LSTM Based on the Classification of Emotion about User Evaluation on Shopping Site - 副本.docxVIP

下载本文档

16
0
约1.52万字
约 4页
2017-07-17 发布于河北
举报
版权申诉

LSTM Based on the Classification of Emotion about User Evaluation on Shopping Site - 副本.docx

1、本文档共4页，可阅读全部内容。
2、原创力文档（book118）网站文档一经付费（服务费），不意味着购买了该文档的版权，仅供个人/单位学习、研究之用，不得用于商业用途，未经授权，严禁复制、发行、汇编、翻译或者网络传播等，侵权必究。
3、本站所有内容均由合作方或网友上传，本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺！文档内容仅供研究参考，付费前请自行鉴别。如您付费，意味着您自己接受本站规则且自行承担风险，本站不退款、不进行额外附加服务；查看《如何避免下载的几个坑》。如果您已付费下载过本站文档，您可以点击这里二次下载。
4、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等，请点击“版权申诉”（推荐），也可以打举报电话：400-050-0827(电话支持时间：9:00-18:30)。
5、该文档为VIP文档，如果想要下载，成为VIP会员后，下载免费。
6、成为VIP后，下载本文档将扣除1次下载权益。下载后，不支持退款、换文档。如有疑问请联系我们。
7、成为VIP后，您将拥有八大权益，权益包括：VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
8、VIP文档为合作方或网友上传，每下载1次，网站将根据用户上传文档的质量评分、类型等，对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档

LSTM Based on the Classification of Emotion about User Evaluation on Shopping Site - 副本

LSTM Based on the Classification of Emotion about User Evaluation on Shopping Site Xiao Rong, Cui Xiaohui, Zhou peipei, Ge Wanfeng, Shu Bowei Abstract—With the development of e-commerce and logistics, more and more people begin to turn to online shopping and consumption. User evaluation for the goods is important for sellers in the sales planning and positioning, because it has a guiding function in next step. At the same time, the operator can also grasp the customer demand and improve the user experience of buying better based on this data. However, the user evaluation of shopping websites always has huge amounts of data. What’s more, a series of reviews about emotional bias judging by manual work is a waste of manpower and material resources. Aiming at this problem, this paper puts forward a model based on LSTM and word vectors [1]. This scheme adopts the method that converts a statement term vectors, using the LSTM neural network model and the KERAS deep learning under the framework of the model for supervised learning and training user reviews to assess quality. Compared with the traditional neural network model of RNN neural network model, LSTM can be a very good solution because of the long distance learning of the neural nodes to forward neural nodes of declining awareness, thus LSTM neural network model can be better to finish the task of user sentiment analysis. Keywords: Emotional Classification Neural Network LSTM 1 Introduction In the age of the Internet, the online shopping platform sells millions of products every day. Users can also evaluate the goods through the online comments channel after the purchase of goods. The evaluation often contains a huge business information, which is useful for vendors. It is also helpful for investors to know the potential market of e-commerce sites and brand value, and also provide the reference basis for other customers and help them to find the ideal shopping website fast, so emotional classification carrie