Deep Learning Model Based on Particle Swam Optimization for Buzzer Detection

Along with the development of the internet, the presence of buzzers is increasingly widespread on social platforms, especially on Twitter. Buzzers have played an important role in influencing and spreading misinformation, manipulating public opinion, and harassing and intimidating online social media users. Therefore, an effective detection algorithm is needed to detect buzzer accounts that endanger social networks because they affect neutrality. In this research, we propose a Deep Neural Network model to detect buzzer accounts on Twitter. We conducted experiments on 1000 datasets using PSO-based Deep Neural Network models and Ada Boost-based Deep Neural Networks to obtain the best model in detecting buzzer accounts. The results show that the performance of the PSO-based Deep Neural Network is the best with 98.90% accuracy compared to Ada Boost-based Deep Neural Network 95.30% or without feature weight and boosting algorithms with 46.60% accuracy. This clearly shows the superiority of our proposed method. These results are expected to help maintain neutral information on social media and minimize noise in the data that will be used for sentiment analysis research.