Please wait a minute...
Advanced Search
数据分析与知识发现  2020, Vol. 4 Issue (2/3): 207-213     https://doi.org/10.11925/infotech.2096-3467.2019.0678
  专辑 本期目录 | 过刊浏览 | 高级检索 |
一种基于CRF与ATAE-LSTM的细粒度情感分析方法*
薛福亮(),刘丽芳
天津财经大学商学院 天津 300222
Fine-Grained Sentiment Analysis with CRF and ATAE-LSTM
Xue Fuliang(),Liu Lifang
Business School, Tianjin University of Finance & Economics, Tianjin 300222, China
全文: PDF (831 KB)   HTML ( 14
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 应用细粒度情感分析方法提取产品属性及情感,进而将属性词聚类到属性面,分析用户在产品属性面的情感。【方法】 通过CRF抽取产品属性词,利用基于注意力机制的长短期记忆网络做属性情感分析,最后基于Word2Vec将属性词聚集为属性面,并分析电商平台产品属性面的情感。【结果】 CRF抽取属性词的F1值为0.76,ATAE-LSTM属性情感分析的F1值为0.78。【局限】 只抽取显式属性词,对隐式属性词抽取效果较差;数据集偏小。【结论】 通过对属性词的抽取、情感分析以及属性面聚类,可较好地解释用户对产品的属性偏好。

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
薛福亮
刘丽芳
关键词 CRF长短期记忆网络注意力机制情感分析Word2Vec    
Abstract

[Objective] This paper tries to extract product attributes, aiming to cluster these words and analyze user’s sentiments.[Methods] Firstly, we identified the attributes of products with CRF technique. Then, we analyzed the sentiment of extracted terms with attention-based LSTM. Finally, we clustered these terms into appropriate categories with the help of Word2Vec and conducted fine-grained sentiment analysis of the products.[Results] The F1 values of term extraction and sentiment analysis were 0.76 and 0.78.[Limitations] We only retrieved explicit terms for this study and the sample size needs to be expanded.[Conclusions] The proposed method could effectively explore user’s preference in products.

Key wordsCRF    LSTM    Attention Mechanism    Sentiment Analysis    Word2Vec
收稿日期: 2019-06-14      出版日期: 2020-04-26
ZTFLH:  TP391  
基金资助:*本文系天津市哲学社会科学规划项目“基于电子商务用户评论文本的领域情感词典构建方法研究”的研究成果之一(TJGL19-009)
通讯作者: 薛福亮     E-mail: fuliangxue@163.com
引用本文:   
薛福亮,刘丽芳. 一种基于CRF与ATAE-LSTM的细粒度情感分析方法*[J]. 数据分析与知识发现, 2020, 4(2/3): 207-213.
Xue Fuliang,Liu Lifang. Fine-Grained Sentiment Analysis with CRF and ATAE-LSTM. Data Analysis and Knowledge Discovery, 2020, 4(2/3): 207-213.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2019.0678      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2020/V4/I2/3/207
Fig.1  研究框架
Fig.2  ATAE-LSTM结构
Fig.3  Skip-gram模型
评论 Pos Tag 评论 Pos Tag
运行/ v B 也/ d O
速度/ n I 很/ d O
快/ a O 耐用/ a O
,/ x O x O
电池/ n B
Table 1  属性词标记示例
Fig.4  不同聚类数目K下的欧氏距离变化趋势
Fig.5  属性词聚类结果
实验 P R F1
基于CRF抽取属性词
基于关联规则抽取属性词
0.84
0.48
0.70
0.14
0.76
0.21
基于ATAE-LSTM属性情感分析
基于LSTM属性情感分析
0.78
0.71
0.81
0.79
0.78
0.73
Table 2  实验结果
属性面 属性词 正面情感 中性情感 负面情感
设计 设计 75% 0 25%
外形与功能 信号 4% 96% 0
相机 75% 0 25%
外形 89% 0 11%
摄像头 9% 0 91%
速度 充电速度 100% 0 0
系统速度 100% 0 0
Table 3  部分属性面的情感指标
[1] Cheng Z, Ding Y, He X , et al. A^ 3NCF: An Adaptive Aspect Attention Model for Rating Prediction [C]// Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018: 3748-3754.
