Survey on diverse facets and research issues in social media mining

Social media sites are a major source for feedbacks, opinion, decision and other user-generated information on services products and ideas which help to mine human behavioral patterns and maps and measures formal and informal relationships between them. Blogs and social networks sites have recently become a valuable resource for mining sentiments, user opinion in fields as diverse as customer relationship management, targeted marketing, public opinion tracking and text filtering. If the user-generated information is extracted reliably from social media then it provides a positive impact on critical applications related to Health Informatics, including Bioinformatics, Image Informatics, Clinical Informatics, Public Health Informatics, safety, marketing etc. This survey discusses various data mining techniques, research issues, future trends used in mining diverse aspects of the social media over decades going from the historical techniques to the up-to-date techniques with a focus on those which are thought to have the most promise and applicability to future data mining, including a novel technique named multiscale community detection.