JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE) ›› 2019, Vol. 54 ›› Issue (3): 46-55.doi: 10.6040/j.issn.1671-9352.1.2018.159

•   • Previous Articles     Next Articles

User sentiment tendency aware based Micro-blog sentiment analysis method

Jie WU(),Xiao-fei ZHU*(),Yi-hao ZHANG,Jian-wu LONG,Xian-ying HUANG,Wu YANG   

  1. School of Computer Science and Engineering, Chongqing University of Technology, Chongqing 400054, China
  • Received:2018-10-17 Online:2019-03-01 Published:2019-03-19
  • Contact: Xiao-fei ZHU E-mail:wwjj@2017.cqut.edu.cn;zxf@cqut.edu.cn
  • Supported by:
    国家自然科学基金资助项目(61702063);国家自然科学基金资助项目(61502064);国家自然科学基金资助项目(61502065);国家社会科学基金资助项目(17XXW005);重庆市基础科学与前沿技术研究项目(cstc2017jcyjBX0059);重庆市基础科学与前沿技术研究项目(cstc2015jcyjBX0127);重庆市基础科学与前沿技术研究项目(cstc2017jcyjAX0144);重庆市基础科学与前沿技术研究项目(cstc2017jcyjAX0339);重庆市基础科学与前沿技术研究项目(cstc2017jcyjAX0144);重庆市教委人文社科重点研究项目(17SKG136)

RichHTML

26

PDF (PC)

491

Abstract:

Micro-blog's speech often has strong sentimental color, and the sentiment analysis of Micro-blog's speech is an important way to get users' opinions and attitudes. Many researchers conduct research via focusing on the parts of speech (POS), emotion symbol and emotion corpus. This paper proposes a novel method for Micro-blog sentiment analysis, which aims to identify the sentiment features of a text by modeling user sentiment tendency. Specifically, we construct a sentiment information embedded word embedding sequence, and input it into a long short term memory (LSTM) model to get a sentiment embedded output representation. Then we merge both the user sentiment tendency score and the output representation of LSTM, and use it as the input of a fully connected layer which is followed by a softmax layer to get the final sentiment classification result. The experiment shows that the performance of our proposed method UA-LSTM is better than all the baseline methods on the sentimental classification task, and it achieves the F1-score up to 0.91, with an improvement of 3.4% over the best baseline method MF-CNN.

Key words: sentiment analysis, long short term memory, user sentiment tendency

CLC Number: 

  • TP391

Fig.1

Network structure diagram with model UA-LSTM"

Table 1

Emotional tendency of some emoticons"

Fig.2

Splicing user emotional characteristics"

Fig.3

Comparison of recall for different user feature weights"

Table 2

Model parameter setting"

参数名 值
词向量维度 200
用户特征权重μ 0.8
权重正则限制 2
dropout 0.9

Fig.4

The effect of the number of training iterations on the mode"

Table 3

Test results of different models on three indicators (Preciseness, Recall, F1)"

