Web-based social networks have been growing extremely fast in recent years. It has become one of the most important issues of web-based technologies. Meanwhile, data mining and processing techniques have been applied extensively to various research domains including web technology and social networks.
  Intelligent Data Processing has attracted much attention from various research communities. Researchers in related fields are facing the challenges of data explosion, which demands enormous manpower for data processing. Artificial intelligence and intelligent systems offer efficient mechanisms that can significantly reduce the costs of processing large volume data and improve data processing quality. Practical applications have been developed in different areas including health informatics, financial data analysis, geographic systems, automated manufacturing processes, etc.
  This special issue aims to gather experts and scholars from related fields to present and share their recent research on social networks, data processing and the integration of these two areas. This special issue contains extended versions of the accepted papers from the 14th International Symposium on Knowledge and Systems Sciences, hosted by NIT, Zhejiang University. 10 papers have been invited to the special issue selected from over 44 conference submissions. 4 papers have been accepted after two rounds of review. We are pleased to serve as guest editors for this special issue to bring together researchers, practitioners and users interested in the full spectrum of online social network data processing. This issue reflects the breadth of enterprise services computing topics. There are four papers, each of which is concerned with a specific aspect of the topic and summarised as follows.
  Referring to the first paper “A Novel Approach for Customer Segmentation Based on Bi-clustering”, Hu et al present a novel approach to classify customers for an effective Customer Relationship Management. This approach uses the chisquare statistical analysis to select the set of attributes and uses K-means algorithm to quantize the value of each selected attribute. It then classifies the customers into three groups by using DBSCAN algorithm. The efficiency of this approach has been demonstrated on the real data set from an airline company.
  ......

[PDF]