Affiliations: Arizona State University, Tempe, AZ, USA
Correspondence:
[*]
Corresponding author: Yi Chen, Arizona State University, Tempe, AZ, USA. E-mail: [email protected]
Abstract: With the rapid development of web 2.0 technology and e-business, influential bloggers can bring great business values to modern enterprise by increasing market profits and enlarging business impacts. Despite that several systems are available for mining influential bloggers, they are oblivious to domain specific features and potential influence, which are critical for real application requirements. In this paper, we propose an effective model to mine top-k influential bloggers that considers not only post-reply relationships, external links and network proximity, but interest domains, as well as both explicit influence and implicit influence. We develop an influential blogger mining system based on the proposed model, and discuss business applications that can be benefited from these techniques. The experiment results show that our system can effectively mine influential bloggers.
Keywords: Social network, data mining, computational advertising, influence modelling, text mining, link analysis
