An Empirical Investigation of Personalization Factors on TikTok

TL;DR

This study empirically analyzes how personalization factors like language, location, and user interactions influence TikTok's recommendation algorithm, revealing significant impacts and implications for filter bubbles and content diversity.

Contribution

It introduces a novel sock-puppet audit methodology and provides empirical evidence on the influence of various personalization factors on TikTok's content recommendations.

Findings

Follow-feature has the strongest influence on recommendations

Like-feature significantly affects content personalization

Video watch duration impacts recommended content

Abstract

TikTok currently is the fastest growing social media platform with over 1 billion active monthly users of which the majority is from generation Z. Arguably, its most important success driver is its recommendation system. Despite the importance of TikTok's algorithm to the platform's success and content distribution, little work has been done on the empirical analysis of the algorithm. Our work lays the foundation to fill this research gap. Using a sock-puppet audit methodology with a custom algorithm developed by us, we tested and analysed the effect of the language and location used to access TikTok, follow- and like-feature, as well as how the recommended content changes as a user watches certain posts longer than others. We provide evidence that all the tested factors influence the content recommended to TikTok users. Further, we identified that the follow-feature has the strongest influence, followed by the like-feature and video view rate. We also discuss the implications of our findings in the context of the formation of filter bubbles on TikTok and the proliferation of problematic content.