSI3 控制变量、BSI3tBSI3(t-1) 2301.17
RF _R _Base 上证综指收益率Rt 控制变量(TRFR) 0.54
RF _R _BSI1 控制变量、BSI1tBSI1(t-1) 0.34
RF _R _BSI2 控制变量、BSI2tBSI2(t-1) 0.33
RF _R _BSI3 控制变量、BSI3tBSI3(t-1) 0.34
  非线性模型预测结果
[1] Baker M, Wurgler J.Investor Sentiment in the Stock Market[J]. Journal of Economic Perspectives, 2007, 21(2): 129-151.
doi: 10.1257/jep.21.2.129
[2] Brown G W, Cliff M T.Investor Sentiment and the Near-term Stock Market[J]. Journal of Empirical Finance, 2004, 11(1): 1-27.
doi: 10.1016/j.jempfin.2002.12.001
[3] Fisher K L, Statman M.Investor Sentiment and Stock Returns[J]. Financial Analysts Journal, 2000, 56(2): 16-27.
doi: 10.3905/jwm.1999.320352
[4] 王美今, 孙建军. 中国股市收益、收益波动与投资者情绪[J]. 经济研究, 2004(10): 75-83.
[4] (Wang Meijin, Sun Jianjun. Stock Market Returns, Volatility and the Role of Investor Sentiment in China[J]. Economic Research Journal, 2004(10): 75-83.)
[5] 郁晨. 投资者情绪理论、度量及应用研究综述[J]. 金融评论, 2017(3): 111-126.
[5] (Yu Chen.Investor Sentiment Theory: Measurement and Application[J]. Chinese Review of Financial Studies, 2017(3): 111-126.)
[6] Barberis N, Shleifer A, Vishny R.A Model of Investor Sentiment[J]. Journal of Financial Economics, 1998, 49(3): 307-343 .
doi: 10.1016/S0304-405X(98)00027-0
[7] 张强, 杨淑娥, 杨红, 等. 中国股市投资者情绪与股票收益的实证研究[J]. 系统工程, 2007, 25(7): 13-17.
doi: 10.3969/j.issn.1001-4098.2007.07.003
[7] (Zhang Qiang, Yang Shue, Yang Hong.An Empirical Study on Investors’ Sentiment and Stock Returns in Chinese Stock Market[J].Systems Engineering, 2007, 25(7): 13-17.)
doi: 10.3969/j.issn.1001-4098.2007.07.003
[8] Stambaugh R F, Yu J F, Yuan Y.The Short of It: Investor Sentiment and Anomalies[J]. Journal of Financial Economics, 2012, 104(2): 288-302.
doi: 10.1016/j.jfineco.2011.12.001
[9] Antweiler W, Frank M Z.Is All that Talk just Noise? The Information Content of Internet Stock Message Boards[J]. The Journal of Finance, 2004, 59(3): 1259-1294.
doi: 10.1111/j.1540-6261.2004.00662.x
[10] Das S R, Chen M Y.Yahoo! for Amazon: Sentiment Extraction from Small Talk on the Web[J]. Management Science, 2007, 53(9): 1375-1388.
doi: 10.1287/mnsc.1070.0704
[11] 蒋翠清, 梁坤, 丁勇, 等. 基于社会媒体的股票行为预测[J]. 中国管理科学, 2015, 23(1): 17-24.
doi: 10.16381/j.cnki.issn1003-207x.2015.01.003
[11] (Jiang Cuiqing, Liang Kun, Ding Yong, et al.Predicting Stock Behavior via Social Media[J]. Chinese Journal of Management Science, 2015, 23(1): 17-24.)
doi: 10.16381/j.cnki.issn1003-207x.2015.01.003
[12] 陆静, 周媛. 投资者情绪对股价的影响——基于AH股交叉上市股票的实证分析[J]. 中国管理科学, 2015, 23(11): 21-28.
doi: 10.16381/j.cnki.issn1003-207x.2015.11.003
[12] (Lu Jing, Zhou Yuan.The Effect of Investor Sentiment on Stock Pricing—An Empirical Study Based on A-H Shares of Cross-listing Companies[J]. Chinese Journal of Management Science, 2015, 23(11): 21-28.)