模型 指标 积极 消极 总体
P 0.77 0.68 0.71
CDLS R 0.42 0.91 0.70
F1 0.54 0.78 0.70
P 0.67 0.73 0.70
LR R 0.57 0.80 0.71
F1 0.61 0.76 0.70
P 0.76 0.80 0.78
SVM R 0.69 0.85 0.78
F1 0.72 0.82 0.78
P 0.85 0.81 0.83
W2V+CNN R 0.74 0.90 0.83
F1 0.79 0.85 0.83
P 0.91 0.80 0.85
Att-CTL R 0.72 0.94 0.84
F1 0.80 0.86 0.84
P 0.91 0.86 0.88
MF-CNN R 0.79 0.95 0.88
F1 0.84 0.90 0.88
P 0.92 0.91 0.91
UA-LSTM R 0.88 0.94 0.91
F1 0.90 0.92 0.91
1 PANG B , LEE L . Opinion mining and sentiment analysis[J]. Foundations and Trends in Information Retrieval, 2008, 2 (1/2): 1- 135.
2 丁兆云, 贾焰, 周斌. 微博数据挖掘研究综述[J]. 计算机研究与发展, 2014, 51 (4): 691- 706.
DING Zhaoyun , JIA Yan , ZHOU Bin . Survey of data mining for microblogs[J]. Journal of Computer Research and Development, 2014, 51 (4): 691- 706.
3 TABOADA M , BROOTE J , TOFILOSTI M , et al. Lexicon-based methods for sentiment analysis[J]. Computational Linguistics, 2011, 37 (2): 267- 307.
doi: 10.1162/COLI_a_00049
4 WIEBE J , WILSON T , CARDIE C . Annotating expressions of opinions and emtions in language[J]. Language Resources and Evaluation, 2005, 39 (2): 165- 210.
5 BOIY E , MOENS M F . A machine learning approach to sentiment analysis in multilingual Web texts[J]. Information Retrieval, 2009, 12 (5): 526- 558.
doi: 10.1007/s10791-008-9070-z
6 陈铁明, 缪茹一, 王小号. 融合显性和隐性特征的中文微博情感分析[J]. 中文信息学报, 2016, 30 (4): 184- 192.
CHEN Tieming , MIAO Ruyi , WANG Xiaohao . Chinese micro-blog sentiment analysis using both explicit and implicit text features[J]. Journal of Chinese Information Processing, 2016, 30 (4): 184- 192.
7 万圣贤, 兰艳艳, 郭嘉丰, 等. 基于弱监督预训练深度模型的微博情感分析[J]. 中文信息学报, 2017, 31 (3): 191- 197.
WAN Shengxian , LAN Yanyan , GUO Jiafeng , et al. Pretrain deep models by distant supervision for weibo sentiment analysis[J]. Journal of Chinese Information Processing, 2017, 31 (3): 191- 197.
8 KIM Y . Convolutional neural networks for sentence classification[J]. Eprint Arxiv, 2014, 2014: 1746- 1751.
9 王文凯,王黎明,柴玉梅.基于卷积神经网络和Tree-LSTM的微博情感分析[J/OL].计算机应用研究, 2019, 36(5).(2018-03-09).http://www.arocmag.com/article/02-2019-05-007.html.
WANG Wenkan, WANG Liming, CHAI Yumei.Sentiment analysis of micro-blog based on CNN and Tree-LSTM[J/OL]. Application Research of Computers, 2019, 36(5).(2018-03-09). http://www.arocmag.com/article/02-2019-05-007.html.
10 蔡林森,彭超,陈思远,等.基于多样化特征卷积神经网络的情感分析[J/OL].计算机工程, [2018-03-14].https://doi.org/10.19678/j.issn.1000-3428.0050338.
CAI Linsen, PENG Chao, CHEN Siyuan, et al. Sentiment analysis based on multiple features vonvolutional neural networks[J/OL]. Computer Engineering, [2018-03-14]. https://doi.org/10.19678/j.issn.1000-3428.0050338.
11 赵妍妍, 秦兵, 刘挺. 文本情感分析[J]. 软件学报, 2010, 21 (8): 1834- 1848.
ZHAO Yanyan , QIN Bing , LIU Ting . Text sentiment analysis[J]. Journal of Software, 2010, 21 (8): 1834- 1848.
12 何炎祥, 孙松涛, 牛菲菲, 等. 用于微博情感分析的一种情感语义增强的深度学习模型[J]. 计算机学报, 2017, 40 (4): 773- 790.
HE Yanxiang , SUN Hongtao , NIU Feifei , et al. A deep learning model enhanced with emotion semantics for Microblog sentiment analysis[J]. Chinese Jouranal of Computers, 2017, 40 (4): 773- 790.
13 董振东.知网情感分析用词语集[CP/OL]. (2012-04-25).http://www.keenage.com.
DONG Zhendong.Word sets for HowNet sentiment analysis[CP/OL]. (2012-04-25).http://www.keenage.com.
14 赵妍妍, 秦兵, 石秋慧, 等. 大规模情感词典的构建及其在情感分类中的应用[J]. 中文信息学报, 2017, 31 (2): 187- 193.
ZHAO Yanyan , QIN Bing , SHI Qiuhui , et al. Large-scale sentiment lexicon collection and its application in sentiment classification[J]. Journal of Chinese Information Processing, 2017, 31 (2): 187- 193.
