One of the most applauded features of music streaming platforms like Spotify, Last.fm or Deezer is their theme recommendation system. It is very useful for browsing your extensive catalogs and, if it works well, it even allows you to discover new favorite bands. A study recently published in the journal EPJ Data Science concludes that the type of music that is listened to influences, and a lot, in the effectiveness of the recommendations. More specifically, the work establishes that those interested in "conventional music" (the most popular or listened to) tend to receive recommendations that are much more suited to their tastes than those who prefer more alternative genres, such as hard rock or hip hop.
This problem has to do with the so-called popularity bias: songs with fewer interactions are less likely to be recommended by the users themselves, and therefore to be taken into account by the algorithm. It is also known from previous research that those who listen to music that stray from the lane tend to have more complex user profiles: they have listened to more different artists than lovers of popular music
The recommender works apparently simple: the algorithms record and classify all the music that each user listens to (musical genres and subgenres, band names, average playing time, etc.). When someone clicks on a topic, the system shows them what like-minded users have heard
The team of researchers who signed the study, all from Austrian and Dutch universities and research centers, decided to test the effectiveness of recommendation systems to find the seams. To do this, he applied a computerized model to his own database made from the history of music listened to by 4,148 Last.fm users. Half of them were chosen to be regular listeners of mainstream music , or mainstream music (the most common), and the other half prefer more alternative genres (those that deviate from the most usual) .
The Queens of the Stone Age band during its presentation at the Vive Latino 2018 rock festival in Mexico City on March 18, 2018. Alicia Fernandez / El País Four alternative subgenres
The more than 3.4 million songs included in the database were classified into based on a series of "acoustic components" that describe the content of a specific track, the same ones that Spotify uses in its song screening systems: if it is danceable, if the song includes voices or is entirely instrumental, if it is a song by studio or performed live, etc.
With this information, the researchers obtained a more detailed portrait of what is mainstream music and what is not. From there, they used a computerized model to classify music that escapes the canons (the unconventional) into four main categories: folk (music with a lot of acoustics), hard rock (music with a lot of energy), ambient (music with a lot of acoustics). a strong acoustic and instrumental component) and electronic (high energy and strong instrumental component).
After having all the users classified into subgroups, four different algorithms for music recommendation were applied. The study concludes that listeners who prefer background music receive significantly better recommendations than lovers of hardrock .
Variety and quantity influence
The so-called “openness” (if lovers of a musical genre also recommend songs from other genres) and the “ diversity ”(listening to different groups, but within the same gender) are two variables that, the authors assure, have been found in other studies to influence the quality of the recommendations. One of the questions posed to answer this research was whether listeners of unconventional music also have more open and diverse tastes than the rest, which would help explain the lack of success of the recommendation algorithms.
However, when relating the results with openness and diversity, ambient music listeners turn out to be the most open group but also the least diverse (they recommend more songs from other genres, but listen to fewer bands), while hard rock lovers On the contrary: they are the least open to recommending other genres, but they follow more bands.
“Four recommendation algorithms have been applied and, in the four cases, the hardrock group is the one with the worst results. Those of the ambient music group, on the other hand, received better recommendations even than those of conventional music ”, underline the researchers, who call on the platforms to make an effort to better fit the tastes of those who listen to hard rock and other less popular genres. "We understand that improving the recommendations for this active group of users has other effects, such as improving the exposure of artists to recommendation systems."
You can follow EL PAÍS TECNOLOGÍA on Facebook and Twitter .