doi: 10.16381/j.cnki.issn1003-207x.2015.11.003
[13] 宋顺林, 王彦超. 投资者情绪如何影响股票定价?—基于IPO公司的实证研究[J]. 管理科学学报, 2016, 19(5): 41-55.
doi: 10.3969/j.issn.1007-9807.2016.05.004
[13] (Song Shunlin, Wang Yanchao.How does Investor Sentiment Affect Stock Pricing? An Empirical Research Based on IPO Firms[J]. Journal of Management Sciences in China, 2016, 19(5): 41-55.)
doi: 10.3969/j.issn.1007-9807.2016.05.004
[14] 王春. 投资者情绪对股票市场收益和波动的影响——基于开放式股票型基金资金净流入的实证研究[J]. 中国管理科学, 2014, 22(9): 49-56.
[14] (Wang Chun.The Effect of Investor Sentiment on Return and Volatility of Stock Market-Based on Empirical Study of Open-end Equity Funds[J]. Chinese Journal of Management Science, 2014, 22(9): 49-56.)
[15] Chen M P, Chen P F, Lee C C.Asymmetric Effects of Investor Sentiment on Industry Stock Returns: Panel Data Evidence[J]. Emerging Markets Review, 2013, 14(1): 35-54.
doi: 10.1016/j.ememar.2012.11.001
[16] 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.
[16] (Duan Jiangjiao, Liu Hongzhong, Zeng Jianping.Research on the Impact of Investor Sentiment Index, Analyst Recommendation Index and Stock Index Yield - Based on the Ranking of China Orient Bank.com.cn and Sina.com[J]. Shanghai Finance, 2014(11): 60-64.)
[17] 王洪伟, 张对, 郑丽娟, 等. 网络股评对股市走势的影响:基于文本情感分析的方法[J]. 情报学报, 2015, 34(11): 1190-1202.
[17] (Wang Hongwei, Zhang Dui, Zheng Lijuan, et al.The Effect of Online Comments on Stock Trends by Sentiment Analysis[J]. Journal of the China Society for Scientific and Technical Information, 2015, 34(11): 1190-1202.)
[18] 黄润鹏, 左文明, 毕凌燕. 基于微博情绪信息的股票市场预测[J]. 管理工程学报, 2015, 29(1): 47-52.
[18] (Huang Runpeng, Zuo Wenming, Bi Lingyan.Predicting the Stock Market Based on Microblog Mood[J]. Journal of Industrial Engineering, 2015, 29(1): 47-52.)
[19] Kurov A.Investor Sentiment and the Stock Market’s Reaction to Monetary Policy[J]. Journal of Banking & Finance, 2010, 34(1): 139-149.
doi: 10.1016/j.jbankfin.2009.07.010
[20] Porshnev A, Redkin I, Shevchenko A.Machine Learning in Prediction of Stock Market Indicators Based on Historical Data and Data from Twitter Sentiment Analysis[C]// Proceedings of the 13th International Conference on Data Mining Workshops. IEEE, 2011: 440-444.
[21] Kearney C, Liu S.Textual Sentiment in Finance: A Survey of Methods and Models[J]. International Review of Financial Analysis, 2014, 33(3): 171-185.
doi: 10.1016/j.irfa.2014.02.006
[22] Oliveira N, Cortez P, Areal N.Stock Market Sentiment Lexicon Acquisition Using Microblogging Data and Statistical Measures[J]. Decision Support Systems, 2016, 85(C): 62-73.
doi: 10.1016/j.dss.2016.02.013
[23] Renault T.Intraday Online Investor Sentiment and Return Patterns in the U.S. Stock Market[J]. Journal of Banking & Finance, 2017, 84(11): 25-40.
doi: 10.1016/j.jbankfin.2017.07.002
[24] 杨晓兰, 沈翰彬, 祝宇. 本地偏好、投资者情绪与股票收益率:来自网络论坛的经验证据[J]. 金融研究, 2016(12): 143-158.
