计算机与数字工程2018，Vol.46Issue(5)：921-927,7.DOI:10.3969/j.issn.1672-9722.2018.05.015
基于深度学习的商品评价情感分析与研究
Commodity Evaluation Analysis and Research Based on Deep Learning
摘要
Abstract
This paper proposes an improved deep learning model for commodity evaluation sentiment analysis.Firstly,this pa-per uses stop words and tokenizer to pretreatment the data,then Skip-gram model is used to generate word vectors.Secondly,an au-togenerated sentiment lexicon is used to quantify the sentiment polarity of words in commodity reviews and integrate this information into the model input matrix.Lastly,this paper counts the differences between the network input through the distribution rules of de-signed and chose RNN or CNN for feature extraction. Above all is the Shunt-C&RNN commodity reviews sentiment classification model(improved deep learning approach).Compared with the traditional machine learning SVM and the single deep learning meth-od the proposed method has improved the precision by 6.6% and 1.5% respectively.关键词
深度学习/自然语言处理/词向量/卷积神经网络/循环神经网络/分流器/情感Key words
deep learning/natural language processing/word embidding/CNN/RNN/shunt/sentiment analysis分类
信息技术与安全科学引用本文复制引用
刘智鹏,何中市,何伟东,张航..基于深度学习的商品评价情感分析与研究[J].计算机与数字工程,2018,46(5):921-927,7.基金项目
国家交通部科技项目(编号:2011318740240) （编号:2011318740240）
重庆市研究生科研创新项目(编号:CYS16031)资助. （编号:CYS16031）
