摘要
该文主要研究在评论性数据中用户个性及产品信息对数据情感类别的影响。在影响数据情感类型的众多因素中,该文认为评价的主体即用户以及被评价的对象等信息对评论数据的情感至关重要。该文提出一种基于协同过滤Attention机制的情感分析方法(LSTM-CFA),使用协同过滤(CF)算法计算出用户兴趣分布矩阵,再将矩阵利用SVD分解后加入层次LSTM模型,作为模型注意力机制提取文档特征、实现情感分类。实验表明LSTMCFA方法能够高效提取用户个性与产品属性信息,显著提升了情感分类的准确率。
This paper investigates the influence of user's personality and product information on data emotion category in review data.Among the many factors that affect the emotional data type,the subject of the evaluation,that is,the user and the object of the evaluation,are emotionally important to the commentary data.In this paper,an emotional analysis model(LSTM-CFA)based on cooperative filtering attention mechanism is proposed.The user interest distribution matrix is calculated by using the collaborative filtering(CF)algorithm.After the matrix is decomposed with SVD,the matrix is added to the hierarchical LSTM model as an attention mechanism in order to achieve emotion classification.Experiments show that the LSTM-CFA model can extract the information of user's personality and product attribute efficiently,to improve the accuracy of emotion classification.
作者
赵冬梅
李雅
陶建华
顾明亮
ZHAO Dongmei;LI Ya;TAO Jianhua;GU Mingliang(School of Physics Electronic Engineering,Jiangsu Normal University,Xuzhou,Jiangsu 221116,China;National Laboratory of Pattern Recognition,Institute of Automation,Chinese Academy of Sciences,Beijing 100101,China)
出处
《中文信息学报》
CSCD
北大核心
2018年第8期128-134,共7页
Journal of Chinese Information Processing
基金
国家自然科学基金(61425017
61403386
61773379)
"863"高技术研究计划(2015AA016305)
国家社会科学基金(13&ZD189)
关键词
情感分析
协同过滤
LSTM
注意力机制
SVD
sentiment analysis
collaborative filtering
LSTM
attention mechanism
SVD