[24] (Yang Xiaolan, Shen Hanbin, Zhu Yu.The Effect of Local Bias in Investor Attention and Investor Sentiment on Stock Markets: Evidence from Online Forum[J]. Journal of Financial Research, 2016(12): 143-158.)
[25] Bollen J, Mao H, Zeng X.Twitter Mood Predicts the Stock Market[J]. Journal of Computational Science, 2011, 2(1):1-8.
doi: 10.1016/j.jocs.2010.12.007
[26] Cheng Y H, Ho H Y.Social Influence’s Impact on Reader Perceptions of Online Reviews[J]. Journal of Business Research, 2015, 68(4): 883-887.
doi: 10.1016/j.jbusres.2014.11.046
[27] Piñeiro-Chousa J R, López-Cabarcos M Á, Pérez-Pico A M. Examining the Influence of Stock Market Variables on Microblogging Sentiment[J]. Journal of Business Research, 2015, 69(6): 2087-2092.
doi: 10.1016/j.jbusres.2015.12.013
[28] Oliveira N, Cortez P, Areal N.The Impact of Microblogging Data for Stock Market Prediction: Using Twitter to Predict Returns, Volatility, Trading Volume and Survey Sentiment Indices[J]. Expert Systems with Applications, 2017, 73: 125-144.
doi: 10.1016/j.eswa.2016.12.036
[29] Cortez P, Embrechts M J.Using Sensitivity Analysis and Visualization Techniques to Open Black Box Data Mining Models[J]. Information Sciences, 2013, 225: 1-17.
doi: 10.1016/j.ins.2012.10.039
[30] 阳爱民, 林江豪, 周咏梅. 中文文本情感词典构建方法[J]. 计算机科学与探索, 2013, 7(11): 1033-1039.
doi: 10.3778/j.issn.1673-9418.1305008
[30] (Yang Aimin, Lin Jianghao, Zhou Yongmei.Method on Building Chinese Text Sentiment Lexicon[J]. Journal of Frontiers of Computer Science and Technology, 2013, 7(11): 1033-1039.)
doi: 10.3778/j.issn.1673-9418.1305008
[1] 夏天. 面向中文学术文本的单文档关键短语抽取 *[J]. 数据分析与知识发现, 2020, 4(7): 76-86.
[2] 马建霞,袁慧,蒋翔. 基于Bi-LSTM+CRF的科学文献中生态治理技术相关命名实体抽取研究*[J]. 数据分析与知识发现, 2020, 4(2/3): 78-88.
[3] 关鹏,王曰芬. 国内外专利网络研究进展*[J]. 数据分析与知识发现, 2020, 4(1): 26-39.
[4] 黄名选,卢守东,徐辉. 基于加权关联模式挖掘与规则后件扩展的跨语言信息检索 *[J]. 数据分析与知识发现, 2019, 3(9): 77-87.
[5] 岑咏华,谭志浩,吴承尧. 财经媒介信息对股票市场的影响研究: 基于情感分析的实证 *[J]. 数据分析与知识发现, 2019, 3(9): 98-114.
[6] 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.
[7] 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.
[8] 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.
[9] 汪强兵, 章成志. 融合内容与用户手势行为的用户画像构建系统设计与实现*[J]. 数据分析与知识发现, 2017, 1(2): 80-86.
[10] 谢秀芳, 张晓林. 针对科技路线图的文本挖掘研究: 集成分析及可视化*[J]. 数据分析与知识发现, 2017, 1(1): 16-25.
[11] 姚兆旭,马静. 面向微博话题的“主题+观点”词条抽取算法研究*[J]. 现代图书情报技术, 2016, 32(7-8): 78-86.
[12] 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.
[13] 毕强, 刘健, 鲍玉来. 基于语义相似度的文本聚类研究*[J]. 数据分析与知识发现, 2016, 32(12): 9-16.
[14] 林园园,战洪飞,余军合,李长江,张凡. 基于产品评论的消费者情感波动分析模型构建及实证研究*[J]. 现代图书情报技术, 2016, 32(11): 44-53.
[15] 隋明爽,崔雷. 结合多种特征的CRF模型用于化学物质-疾病命名实体识别[J]. 现代图书情报技术, 2016, 32(10): 91-97.
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