Wang Mengmeng, Zuo Wanli, Wang Ying
College of Computer Science and Technology, Jilin University, Changchun 130012, China ; Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Ministry of Education, Changchun 130012, China.
College of Computer Science and Technology, Jilin University, Changchun 130012, China ; Key Laboratory of Symbolic Computation and Knowledge Engineering, Jilin University, Ministry of Education, Changchun 130012, China ; College of Mathematics, Jilin University, Changchun 130012, China.
Comput Intell Neurosci. 2015;2015:510281. doi: 10.1155/2015/510281. Epub 2015 Aug 31.
Today microblogging has increasingly become a means of information diffusion via user's retweeting behavior. Since retweeting content, as context information of microblogging, is an understanding of microblogging, hence, user's retweeting sentiment tendency analysis has gradually become a hot research topic. Targeted at online microblogging, a dynamic social network, we investigate how to exploit dynamic retweeting sentiment features in retweeting sentiment tendency analysis. On the basis of time series of user's network structure information and published text information, we first model dynamic retweeting sentiment features. Then we build Naïve Bayes models from profile-, relationship-, and emotion-based dimensions, respectively. Finally, we build a multilayer Naïve Bayes model based on multidimensional Naïve Bayes models to analyze user's retweeting sentiment tendency towards a microblog. Experiments on real-world dataset demonstrate the effectiveness of the proposed framework. Further experiments are conducted to understand the importance of dynamic retweeting sentiment features and temporal information in retweeting sentiment tendency analysis. What is more, we provide a new train of thought for retweeting sentiment tendency analysis in dynamic social networks.
如今，微博已日益成为一种通过用户转发行为进行信息传播的手段。由于转发内容作为微博的上下文信息，是对微博的一种理解，因此，用户转发情感倾向分析逐渐成为一个热门研究课题。针对在线微博这个动态社交网络，我们研究如何在转发情感倾向分析中利用动态转发情感特征。基于用户网络结构信息和发布的文本信息的时间序列，我们首先对动态转发情感特征进行建模。然后，我们分别从基于个人资料、关系和情感的维度构建朴素贝叶斯模型。最后，我们基于多维朴素贝叶斯模型构建一个多层朴素贝叶斯模型，以分析用户对一条微博的转发情感倾向。在真实世界数据集上进行的实验证明了所提出框架的有效性。我们还进行了进一步的实验，以了解动态转发情感特征和时间信息在转发情感倾向分析中的重要性。此外，我们为动态社交网络中的转发情感倾向分析提供了一种新的思路。
