Entity

Time filter

Source Type


Cao J.,CAS Institute of Computing Technology | Zhang Y.,CAS Institute of Computing Technology | Ji R.,Xiamen University | Xie F.,Communication and Technical Bureau | Su Y.,Communication and Technical Bureau
Neurocomputing | Year: 2016

The prevailing of Web 2.0 techniques has led to the boom of web video content as well as its social network. To overcome the information overload problem, effective web video topic discovery and structuring techniques are highly demanded. To this end, existing works go to two respective directions: video topic discovery based on content or community detection in social network, with limited interplay between topics and network structures. In this paper, we construct the video social network based on web user interactions over videos. By comparing the topics and communities discovered on this network, we unveil the loose correspondence relationship between content and social network, and correspondingly propose a novel community-driven web video topic discovery model, which regularizes the topic model in relaxed community-level. Quantitatively analysis on real-world YouTube data shows that our model has achieved a significant improvement over the purely content-based or network-based baselines. Meanwhile, we propose a community-based topic structuralization framework, which decomposes a topic in social network space, and tracks the spreading trajectory of this topic among different communities on the time line. This structuralization can help users to catch the important facets of topics, such as "Who is interested with this topic" and "How does it propagate among the communities", which provide valuable insights in related applications such as web monitoring and market development. © 2015. Source


Yu H.,Beijing University of Posts and Telecommunications | Wu G.,Beijing University of Posts and Telecommunications | Su Y.,Communication and Technical Bureau | Li J.,Beijing University of Posts and Telecommunications | And 2 more authors.
2015 12th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2015 | Year: 2015

In recent years, news sentiment analysis is a hotspot in the field of natural language processing, and it is also a challenging problem. Methods based on semantic direction almost only consider polarity of emotion words of every sentence in news. We present an improved news sentiment analysis method. It divides news sentiment analysis into title sentiment analysis and text sentiment analysis. For the title, we use our rule set to process. For the text, we use an algorithm of subjective sentences recognition and an algorithm of subject word recognition to analyze the sentiment of Chinese news. We call the proposed method is Improved Sentiment Analysis (ISA). Experimental data shows that the proposed method improves the accuracy of news sentiment analysis. © 2015 IEEE. Source

Discover hidden collaborations