Modeling to find the top bloggers using Sentiment Features

Weblogs are discussion forums empowering individuals to express their views and opinions. Blogosphere is the virtual world of all the blogs covering wide variety of social issues. The bloggers with the abilities to influence and sway other users' opinions are known as the influential bloggers. Identification of the influential bloggers has vast applications in online marketing, advertising and electronic commerce. Several models for identifying the influential bloggers are proposed in the relevant literature. However, the sentiment expressed by a blogger in a blog post is not explored. In this paper, we propose a model based on the integration of activity and recognition modules. The number of blog posts and quantitative analysis of sentiment expressed in blog posts represent a blogger's activity. The recognition represents the influence and reputation of a blogger in a social community. The experiments have been carried out using the social media blog of TechCrunch. The evaluation of the proposed model, MIBSF, using the performance evaluation measures prove that sentiment expressed in a post should be considered as an important factor for identifying influential bloggers. The findings also indicate that MIBSF shows better results to find the influential bloggers as compared to the existing methods.