“…Previous research in the field of cyberbullying detection has been driven by two paradigms which focus on two different types of analysis: network analysis and content analysis, although many studies combine both types of analyses. The social network analysis paradigm focuses on modelling interactions among users of a social network (Li & Tagami, 2014;Honjo et al, 2011;Hosseinmardi et al, 2014), based in particular on the usage statistics of digital media, such as sender and receiver IDs, account IDs, users' names, content, time and location of communication. Content analysis focuses on detecting cyberbullying instances based on text analytics and the use of Natural Language Processing (NLP) techniques, and, from this perspective, the task of cyberbullying detection was previously approached as a classification task (Yin et al, 2009) that involves data acquisition and pre-processing, feature extraction and classification.…”