Rosenverse

This video is only accessible to Gold members. Log in or register for a free Gold Trial Account to watch.

Log in Register

Most conference talks are accessible to Gold members, while community videos are generally available to all logged-in members.

Designing Delightful Listening Experiences: Mixed Methods Research in the Age of Machine Learning
Gold
Tuesday, March 31, 2020 • Advancing Research 2020
Share the love for this talk
Designing Delightful Listening Experiences: Mixed Methods Research in the Age of Machine Learning
Speakers: Sohit Karol
Link:

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

  • Personalization at Spotify happens on multiple layers: content sequencing, merchandising, and overall experience.

  • Spotify’s playlists balance algorithmic recommendation and editorial curation for personalized yet communal music experiences.

  • User behavior signals like song skipping are commonly assumed negative but are contextually complex and can be positive.

  • Mixed methods research at Spotify integrates user research and data science, with an emerging role for machine learning as a third component.

  • Distinct personas like 'Nick' (music collector) and 'Shelley' (casual listener) exhibit different skipping behaviors and trust models.

  • Skipping meaning depends on user goals: active music exploration vs passive listening.

  • Contextual factors such as environment and social setting affect user interactions and should influence model signals.

  • Machine learning models need to incorporate complex, nuanced human behaviors, mental models, and trust dynamics.

  • Investing in the right raw data signals is a multi-year strategic decision with major impacts on both user experience and business outcomes.

  • User research teams at Spotify have grown significantly as the importance of understanding human factors in ML-driven products is recognized.

Notable Quotes

"Machine learning used to be back-end technology, but now machines decide a lot of consumer experiences."

"If machines are crafting the user experience, why do they need me as a researcher? That was my big question."

"In the old world, radio DJs curated music for everyone; now every individual gets a unique playlist."

"Skipping a song is probably the most benign behavior, but it’s also the most misunderstood signal."

"Nick says, no one else can make your perfect playlist; you have to make it yourself."

"Shelley says, I don’t know what I want, but I know I want something good and I want Spotify to do the work."

"Some signals can be measured, some cannot, and some should not be measured in machine learning."

"Human behavior is complex and machine learning models need to take into account nuances, biases, trust, and mental models."

"We are now using mental model diagrams and journey maps physically in machine learning teams."

"There hasn’t been a better time to be a user researcher in a machine learning-driven product world."

Ask the Rosenbot
Etienne Fang
The Power of Care: From Human-Centered Research to Humanity-Centered Leadership
2021 • Advancing Research 2021
Gold
Prerna Makanawala
Achieving Balanced Design Consistency
2021 • Design at Scale 2021
Gold
Bilan Hashi
The Tension Between Story Collecting and Story Telling in Research
2021 • Advancing Research 2021
Gold
Laura Weiss
Turn Down the Heat: 3 Ways to Handle Conflict in the Moment
2024 • Rosenfeld Community
Margot Bloomstein
Fostering Trust in Your Brand and Beyond (Videoconference)
2020 • Enterprise Community
Alicia Mooty
Design Staffing Models
2021 • DesignOps Summit 2021
Gold
Erin Weigel
UX Lessons from running more than 1,200 A/B Tests (Videoconference)
2024 • Rosenfeld Community
Marissa Cui
Climate Design Product Showcase (Videoconference)
2024 • Climate UX Interest Group (Rosenfeld Community)
Yoel Sumitro
Actions and Reflections: Bridging the Skills Gap among Researchers
2022 • Advancing Research 2022
Gold
Dr. Jamika D. Burge
Bridge Building across Research Disciplines (Videoconference)
2021 • Advancing Research Community
Barb Spanton
Doing Work That Matters: A Look Beyond The Idealistic Notion of 'Doing Meaningful Work'
2022 • Design at Scale 2022
Gold
Sam Proulx
Mobile Accessibility: Why Moving Accessibility Beyond the Desktop is Critical in a Mobile-first World
2022 • Civic Design 2022
Gold
Todd Healy
Driving Change with CX Metrics
2023 • Enterprise UX 2023
Gold
Kate Koch
Flex Your Super Powers: When a Design Ops Team Scales to Power CX
2021 • DesignOps Summit 2021
Gold
Marina Martin
Lives on the Line: The Stakes of UX at the Scale of Government
2018 • Enterprise Experience 2018
Gold
Sean McKay
Whole Product Thinking: Expanding beyond problem and solution space thinking (Videoconference)
2024 • Rosenfeld Community

More Videos

Jack Moffett

"In SAFe, Product Owner and Product Manager roles can be confusing and inverted compared to other models, adding to role ambiguity."

Jack Moffett

SAFe or Sorry? (Videoconference)

May 29, 2019

Tricia Wang

"When you look at the target too closely, you miss what’s around it; focus longer term to avoid target fixation."

Tricia Wang

SCALE: Discussion

June 15, 2018

Fredrik Matheson

"Enterprise experience is often about broken technology and users having to keep their cool under pressure."

Fredrik Matheson

First-time users, longtime strategies: Why Parkinson’s Law is making you less effective at work – and how to design a fix.

June 8, 2016

Laine Riley Prokay

"Starting small is okay, and I actually recommend it for kickstarting this kind of work."

Laine Riley Prokay

How DesignOps can Drive Inclusive Career Ladders for All

September 30, 2021

Shipra Kayan

"VOC enhances but does not replace user research; it captures the nuggets that would otherwise get lost."

Shipra Kayan

How we Built a VoC (Voice of the Customer) Practice at Upwork from the Ground Up

September 30, 2021

Kristen Guth, Ph.D.

"The fog method helps separate facts from assumptions to break unproductive decision loops."

Kristen Guth, Ph.D.

Out of the FOG: A Non-traditional Research Approach to Alignment

March 28, 2023

Joi Freeman

"Often diverse candidates say they have to keep their heads down just to fit in and move up."

Joi Freeman

A New Vantage Point: Building a Pipeline for Multifaceted Research(ers)

March 30, 2020

Victor Udoewa

"Data informs, but humans decide."

Victor Udoewa

Theme One Intro

March 27, 2023

Peter Merholz

"If you do your job as a designer, talk to users, create great designs, it’s not enough. You need to get the strategy right."

Peter Merholz

Customer-Centered Design Organizations

June 8, 2017