Designing Delightful Listening Experiences: Mixed Methods Research in the Age of Machine Learning
Summary
Millions of listeners around the world use Spotify to listen to audio experiences that are personalized to their taste, yet relevant in the broader cultural context. Spotify is a unique product because unlike many other eyes the first app, a majority of Spotify experience is phenomenological – it happens in listeners’ ears, minds and bodies, after they hit “Play”. Why do people form Meaningful Connections™ with some type of audio content, but not all, and how do we ensure that our ML models respect the nuances of what makes listening to music and podcasts enjoyable? This talk will shed light on such topics and leave the audience with ideas, challenges and possible best practices for using Mixed Methods Research in the age of ML to build delightful product experiences.
Key Insights
-
•
Machine learning has shifted from backend tech to a frontline role shaping consumer experiences like music recommendations.
-
•
Spotify personalizes not just music content but also merchandising and UI elements like playlist covers and home screen layout.
-
•
Music preferences are deeply contextual, changing by time of day, activity, and listener persona.
-
•
The assumption that skipping a song is a purely negative signal is often incorrect; skip behavior varies by user goals and trust.
-
•
Mixed methods research at Spotify combines data science, qualitative user research, and now increasingly machine learning itself.
-
•
Personas such as 'Nick' (curators) and 'Shelley' (casual listeners) help segment skip behaviors and user needs effectively.
-
•
Editorial playlists blend human curation with ML personalization, balancing communal music experience and individual taste.
-
•
Contextual factors, including social and environmental considerations, greatly influence music listening behavior and signal interpretation.
-
•
User mental models around music and playlists differ significantly across personas and impact engagement and skipping.
-
•
User research teams at Spotify have grown significantly, highlighting the rising importance of research in ML-driven product development.
Notable Quotes
"Machine learning used to be backend technology, but now millions of consumer experiences are decided by machines or algorithms."
"These playlists have some element of machines recommending music in addition to editors behind the scenes."
"There’s been a fundamental shift in consumer products in the last five years driven by machine learning."
"Skipping a song is one of the most common user behaviors and is often assumed to be a bad thing."
"We showed that a skip is not a skip — it varies based on listener goals and trust in the playlist."
"Human behavior is complex and machine learning models need to understand those nuances."
"We consider machine learning as the third leg of mixed methods research, alongside data science and user research."
"Music is personal but also cultural and communal, which creates complexity for personalization."
"Personas like Nick and Shelley help us understand different user attitudes towards music listening and skipping."
"There hasn’t been a better time to be a user researcher, especially in machine learning enabled experiences."
Or choose a question:
More Videos
"Empathy in jazz means the band is in it together—when someone plays a wrong chord, the rest adapt and turn it into an opportunity."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
November 6, 2017
"Evergreen content needs a strong perspective on why the topic matters along with practical examples on how to apply it."
Louis RosenfeldCoffee with Lou: Should You Write a (UX) Book?
March 7, 2024
"Building influence has been such a challenging part of growing in my own career. It takes a lot of communication and understanding others’ goals."
Catt Small Micah Bennett Brian Carr Jessica HarlleeWhat's Next for ICs: Exploring Staff and Principal Designer Roles
February 22, 2024
"Sharing your research skills broadly within your company can create unexpected opportunities to improve experiences."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"Processing limits and licensing terms currently restrict how much video and audio these AI tools can handle."
Llewyn Paine[Demo] Deploying AI doppelgangers to de-identify user research recordings
June 5, 2024
"Random assignment to treatment or control is essential—if it’s not random, it’s not a true experiment."
Joshua NobleCasual Inference
October 6, 2023
"Not all learnings lead to crucial conversations, but big insights often do, requiring emotional awareness."
Sara LogelYour Colleagues are Your Users Too
March 29, 2023
"Sponsor sessions may require registration by email to prevent Zoom bombings and protect session integrity."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"Accessibility isn’t a checkbox you run automated tests for; you must involve people with disabilities to benchmark success."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023