Are You Human? Detecting Bots on Twitter Using BERT

Abstract

Dissemination of fake news on Twitter is a rapidly growing problem, mostly due to the increasing number of bots. Hence, automatic bot detection is becoming an important area of research. In this work, we present the BERT-based bot detection model along with exploratory data analysis of tweets written by bots and humans. We statistically prove that including additional features alongside contextualized embeddings boosts model performance. Furthermore, we develop a gender prediction model using derived features and compare the difficulties of the two tasks. Finally, we demonstrate how Logistic Regression outperforms Deep Neural Network on both tasks.