UKRI Safe and Trusted AI PhD student, Anna Gausen (2020 cohort), has had her paper, ‘Using Agent-Based Modelling to Evaluate the Impact of Algorithmic Curation on Social Media’, published in the Association for Computing Machinery’s (ACM) Journal of Data and Information Quality.
The paper explores how the objectives of recommendation systems on social media effect online polarisation and the spread of misinformation.
Social media networks have drastically changed how people communicate and seek information. Due to the scale of information on these platforms, newsfeed curation algorithms have been developed to sort through this information and curate what users see. However, these algorithms are opaque and it is difficult to understand their impact on human communication flows. Some papers have criticised newsfeed curation algorithms that, while promoting user engagement, heighten online polarisation, misinformation, and the formation of echo chambers.
As Anna explains, “My paper shows that agent-based modelling offers the opportunity to simulate the complex interactions between these algorithms, what users see, and the propagation of information on social media. This provides useful insights into the impact of curation algorithms on how information propagates and on content diversity on social media”.
Anna and her co-authors work demonstrates that algorithms used by social media platforms which increase user engagement and activity can lead to echo chamber formation and polarisation. They argue that social media platforms need to consider the impact on content quality and diversity when designing algorithms and their research provides insights into how these algorithms could be improved.
Anna is proud of this accomplishment and said, “Getting this work published in an ACM journal is a huge validation of my avenue of research and has motivated me to keep going!”
The paper is co-authored with Wayne Luk and Ce Guo.