Blog Response Volume Prediction using ANFIS and Stochastic Optimization Techniques

Abstract

Due to wide streaming blogs over the social media, blog volume automation has become indispensable for the analysis of blog popularity. As a rule base driven method, Adaptive Neuro Fuzzy Inference System has gained popularity in various prediction tasks for its efficiency and ease of implementation. In this paper, two modified Adaptive Neuro Fuzzy Inference models have been proposed by tuning its premise and consequent parameters with Particle Swarm optimization and Genetic Algorithms. Particle Swarm optimization helps in reducing the training and cross validation error of the predictive model whereas Genetic Algorithm optimize minimum clustering radius which aids in the formation of rule base. With the help of these optimization methods, Adaptive Neuro Fuzzy Inference System obtains optimal premise and consequent parameters which improves its predictive performance. Comparative analysis of proposed method has been performed against Neural Networks, Support Vector Machines and basic Adaptive Neuro Fuzzy Inference System using UCI Blog Feedback dataset. It has been found that both of the proposed variants have outperformed these state-of-art techniques.