基于文本情感和异质网络分析的社会化推荐研究

项目名称： 基于文本情感和异质网络分析的社会化推荐研究

项目编号： No.71471054

项目类型： 面上项目

立项/批准年度： 2015

项目学科： 管理科学

项目作者： 王刚

作者单位： 合肥工业大学

项目金额： 61万元

中文摘要： 面向社交媒体的社会化推荐中除了会碰到传统推荐系统的冷启动、数据稀疏、可解释性差等问题外，在社交媒体环境下，社会化推荐中还存在大量新的数据源和数据类型，从而需要新的数据处理方法，并且社交媒体中也存在着大量新的推荐问题，现有推荐方法已不能很好的解决这些问题。为此，本项目通过引入文本情感和异质网络分析技术来解决目前社会化推荐中碰到的突出问题，首先从分析社交媒体环境下的社会化推荐问题特征及影响入手，然后针对社会化推荐中存在的大量非结构的文本数据以及关系网络数据，分别研究面向社会化推荐的文本情感分析问题，以及面向社会化推荐的异质网络分析问题，接着以此为基础构建面向个体和面向群体的社会化推荐方法，最后以科研社区为例进行案例研究。通过本项目的研究，为解决社交媒体中的信息过载问题提供新的方式和途径，丰富和完善社会化推荐的理论研究体系，推动社会化推荐的理论研究和实践应用的发展，具有重要的理论意义和实践价值。

中文关键词： 社会化推荐；文本情感分析；异质网络分析；社交媒体；信息过载

英文摘要： Social recommendation in the social media meets with the problems of traditional recommendation systems, such as cold start, data sparsity, and bad explanation. At the same time, there are many new data sources and data types in social recommendation, which need new data processing methods. Meanwhile, there are many new recommendation problems in social recommendation. Accordingly, existing recommendation methods cannot solve these problems successfully. In this project, text sentiment analysis and heterogeneous network analysis are introduced to solve these prominent problems. Firstly, the characteristics and influences of social recommendation in social media are analyzed. Then, based on these analyses, text sentiment analysis technology and heterogeneous network analysis technology in social recommendation are studied for the processing of unstructured text data and relation network data. Subsequently, social recommendation methods for individual and group are proposed based on the text sentiment analysis and heterogeneous network analysis. Finally, a science and research community is selected as the case study for this project. Through the research of this project, the new ways and means can be proposed for solving the information overload problem in the social media, which can enrich and improve the theoretical research system of social recommendation. It also has important theoretical and practical value for the promoting the development of theoretical research and practical applications in the social recommendation.

英文关键词： Social Recommendation;Text Sentiment Analysis;Heterogeneous Network Analysis;Social Media;Information Overload