[2] Wang N, Wang H, Jia Y , et al. Explainable Recommendation via Multi-Task Learning in Opinionated Text Data [C]// Proceedings of the 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM, 2018: 165-174.
[3] Hu M, Liu B . Mining and Summarizing Customer Reviews [C]// Proceedings of the 10th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2004: 168-177.
[4] Bafna K, Toshniwal D . Feature Based Summarization of Customers’ Reviews of Online Products[J]. Procedia Computer Science, 2013,22:142-151.
[5] Chen Z, Liu B . Mining Topics in Documents: Standing on the Shoulders of Big Data [C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2014: 1116-1125.
[6] Hu Y, Boyd-Graber J, Satinoff B , et al. Interactive Topic Modeling[J]. Machine Learning, 2014,95(3):423-469.
[7] Lafierty J D, McCallum A, Pereira F C N . Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data [C]// Proceedings of the 18th International Conference on Machine Learning. Burlington, Massachusetts, USA: Morgan Kaufmann Publishers, 2001: 282-289.
[8] Huang S, Liu X, Peng X , et al. Fine-grained Product Features Extraction and Categorization in Reviews Opinion Mining [C]// Proceedings of the 12th International Conference on Data Mining Workshops. IEEE, 2012: 680-686.
[9] 郑丽娟, 王洪伟 . 基于情感本体的在线评论情感极性及强度分析:以手机为例[J]. 管理工程学报, 2017,31(2):47-54.
[9] ( Zheng Lijuan, Wang Hongwei . Sentimental Polarity and Strength of Online Cellphone Reviews Based on Sentiment Ontology[J]. Journal of Industrial Engineering and Engineering Management, 2017,31(2):47-54.)
[10] Manek A S, Shenoy P D, Mohan M C , et al. Aspect Term Extraction for Sentiment Analysis in Large Movie Reviews Using Gini Index Feature Selection Method and SVM Classifier[J]. World Wide Web-Internet & Web Information Systems, 2017,20(2):135-154.
[11] Akhtar M S, Gupta D, Ekbal A , et al. Feature Selection and Ensemble Construction: A Two-Step Method for Aspect Based Sentiment Analysis[J]. Knowledge-Based Systems, 2017,125:116-135.
[12] 李阳辉, 谢明, 易阳 . 基于深度学习的社交网络平台细粒度情感分析[J]. 计算机应用研究, 2017,34(3):743-747.
[12] ( Li Yanghui, Xie Ming, Yi Yang . Fine-grained Sentiment Analysis for Social Network Platform Based on Deep-learning Model[J]. Application Research of Computers, 2017,34(3):743-747.)
[13] Wu H, Gu Y, Sun S , et al. Aspect-based Opinion Summarization with Convolutional Neural Networks [C]// Proceedings of the 2016 International Joint Conference on Neural Networks (IJCNN). IEEE, 2016: 3157-3163.
[14] Xu L, Lin J, Wang L , et al. Deep Convolutional Neural Network Based Approach for Aspect-Based Sentiment Analysis[J]. Advanced Science and Technology Letters, 2017,143:199-204.
[15] Toh Z, Su J . NLANGP at SemEval-2016 Task 5: Improving Aspect Based Sentiment Analysis Using Neural Network Features [C]// Proceedings of the 10th International Workshop on Semantic Evaluation. 2016: 282-288.
[16] Peng H, Ma Y, Li Y , et al. Learning Multi-Grained Aspect Target Sequence for Chinese Sentiment Analysis[J]. Knowledge-Based Systems, 2018,148:167-176.
[17] Rush A M, Chopra S, Weston J . A Neural Attention Model for Abstractive Sentence Summarization [C]// Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 379-389.
[18] Hermann K M, Kocisky T, Grefenstette E , et al. Teaching Machines to Read and Comprehend [C]// Proceedings of the 28th International Conference on Neural Information Processing Systems. 2015: 1693-1701.
[19] Wang Y, Huang M, Zhao L , et al. Attention-Based LSTM for Aspect-Level Sentiment Classification [C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. 2016: 606-615.
[20] 彭敏, 席俊杰, 代心媛 , 等. 基于情感分析和LDA主题模型的协同过滤推荐算法[J]. 中文信息学报, 2017,31(2):194-203.
