Trick and Please. A Mixed-Method Study On User Assumptions About the TikTok Algorithm

Abstract

The short-form video sharing app TikTok is characterized by contentbased interactions that largely depend on individually customized video feeds curated by the app's recommendation algorithm. Algorithms are generally invisible mechanisms within socio-technical systems that can influence how we perceive online and offline reality, and how we interact with each other. Based on experiences from consuming and creating videos, users develop assumptions about how the TikTok algorithm might work, and about how to trick and please the algorithm to make their videos trend so it pushes them to other users' 'for you' pages. We conducted 28 qualitative interviews with TikTok users and identified three main criteria they assume influence the platform's algorithm: video engagement, posting time, and adding and piling up hashtags. We then collected 300,617 videos from the TikTok trending section and performed a series of data exploration and analysis to test these user assumption by determining criteria for trending videos. Our data analysis confirms that higher video engagement through comments, likes, and shares leads to a higher chance of the algorithm pushing a video to the trending section. We also find that posting videos at certain times increases the chances of it trending and reaching higher popularity. In contrast, the highly common assumption that using trending hashtags, algorithm related hashtags (e.g. #fyp, #foryou), and piling up trending hashtags would significantly push videos to the trending section was found not applicable. Our results contribute to existing research on user understanding of social media algorithms using TikTok as an example for a short-video app that is explicitly built around algorithmic content recommendation. Our results provide a broader perspective on user beliefs and behavior in the context of socio-technical systems and social media content creation and consumption.

TikTok’s Spiral of Antisemitism

“…Scholarship on TikTok is still in its early days; however, most research focuses on the role of TikTok's algorithm. Research by Klug et al (2021) found that TikTok users are highly aware of TikTok's algorithm and have developed assumptions about how the algorithm works to make their videos trend. A study by Omar and Dequan (2020) found that self-expression explains active involvement on TikTok with users wanting to express themselves and interact with others.…”

Extracting time patterns from the lifespans of TikTok challenges to characterize non-dangerous and dangerous ones

“…This content-based component of the algorithm is complemented by a second collaborative filtering one. The authors of Klug et al (2021) investigate the principles behind this recommendation algorithm and find some expedients to trick and make it suggest certain trends to other users. They found that some of the aspects taken into consideration by the TikTok's recommendation algorithm are hashtags, time of posting and user engagement.…”

What Do We Know about Algorithmic Literacy? The Status Quo and a Research Agenda for a Growing Field

“…Research in this space began by investigating algorithmic experiences through qualitative methods such as in-depth interviews. Particularly in uncovering folk theories, qualitative studies about Facebook (Bucher, 2017), Google News (Powers, 2017), YouTube (Alvarado et al, 2020), Spotify (Siles et al, 2020), and TikTok (Klug et al, 2021) asked users to share their experiences with these platforms. These methods allow participants to express a wide range of emotions about and expectations of with algorithms in their own use, which can also vary widely by platform.…”

“…Recommender system beliefs recognize the role of an algorithm that recommends videos based on who and what content is similar to what the user likes, while company policy beliefs acknowledges paid recommendations and third-party content. On TikTok, users focus on how content could make it to other users' video feeds, and assumed it was a combination of video engagement, posting time, and using the right hashtags (Klug et al, 2021).…”