基于LSTM深度学习模型的中国电信官方微博用户情绪分析  

Sentiment analysis of telecom official micro-blog users based on LSTM deep learning model

作　　者：蔡鑫[1] 娄京生 

机构地区：[1]中国电信股份有限公司上海研究院,上海200122

出　　处：《电信科学》2017年第12期136-141,共6页Telecommunications Science

摘　　要：中国电信官方微博(简称电信官微)作为一种互联网媒体,是中国电信对外发布信息并获取用户反馈的重要渠道。用户对电信官微消息内容的评论,反映了用户对中国电信品牌、产品和服务的不同态度。爬取了电信官微的消息内容和评论数据,对经过清洗的数据采用Word2vec进行文本信息表示,并使用深度学习平台基于LSTM深度神经网络模型进行用户交互文本的正负面情感分类,实现电信官微访问用户情绪分析。As an internet media, China Telecom official micro-blog is an important channel for the company to publish information and get feedback from users. Users＇ comments on telecom official micro-blog messages reflect different at- titudes towards telecom brand, products and services. The message content and comment data of the micro-blog was crawled, and the Word2vec was used to express the text information after data cleaning, and the deep learning platform was chosen to carry out the positive and negative emotional classification of the user interaction text based on the LSTM deep neural network model, and sentiment analysis of telecom official micro-blog users was realized.

关 键 词：深度学习 LSTM 情绪分析 微博 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]