[20] ( Peng Min, Xi Junjie, Dai Xinyuan , et al. Collaborative Filtering Recommendation Based on Sentiment Analysis and LDA Topic Model[J]. Journal of Chinese Information Processing, 2017,31(2):194-203.)
[21] 李良强, 袁华, 叶开 , 等. 基于在线评论词向量表征的产品属性提取[J]. 系统工程学报, 2018,33(5):687-697.
[21] ( Li Liangqiang, Yuan Hua, Ye Kai , et al. Extraction Product Features from Online Reviews Based on Word-Vector-Representation[J]. Journal of Systems Engineering, 2018,33(5):687-697.)
[22] 王荣洋, 鞠久朋, 李寿山 , 等. 基于CRFs的评价对象抽取特征研究[J]. 中文信息学报, 2012,26(2):56-61.
[22] ( Wang Rongyang, Ju Jiupeng, Li Shoushan , et al. Feature Engineering for CRFs Based Opinion Target Extraction[J]. Journal of Chinese Information Processing, 2012,26(2):56-61.)
[23] Mikolov T, Sutskever I, Chen K , et al. Distributed Representations of Words and Phrases and Their Compositionality [C]// Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013: 3111-3119.
[1] 范涛,王昊,吴鹏. 基于图卷积神经网络和依存句法分析的网民负面情感分析研究*[J]. 数据分析与知识发现, 2021, 5(9): 97-106.
[2] 王昊, 林克柔, 孟镇, 李心蕾. 文本表示及其特征生成对法律判决书中多类型实体识别的影响分析[J]. 数据分析与知识发现, 2021, 5(7): 10-25.
[3] 喻雪寒, 何琳, 徐健. 基于RoBERTa-CRF的古文历史事件抽取方法研究*[J]. 数据分析与知识发现, 2021, 5(7): 26-35.
[4] 杨晗迅, 周德群, 马静, 罗永聪. 基于不确定性损失函数和任务层级注意力机制的多任务谣言检测研究*[J]. 数据分析与知识发现, 2021, 5(7): 101-110.
[5] 谢豪,毛进,李纲. 基于多层语义融合的图文信息情感分类研究*[J]. 数据分析与知识发现, 2021, 5(6): 103-114.
[6] 钟佳娃,刘巍,王思丽,杨恒. 文本情感分析方法及应用综述*[J]. 数据分析与知识发现, 2021, 5(6): 1-13.
[7] 尹鹏博,潘伟民,张海军,陈德刚. 基于BERT-BiGA模型的标题党新闻识别研究*[J]. 数据分析与知识发现, 2021, 5(6): 126-134.
[8] 余本功,朱晓洁,张子薇. 基于多层次特征提取的胶囊网络文本分类研究*[J]. 数据分析与知识发现, 2021, 5(6): 93-102.
[9] 刘彤,刘琛,倪维健. 多层次数据增强的半监督中文情感分析方法*[J]. 数据分析与知识发现, 2021, 5(5): 51-58.
[10] 韩普,张展鹏,张明淘,顾亮. 基于多特征融合的中文疾病名称归一化研究*[J]. 数据分析与知识发现, 2021, 5(5): 83-94.
[11] 段建勇,魏晓鹏,王昊. 基于多角度共同匹配的多项选择机器阅读理解模型 *[J]. 数据分析与知识发现, 2021, 5(4): 134-141.
[12] 王雨竹,谢珺,陈波,续欣莹. 基于跨模态上下文感知注意力的多模态情感分析 *[J]. 数据分析与知识发现, 2021, 5(4): 49-59.
[13] 胡昊天,吉晋锋,王东波,邓三鸿. 基于深度学习的食品安全事件实体一体化呈现平台构建*[J]. 数据分析与知识发现, 2021, 5(3): 12-24.
[14] 成彬,施水才,都云程,肖诗斌. 基于融合词性的BiLSTM-CRF的期刊关键词抽取方法[J]. 数据分析与知识发现, 2021, 5(3): 101-108.
[15] 常城扬,王晓东,张胜磊. 基于深度学习方法对特定群体推特的动态政治情感极性分析*[J]. 数据分析与知识发现, 2021, 5(3): 121-131.
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