User profiling for big social media data using standing ovation model

Online Social Networks (OSNs) have recently been the subject of numerous studies that have attempted to develop effective methods for classifying and analyzing big content. Some of the key contributions of these studies to current scientific understanding include the identification of underlying topics within content (posts and messages), determination of each user's influence and contributions, c) measurement of content quality, and extraction and analysis of users' motives and preferences. We aimed to develop an integrative solution entailing a combination of these methodological advances within a single framework that could facilitate attribution and differentiate OSN members. Specifically, we examined peer effects within Twitter and assessed the propensity of members to alter their views on commonly discussed matters based on their exposure to alternative views expressed by respected and influential members. We availed of abundant available resources and tracked historical interactions of selected users to create a workable model that captured differences in opinions. The resulting solution enables peer influence within the online environment to be quantified and the level of investment of identified social media users in particular topics to be assessed.