15 于海燕, 陆慧娟, 郑文斌. 情感分类中基于词性嵌入的特征权重计算方法[J]. 计算机工程与应用, 2017, 53 (22): 121- 125.
doi: 10.3778/j.issn.1002-8331.1605-0342
YU Haiyan , LU Huijuan , ZHENG Wenbin . Feature weighting method based on part of speech embedding for sentiment classification[J]. Computer Engineering and Applications, 2017, 53 (22): 121- 125.
doi: 10.3778/j.issn.1002-8331.1605-0342
16 王素格, 杨安娜, 李德玉. 基于汉语情感词表的句子情感倾向分类研究[J]. 计算机工程与应用, 2009, 45 (24): 153- 155.
doi: 10.3778/j.issn.1002-8331.2009.24.045
WANG Suge , YANG Anna , LI Deyu . Research on sentence sentiment classification based on Chinese sentiment word table[J]. Computer Engineering and Applications, 2009, 45 (24): 153- 155.
doi: 10.3778/j.issn.1002-8331.2009.24.045
17 张书卿, 周文, 欧阳纯萍, 等. 基于主体句和句法依赖的微博情感倾向性分析[J]. 南华大学学报(自然科学版), 2015, 29 (1): 109- 114.
doi: 10.3969/j.issn.1673-0062.2015.01.023
ZHANG Shuqing , ZHOU Wen , OUYANG Chunping , et al. Sentiment analysis of Micro Blog based on the main sentence and syntactic dependencies[J]. Journal of University of South China(Science and Technology), 2015, 29 (1): 109- 114.
doi: 10.3969/j.issn.1673-0062.2015.01.023
18 JIANG F , LIU Y , LUAN H , et al. Microblog sentiment analysis with emoticon space model[J]. Journal of Computer Science and Technology, 2015, 30 (5): 1120- 1129.
doi: 10.1007/s11390-015-1587-1
19 PANG B, LEE L, VAITHYANATHAN S. Thumbs up?: sentiment classification using machine learing techniques[C]//Proceedings of the ACL-02 Conference on Empirical Methods in Natural Ianguage Processing: Volume 10.[S.l]: Association for Computational Linguistics, 2002: 79-86.
20 张志琳, 宗成庆. 基于多样化特征的中文微博情感分类方法研究[J]. 中文信息学报, 2015, 29 (4): 134- 143.
doi: 10.3969/j.issn.1003-0077.2015.04.018
ZHANG Zhilin , ZONG Chengqing . Sentiment analysis of Chinese Micro Blog based on rich-features[J]. Journ al of Chinese Information Processing, 2015, 29 (4): 134- 143.
doi: 10.3969/j.issn.1003-0077.2015.04.018
21 陈钊, 徐睿峰, 桂林, 等. 结合卷积神经网络和词语情感序列特征的中文情感分析[J]. 中文信息学报, 2015, 29 (6): 172- 178.
doi: 10.3969/j.issn.1003-0077.2015.06.023
CHEN Zhao , XU Ruifeng , GUI Lin , et al. Combining convolutional neural networks and word sentiment sequence features for Chinese text sentiment analysis[J]. Journal of Chinese Information Processing, 2015, 29 (6): 172- 178.
doi: 10.3969/j.issn.1003-0077.2015.06.023
22 杨艳, 徐冰, 杨沐昀, 等. 一种基于联合深度学习模型的情感分类方法[J]. 山东大学学报(理学版), 2017, 52 (9): 19- 25.
YANG Yan , XU Bing , YANG Muyun , et al. An emotional classification method based on joint deep learning model[J]. Journal of Shandong University(Natural Science), 2017, 52 (9): 19- 25.
23 陈国兰. 基于情感词典与语义规则的微博情感分析[J]. 情报探索, 2016, (2): 1- 6.
doi: 10.3969/j.issn.1005-8095.2016.02.001
CHEN Guolan . Microblog sentiment analysis basing on emotion dictionary and semantic rule[J]. Information Research, 2016, (2): 1- 6.
doi: 10.3969/j.issn.1005-8095.2016.02.001
[1] CHEN Xin, XUE Yun, LU Xin, LI Wan-li, ZHAO Hong-ya, HU Xiao-hui. Text feature extraction method for sentiment analysis based on order-preserving submatrix and frequent sequential pattern mining [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2018, 53(3): 36-45.
[2] YU Chuan-ming, FENG Bo-lin, TIAN Xin, AN Lu. Deep representative learning based sentiment analysis in the cross-lingual environment [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2018, 53(3): 13-23.
