Photo: Markus Spiske
Project Someone collaborator and former postdoctoral fellow, Maxime Bérubé, recently co-authored a new article titled “Social Media Forensics Applied to Assessment of Post–Critical Incident Social Reaction: The Case of the 2017 Manchester Arena Terrorist Attack”in Forensic Science International Journal.
The paper’s authors explain that forensic science has ongoing issues concerning digital data. They suggest a solution for this problem using machine-learning techniques, particularly natural language processing and Latent Dirichlet Allocation (LDA) topic modeling, to study large-scale text data. For this study, the authors used Twitter messages posted within 24 hours of the 2017 Manchester Arena terrorist attack. The findings indicate that this method improves on existing social media monitoring tools.
To read the publication, please click here.
Français