FADOHS: Framework for Detection and Integration of Unstructured Data of Hate Speech on Facebook Using Sentiment and Emotion Analysis

Abstract

Media like as social networks play a crucial role in the dissemination of knowledge, ideas, and sway among people. Understanding the properties of social networks, learning how information spreads via the "word-of-mouth" impact of social networks, and learning about the social effects among individuals are the primary areas of study in the extant literature. Persons and communities alike. However, most studies don't account for the presence of destructive influences between people. To combat social ills like excessive drinking, smoking, and gambling, as well as influence-spreading issues like the promotion of new products, we take both positive and negative influences into account and propose a new optimization problem called the Minimum-sized Positive Influential Node Set (MPINS) selection problem to find the smallest group of nodes from which every other node in the network can benefit. Our help here is threefold. In the first place, we show that MPINS is APX-hard when seen as an independent cascade model with both positive and negative impacts. The MPINS selection issue is then addressed by a greedy approximation approach that we provide. Finally, we run extensive simulations and experiments on random graphs and seven different real-world data sets that represent small-, medium-, and large-scale networks to verify the efficacy of the proposed greedy algorithm.