Analysing the Existence of Organisation Specific Languages on Twitter: The Dataset

Résumé

The presence of organisations in Online Social Networks (OSNs) has motivated malicioususers to look for attack vectors, which are then used to increase the possibility of carrying out successfulattacks and obtaining either private information or access to the organisation. This article hypothesisedthat organisations have specific languages that their members use in OSNs, which malicious users couldpotentially use to carry out an impersonation attack. To prove these specific languages, we propose twotasks: classifying tweets in isolation by their author’s organisation and classifying users’ entire timelines byorganisation. To accomplish both tasks, we generate this dataset of over 15 million tweets from more than 5000 members of five different organisations.