Detection of Human, Legitimate Bot, and Malicious Bot in Online Social Networks Based on Wavelets

摘要: Social interactions take place in environments that influence people’s behaviours and perceptions. Nowadays, the users of Online Network (OSN) generate a massive amount content based on social interactions. However, OSNs wide popularity ease access created perfect scenario to practice malicious activities, compromising their reliability. To detect automatic information broadcast OSN, we developed wavelet-based model classifies as being human, legitimate robot, or result spectral patterns obtained from users’ textual content. We create feature vector Discrete Wavelet Transform along with weighting scheme called Lexicon-based Coefficient Attenuation. In particular, induce classification using Random Forest algorithm over two real Twitter datasets. The corresponding results show achieved an average accuracy 94.47% considering different scenarios: single theme miscellaneous one.