Overall this has been an interesting and inciteful look into how a user can navigate their way through Spotify's recommender system. We have examined how users can be pushed into a filter bubble through using Spotify's curated playlist and how the application will create personalised illusions that give the impresion that a user is discovering 'new music'.
I would say my experience with using Spotify's curated playlists was, at times, repetative and lacking variety. I noticed a narrowing effect within the first week of using the application and found that Spotify favours recommending new users contempary mainstream music of today. Later research would prove that Spotify's RA collects data from rising trends and users behaviour on and off the app. (Spotify, No Date) Alongside this, Spotify also state that musicians can pay for their songs to be recommended to targeted users. Stassen offers additonal research proving that artists record labels are influencing personalised recommendations, offering their artists ryalties as collateral. With this additional imformation we can gauge how Spotify's RA shapes a users music taste, potentially making the user experience disatisfying if they primaraly use the curated playlists. https://www.statista.com/topics/11066/music-streaming-services-worldwide/#topicOverview
https://www.musicbusinessworldwide.com/spotify-is-letting-record-labels-influence-personalized-recommendations-so-long-as-they-pay-for-it-in-royalties/#:~:text=Spotify%20is%20letting%20record%20labels,in%20royalties%20%2D%20Music%20Business%20Worldwide
https://www.spotify.com/uk/safetyandprivacy/personal-data-collected
https://www.spotify.com/uk/safetyandprivacy/understanding-recommendations
Patterns emerged throughout the experiment, as I had noticed Spotify recommending sub-genres and similar genres that related to my base recommendations. This made it difficult to experience a truely 'new genre' as the RA was primarily recommending me music that was similar to what I had first listened to. Playlists such as:
- Lo-Fi House,
- Drake Mix and
- Indie Chillout
Were presented as new experiences. However, they rarely introduced any new artists, or genres, and instead pushed content that I had heard previously in my base recommendations.
Playlists such as these formed personalised illusions that made me think I was experiencing new content. The 'Discover Weekly' playlist was the biggest offender for this, as each week it would present me with truely new music that would bring an entirely new listening experience. However, these experiences rarely ever translated into my base recommendation pool; which stayed consisitant throughout the whole experiment. Research conducted out of this experiment found that the RA is designed to present you playlists thart are familiar, in hopes to keep you listening to music as you would be more likely to hear your favourite tracks more often.
My first temporal change I felt while using the application was my switch from primaraly Pop catered playlists, to R&B catered playlits. This happened early in the experiment and can be explained due to the fact that the RA simply didnt have enough historical data to understand exactly what type of music I like. So when switching up my listening habits, I would see drastic changes within my recommendations; This is how I was introduced to R&B.
Another monumental change happened during the last leg of the experiment. Throughout the experiment, I found it difficult to translate the new genres I was being recommended into my base recommendations. Unexpectadley, I was recommended a Soul/Funk playlist that featured music from the 60s-70s. This in its self contradicts previous research around filter bubbles on Spotify, and suggests that the diversification tools Spotify implement, allow users to reach new genres. Plus, I was able to filter this type of music into my base recommendations through listeing to the playlists more than once. Essentially, shaping my own music tastes through using the curated playlists Spotify offer. After this, my recommendations started experimenting with music from different eras such as 80s-90s Rap and Pop. Previously, the RA had only recommended me music that went as far back as the 2000s. (More info on day 29 blog)
Multiple times throughout the experiment I felt like I had fell into a filter bubble. Discovering music purely through the curated playlists isnt impossible, but challenging.
Comments
Post a Comment