Music Recommendation Algorithms: Discovering Weekly or Discovering Weakly?

This thesis analyzes and assesses the cultural impact and economic viability that the top music streaming platforms have on the consumption and discovery of music, with a specific focus on recommendation algorithms. Through the support of scholarly and journalistic research as well as my own user experience, I evaluate the known constructs that fuel algorithmic recommendations, but also make educated inferences about the variables concealed from public knowledge. One of the most significant variables delineated throughout this thesis is the power held by human curators and the way they interact with algorithms to frame and legitimize content. Additionally, I execute my own experiment by creating new user profiles on the two streaming platforms popularly used for the purpose of discovery, Spotify and SoundCloud, and record each step of the music discovery process experienced by a new user. After listening to an equal representation of all genre categories within each platform, I then compare the genre, release year, artist status, and content promotion gathered from my listening history to the algorithmically-generated songs listed in my ‘Discover Weekly’ and ‘SoundCloud Weekly’ personalized playlists. The results from this experiment demonstrate that the recommendation algorithms that power these discovery playlists intrinsically facilitate the perpetuation of a stardriven, “winner-take-all” marketplace, where new, popular, trendy, music is favored, despite how diverse of a selection the music being listened to is.The content of this thesis is significant to understanding the culture of music streaming and is also contributory to the field of media communication. Unlike any other scholarly research, the “walk-through” experiment uniquely tracks a new user experience through the cognizant application of user actions and directly assesses the factors that challenge successful music recommendation. This method of research specifically highlights the influence that music streaming platforms have not only as tastemakers, but more importantly, as gatekeepers of cultural information, shaping the perceived value and relevance of artists and genres through recommendation. This thesis underlines the challenges faced by recommendation systems in providing the novel, yet relevant recommendations necessary to satisfy the needs of users, while also providing wide-ranging, yet representative recommendations to stimulate diversity and creativity within society.These challenges include the subjective organization of songs and genres within a platform’s interface, the misrepresentation of songs and artists within genre-based playlists, the use of user actions (skips, likes, dislikes, passive listening, drifting, etc.) as an assertion of one’s likes and dislikes, as well as the manipulation of hit-producing market trends. This thesis delves deeply into each challenge and the ways they affect the inaccuracy, subjectivity, and homogeneity currently projected through music streaming recommendations. Lastly, this thesis addresses the potential benefits and apprehensions of future contextually aware technology and its ability to reshape the way recommendation algorithms gather and process user listening data. Ultimately, my hope is that this research sheds light on the responsibility of music listeners, but more importantly, of music distributors and curators, as taste makers and gatekeepers, to act progressively and ethically in constructing the cultural reality we live in.