Search

Twitter's popularity has exploded in the previous few years, making it one of the most widely used social media sites. As a result of this development, the strategies described in this study are now more beneficial. Additionally, there has been an increase in the number of people who express their views in demeaning ways to others. As a result, hate speech has piqued interest in the subject of sentiment analysis, which has developed various algorithms for detecting emotions in social networks using intuitive means. This paper proposes the deep learning model to classify the sentiments in two separate analyses. In the first analysis, the tweets are classified based on the hate speech against the migrants and the women. In the second analysis, the detection is performed using a deep learning model to organise whether the hate speech is performed by a single or a group of users. During the text analysis, word embedding is implemented using the combination of deep learning models such as BiLSTM, CNN, and MLP. These models are integrated with word embedding methods such as inverse glove (global vector), document frequency (TF-IDF), and transformer-based embedding., Competing Interests: The authors declare no conflicts of interest., (Copyright © 2022 Asif Hasan et al.)

The role of social media, particularly Twitter, in ensuring the large-scale propagation of information cannot be overemphasised. This study introduces the recipient network's reciprocity toward a particular topic as a novel factor that contributes toward a central node's information propagation potential, in addition to other widely studied factors. It first employs multiple regression analysis to present a model that reveals the prominent roles played by both content popularity, focal ratio, engagement efforts of users, and the recipient network's reciprocity toward a topic, in determining his or her propagation potential. Further, it investigates the impact of the interaction terms of each of these propagation dimensions and the network's reciprocity toward the topic on a user's propagation potential. The results show that the network's reciprocity toward the topic (i.e. 'blockchain' in this study) is important for modelling the diffusion process accurately. Second, applying a multi-methods approach, this study also incorporates fuzzy set qualitative comparative analysis (fsQCA). It reveals four alternative combinations of explanatory variables (propagation dimensions) that are sufficient for achieving the expected outcome (propagation potential of the user/central node). The study found fsQCA results complementing the results of the regression model. [ABSTRACT FROM AUTHOR]