From Online Behaviours to Images: A Novel Approach to Social Bot Detection
This addresses the issue of unreliable content spread by bots on social networks, but it is incremental as it applies an existing method (CNNs) to a new representation of data.
The paper tackles the problem of detecting automated social media accounts (bots) on Twitter by proposing a novel approach that transforms account action sequences into images and uses Convolutional Neural Networks for classification. The results show detection capability on par with or better than state-of-the-art methods in some cases.
Online Social Networks have revolutionized how we consume and share information, but they have also led to a proliferation of content not always reliable and accurate. One particular type of social accounts is known to promote unreputable content, hyperpartisan, and propagandistic information. They are automated accounts, commonly called bots. Focusing on Twitter accounts, we propose a novel approach to bot detection: we first propose a new algorithm that transforms the sequence of actions that an account performs into an image; then, we leverage the strength of Convolutional Neural Networks to proceed with image classification. We compare our performances with state-of-the-art results for bot detection on genuine accounts / bot accounts datasets well known in the literature. The results confirm the effectiveness of the proposal, because the detection capability is on par with the state of the art, if not better in some cases.