Bacterial foraging information swarm optimizer for detecting affective and informative content in medical blogs

The web has turned out to be an ever-present source of knowledge as well as information with which individuals can contribute to show their performance. Typically, content on the web may be sorted into two categories: the first being a user’s personal sentiments or opinions which are known as affective content, and the second being factual information regarding events or technology which is understood as informative content. In the current work, an hybrid multi stage optimization named ‘Bacterial Foraging Information Swarm Optimizer’ as a novel algorithm is proposed to classify the affective content and the informative content from the medical weblogs. In order to enhance this algorithm and to evaluate its accuracy, the medical data source such as MAYO clinic data is taken for the consideration of classification of information as well as affective content. The expansion of the web permits consumers to present their views and opinions online by way of blogs, videos or social networking sites that offer data with regard to particular products or services. Applications are numerous in new generation organizations, products for managing reputations, perceptions of online markers or even monitoring of online content. The current work examines this multistage optimization algorithm for selecting the relevant information at first stage which is followed by the optimization in the second stage and finally as post processing task the classification protocols is applied to contrasts their performance. The valuation is carried out by using opinions gathered from reviews from medical blogs.