Bubbles bursting: Investigating and measuring the personalisation of social media searches

Abstract

Social media platforms implement personalisation algorithms to provide users with a tailored selection of posts under the assumption of a better experience. However, prior studies examining social media timelines revealed that, due to personalisation algorithms, social media users are more likely to encounter attitude-consistent content that reinforces their existing beliefs than information that contradicts them, creating filter bubbles and ultimately hampering their ability to make good decisions. To burst the bubbles, this paper proposes a framework for investigating and measuring the factors that affect personalisation in social media search mechanisms by controlling external noises that can mask the results and be misinterpreted as personalisation. Upon conducting a comprehensive set of experiments with Twitter as our study social media platform, we observed that users’ followees, cookies, and carry-over effect play a role in shaping personalised search results. While the extent of their influence is relatively limited, they can still lead to the introduction of biases, consequently affecting users’ opinions and judgements. In addition, the experiments also shed light on the fact that searches on polarised issues can lead to unwarranted one-sided inclinations in the results. Lastly, we argue in favour of alleviating the multifaceted societal and ethical consequences of algorithmic personalisation through encouraging users to develop healthy social media use habits and by urging social media platforms as well as policymakers to actively work towards fostering a more diverse and reliable online information ecosystem.