期刊名称：International Journal of Computer Science and Network
印刷版ISSN：2277-5420
出版年度：2017
卷号：6
期号：6
页码：702-707
出版社：IJCSN publisher
摘要：As billions of individuals share data, opinions, images, videos, through social media, enormous data is getting
accumulated attracting researchers towards Social Network Analytics which involves combination of structural and
content analytics to mine patterns/knowledge from social media. This paper provides a comprehensive survey of various
concepts, challenges, techniques, and outcomes of recent research on Social Media Analytics. The major research issues
including partial information, scalability, heterogeneity, structural component and dynamically changing content call for
specifically designed techniques for representation and analysis of social media content. Different types of node centralities to
quantify the impact of an individual in social media are discussed. This paper provides useful insights on different types
of network structures and models for propagation of opinions/influence in different types of networks. It also provides
inputs on latest methods for dynamically changing link prediction and visualization for better understanding. The paper
discusses successful methods for Sentiment Analysis. It also discusses the concept of Socio dimensions to identify the
heterogeneity of connections between nodes of a social network to accurately predict the interests of an individual for targeted
marketing etc. Recent research on dynamic topic detection from tweet stream based on a predefined threshold on Minimum
Bounding Similarity is discussed. Extensive reference material on related concepts and techniques are briefly discussed in this
paper and the citations are helpful for further readings.