[3] HE Yan-xiang, LIU Jian-bo, SUN Song-tao, WEN Wei-dong. Product reviews sentiment classification in Micro-blog based on cascaded conditional random field [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2015, 50(11): 67-73.
[4] ZHU Zhu, LI Shou-shan, DAI Min, ZHOU Guo-dong. Opinion target extraction with active-learning and automatic annotation [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2015, 50(07): 38-44.
[5] ZHOU Wen, ZHANG Shu-qing, OUYANG Chun-ping, LIU Zhi-ming, YANG Xiao-hua. Topic sentiment analysis of Chinese news based on emotional dependency tuple [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(12): 1-6.
[6] SUN Song-tao, HE Yan-xiang, CAI Rui, LI Fei, HE Fei-yan. Comparative study of methods for Micro-blog sentiment evaluation tasks [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 43-50.
[7] LIU Ming, ZAN Hong-ying, YUAN Hui-bin. Key sentiment sentence prediction using SVM and RNN [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 68-73.
[8] ZHU Xi, DONG Xi-shuang, GUAN Yi, LIU Zhi-guang. Sentiment analysis of Chinese Micro-blog based on semi-supervised learning [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 37-42.
[9] YANG Jia-neng, YANG Ai-min, ZHOU Yong-mei. Sentiment classification method of Chinese Micro-blog based on semantic analysis [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(11): 14-21.
[10] ZHANG Cheng-gong 1, 2, LIU Pei-yu1, 2*, ZHU Zhen-fang1,2, FANG Ming1,2. A sentiment analysis method based on a polarity lexicon [J]. J4, 2012, 47(3): 47-50.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] ZHAO Tong-xin1, LIU Lin-de1*, ZHANG Li1, PAN Cheng-chen2, JIA Xing-jun1. Pollinators and pollen polymorphism of  Wisteria sinensis (Sims) Sweet[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(03): 1 -5 .
[2] GUO Lan-lan1,2, GENG Jie1, SHI Shuo1,3, YUAN Fei1, LEI Li1, DU Guang-sheng1*. Computing research of the water hammer pressure in the process of #br# the variable speed closure of valve based on UDF method[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(03): 27 -30 .
[3] LI Min1,2, LI Qi-qiang1. Observer-based sliding mode control of uncertain singular time-delay systems#br#[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(03): 37 -42 .
[4] HAN Ya-fei, YI Wen-hui, WANG Wen-bo, WANG Yan-ping, WANG Hua-tian*. Soil bacteria diversity in continuous cropping poplar plantation#br# by high throughput sequencing[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(05): 1 -6 .
[5] MA Yuan-yuan, MENG Hui-li, XU Jiu-cheng, ZHU Ma. Normal distribution of lattice close-degree based on granular computing[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2014, 49(08): 107 -110 .
[6] XU Jun-feng. On the growth of the meromorphic solutions of complex algebraic differential equations[J]. J4, 2010, 45(6): 91 -93 .
[7] WU Zhi-jun,SHEN Dan-dan. Architecture and key technologies of network-enabled next generation global flight tracking based on information integration and sharing[J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2016, 51(11): 1 -6 .
[8] QU Xiao-ying ,ZHAO Jing . Solution of the Klein-Gordon equation for the time-dependent potential[J]. J4, 2007, 42(7): 22 -26 .
[9] CHEN Yong, . An approximate algorithm for the cost totalcoloring of trees[J]. J4, 2006, 41(1): 111 -114 .
[10] LIU Da-Kun, Wang Shu-Dong. Incidence chromatic number of several generalized Petersen graphs[J]. J4, 2008, 43(12): 48 -51 .
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd