Day 30 and outro script

A lot has happened in these last ten days. 

I managed to do the unthinkable, what I thought was impossible. 

Discover new music

This aint no Bullshit, the RA didnt hoodwink me here, put me in a personalised illusion, I was actually recommened a brand new genre, seperate from my base recommendations. 

Somehow, deep in the brain of the RA, the diversification tools decided to wake up and recommend me this... (Put hand up)

'Happy hour' 

Filled with Funk and Soul hits from the 60s and 70s. 

But thats not all. On top of this, I somehow managed to translate this genre into my base recommendations and it has now become a main stay in my recommendation pool. 

Days before this I was sulking, the data I was collecting was very generic and seemed to correlate with mostly everything credible sources online spoke about. You Know, 'Spotify is influencing your music tastes' 'Can you gain control from the algorithm' 

Well it seems you can. Not only was I recommended something so outa left field, but through replaying that music, I shifted my recommendations to include music from different eras. I was getting 90s rap 80s pop. This single playlist had opened up my recommendations and made me feel like I was in control of my own music tastes. 

In fact, a study conducted by a fella named George knox, found that when users switched from payed services like Itunes, to Streaming services such as Spotify, unique artists heard jumped by 62%, 12 months later lowering to only 32%. https://pubsonline.informs.org/doi/10.1287/mksc.2017.1051

Suggesting that discovering music through Spotifys RA and the curated playlists, can introduce users to more unique genres and artists. 

It would be interesting to see an experiment go on like this for longer than what I did because it seems like once the RA gathers more historical data from you, it begins to branch out abit.  

Of course I am still heavily pushed the same mainstream contemporary slop Im use to, but there have been moments throughout this experiment that showed a more diverse and varied experience. Everything from the occasionally "new" playlists to the fun and experimental discover weekly's that offered the most "natural feel" for a curated playlist.

Outro

Overall this has been an interesting and inciteful look into how a user can navigate their way through Spotify's recommender system. examining the potential for users to be pushed into a filter bubble through using Spotify's curated playlist and how the RA will create personalised illusions that give the impresion that a user is discovering 'new music'. 

At times it felt like the RA lacked any variety or diversification and it repeatedly felt like the RA was limiting the content it could recommend to me. 

By the first week I was noticing a narrowing effect within my recommendations and saw a consistant pattern within my curated playlists. This being the general push towards mainstream content that I felt the RA was navigating me towards. 

It seems Spotify collects data from rising online trends and third party sources that are connected to your Spotify account. Meaning what you interact with on Facebook or TikTok could potentially influence the music you are recommended. https://www.spotify.com/uk/safetyandprivacy/personal-data-collected

https://www.spotify.com/uk/safetyandprivacy/understanding-recommendations

and I was seeing this alot. It felt as if most of the songs featured on my daylist or discover weekly were taken straight of TikTok and placed into my recommendation pool. 

Alongside this, Spotify also states that musicians can pay for their songs to be recommended to targeted users. (Show image of Spotify payed recommendations) and articals such as this one show how record labels are using this feature to influence users music tastes, offering their artists royalties as collateral. 

With this, do I think RA's are affecting users music tastes. 

Yes 

But, through my research we have found that users can take control of their recommendations and utilise their personalised illusions to expand their music tastes. and it seems that RA's have been shown to increase the amount of unique artists and genres that a user can experience. 

and I would be lying if I said I didnt enjoy some of the curated playlists that were recommended to me over the course of the experiment. 

References  

Comments

Post a Comment

Popular posts from this blog

Intro Script

Algorithms, almost seems like every year they dictate more and more things we do. From the things we buy, watch, scroll past and listen to. It seems like our whole life will soon be dictated by some algorithm that recommends us the most optimal daily routine taking our daily habits and diet into consideration. I'm sure that's fare into the distant future though there's definitely no apps that are already doing that. (Look dead into camera and pull ‘are you serious rn face)  https://clickup.com With how much Ai is being integrated into our lives it honestly seems like we have no control over what we are being recommended any more. And this is seemingly locking people into certain types of shows they watch, videos they see while doom scrolling and music they hear on apps like Spotify. Like I have a playlist on Spotify with over 2000 songs ok and I swear it feels like the same ten artists are being played more so than others.  The worst part about it though is that I don't...
Read more

Day 29 (Success)

My work has payed off and it seems that there are ways to bring new recommendations into your base recommendation pool. Granted this took a lot of time and meant I had to listen to the Happy Hour playlist on repeat. However, we now have three new playlists that include this type of music. This includes: Daylist (Funk Soul Groovy Evening) Daily Mix 2 Martha Reeves and The Vandellas Mix Along with this, It seems the throwback subheading, on the homepage, is experimenting with older music. As I now have a 'Born in The 90s' playlist. Previously, this subheading only contained music that went as far back as the 2000s. This does show, that the diversification tools, that Spotify include in their recommender systems, are able to expand a users music tastes, when given enough historical data. If this experiment was to happen for a longer period, and a bot was used instead of myself, then the results would perhaps show that: 'While Spotify's RA does seem to favour pushing users ...
Read more

Day 17

I got a chance to look into some different playlists. Today I listened to a playlist caled unwind 00s and it consisted of throwback songs from the past decades. It was a fun experience but it didnt really bring any new genres into the recommendation pool.  The playlist was mostly filled with popular artists from around the 2000s such as Bruno Mars and MGMT. 
Read more