Issue of the day: Spotify wants to get to know you
IT is a global streaming sensation, with 248 million monthly active users. Now Spotify is working on a programme to personalise its service by determining users’ personality traits.
So Spotify is trying to figure out what its users are like?
It has just been granted a US patent for “methods and systems for personalising user experience based on personality traits”.
What are these “methods”? The patent states that before “assigning a personality trait to the user, a personality model may be built” to figure out “traits”. This model would be based on a variety of factors, such as age and gender; musical taste and listening history. It would also be based on a questionnaire looking at the
“big five” personality traits of “openness, conscientiousness, extraversion, agreeableness, and neuroticism”.
So Spotify wants to make more accurate recommendations? That’s the basic aim. For example, a user assigned the trait of extraversion may be played tracks that are associated with an upbeat mood, while a user said to be introverted would be played quieter tunes.
However?
Presumably Stockholm-based Spotify, which launched in 2008, could then promote content – such as advertising – based on these personality traits.
And it might shout louder at the extroverts in the room? Users could be treated according to who Spotify thinks they are. The patent states: “For example, the tone of voice may be more upbeat, high-pitched and/or exciting for users that have been assigned the personality trait of extroversion”, adding that this “helps to humanise the user interface…thereby improving the user experience”.
It comes as…
Spotify scientists and researchers asked 5,808 volunteers to complete personality tests and then analysed 17.6 million songs – more than 662,000 hours of music – listened to by these users over a three-month period, ultimately linking musical genres to one of the “big five”. The research paper, Just The Way You Are: Linking Music Listening On Spotify And Personality Building On Interactionist Theories, showed that personality traits are predicted by musical preferences and habitual listening behaviours with “moderate to high accuracy”.
Specifically?
They found that, for example, people who like soul music tend to be more agreeable, as are jazz enthusiasts, while lovers of folk are more likely to be open. R&B fans are extroverts, reggae lovers are open and punk fans are “anti-social and emotionally unstable”.
It could ultimately go further? In a far cry from record players and tape decks, the researchers offered insight into the way things could go, saying that “future research could begin to link streaming behaviour with brain scanning, genetic, and physiological data” to match up users with the music they want to hear, without them even articulating it.