Abstract
User beliefs about algorithmic systems are constantly co-produced through user interaction and the complex socio-technical systems that generate recommendations. Identifying these beliefs is crucial because they influence how users interact with recommendation algorithms. With no prior work on user beliefs of algorithmic video recommendations, practitioners lack relevant knowledge to improve the user experience of such systems. To address this problem, we conducted semi-structured interviews with middle-aged YouTube video consumers to analyze their user beliefs about the video recommendation system. Our analysis revealed different factors that users believe influence their recommendations. Based on these factors, we identified four groups of user beliefs: Previous Actions, Social Media, Recommender System, and Company Policy. Additionally, we propose a framework to distinguish the four main actors that users believe influence their video recommendations: the current user, other users, the algorithm, and the organization. This framework provides a new lens to explore design suggestions based on the agency of these four actors. It also exposes a novel aspect previously unexplored: the effect of corporate decisions on the interaction with algorithmic recommendations. While we found that users are aware of the existence of the recommendation system on YouTube, we show that their understanding of this system is limited.
Highlights
Recommender systems help users navigate immense number of movies, songs, news articles, friends, restaurants, and others
In line with the research gaps, we focused on users with three main characteristics: 1) users who only consume videos, 2) middle-aged users who did not grow up with social media and algorithmic recommendations, and 3) users with high education levels but with no formal training in computer science or related disciplines
We investigated video consumer’s beliefs about algorithmic recommendations on YouTube, the most widely used video recommendation system in the world at the time of the investigation
Summary
Recommender systems help users navigate immense number of movies, songs, news articles, friends, restaurants, and others. Since user beliefs about algorithmic systems are constantly co-produced and formed during usage, academics need to study them in a specific context with real users. We describe the relevance of studying recommendation systems because of their social implications and consequences towards their users. We highlight previous work on how users perceive and experience these systems and related design proposals. We explore previous investigations of algorithmic beliefs and related research. We use the term recommendation system (RS) to refer to systems based on machine learning, collaborative filtering, or other user-content based recommendation strategies. Since we center our investigation on users and their understanding and experiences about these recommendations systems, we highlight specific technical implementation details only when they relate to this topic. The participants in our investigation did not differentiate between concepts like collaborative filtering, machine learning or neural networks, neither explicitly nor implicitly
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the ACM on Human-Computer Interaction
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
