A Framework for Studying Coordinated Behaviour Applied to the 2019 Philippine Midterm Elections

• Main Author: Yu, William Emmanuel S
• Format: text
• Published: Archīum Ateneo 2021
• Subjects: social media; elections; content networks; coordinated inauthentic behaviour; crowdtangle
• Online Access: https://archium.ateneo.edu/discs-faculty-pubs/207; https://archium.ateneo.edu/cgi/viewcontent.cgi?article=1206&context=discs-faculty-pubs
• Institution: Ateneo De Manila University

This paper covers a hybrid framework to studying coordinated social media behaviour. The study focuses on social media activity during the 2019 Philippine National and Local Elections. With the use of social media information obtained from the CrowdTangle platform, the research is able to extract necessary post detail information that can be used to determine coordinated behaviour. The study tags posts are coordinated if they have shared media content between five (5) or more posts within a one minute period. This should point to a high degree of coordination. The results are then visualized using the Fruchterman-Reingold algorithm using the networkx library to see the various clusters. This gives us a reasonable amount of data to further explore and act upon. This framework was able to extract a number of Facebook accounts that showed a high degree of coordinated behaviour. These accounts refer to media that are no longer available which is not characteristic of reputable content.