Spotify Me: Facebook-assisted automatic playlist generation

Abstract

We design a novel method for automatically generating a playlist of recommended songs in the popular social music sharing application Spotify that are liked with high probability by a user. Our method employs multiple seed artists as an input that are obtained via the Facebook likes of artists and the listening history of songs of a Spotify user. First, we construct an input vector comprising all the artists that the user likes on Facebook and listens to in Spotify. Then, we search for other artists and bands related to them using EchoNest, an online state-of-theart machine learning platform. We assign a score to every artist in the thereby obtained collection, based on the frequency of his/her appearance. Finally, we construct a playlist comprising randomly selected popular songs associated with the most frequently cited artists. We examine the recommendation performance of our algorithm by computing its WTF score (fraction of disliked songs) and novelty factor (fraction of new liked songs) on playlists generated for different seed input sizes. We observe that our approach substantially outperforms the built-in Spotify Radio recommender. On 30 song playlists, we are able to improve the WTF score by 49% and the novelty factor by 42%, on average. Due to its general design, our method is broadly applicable to a variety of personal content management scenarios.

Analysis of The Trend of Spotify

“…So to compete, Spotify might want to think about creating its own hardware. Although it is quite challenging, creating hardware is the most practical [10]. With the ability to add new subscriber services on top of that, Spotify's smart speakers give the corporation total control over what is provided to its users.…”

A Joint Markov Model for Communities, Connectivity and Signals Defined Over Graphs

“…This occurs for instance, in social networks, where users are profiled as belonging to a community, e.g. by age, school or association, but mutual interactions and correlation between users have to be estimated to setup personalized advertising [23]. In such a case, the community information can be leveraged in estimating connectivity pattern between users' choices.…”

Cluster Analysis of Musical Attributes for Top Trending Songs

“…Data scientists at Spotify had developed Discover Weekly, a personalized playlist which updates weekly and reached 1 billion streams within the first 10 weeks from its release, powered by a scalable factor analysis of Spotify's over two billion user-generated playlists matched to each user's current listening behavior [6]. Others had also generated playlist recommender systems based upon playlist names [10], social data of musicians [3], or the Facebook likes of artists and the listening history of songs of a Spotify user [4]. Finally, a survey study finds that track and artist popularity can play a dominant role in the automated playlist generation process [1].…”