From Online Behaviours to Images: A Novel Approach to Social Bot Detection

Online Social Networks have revolutionized how we consume and share information, but they also led to a proliferation of content not always reliable accurate. One particular type social accounts is known promote unreputable content, hyperpartisan, propagandistic information. They are automated accounts, commonly called bots. Focusing on Twitter propose novel approach bot detection: first new algorithm that transforms the sequence actions an account performs into image; then, leverage strength Convolutional Neural proceed with image classification. We compare our performances state-of-the-art results for detection genuine accounts/bot datasets well in literature. The confirm effectiveness proposal, because capability par state art, if better some cases.