Today Eelco Wiechert presented and defended his master thesis on the occurrence of the peak-end effect in music playlist experience, supervised by Martijn Willemsen and myself. Psychological literature tells us that when evaluating an experience, all individual episodes that make up the experience have equal weights. When people evaluate an experience, they mainly consider the most intense episode (peak) and the last episode (end). Thus when we do our objective playlist evaluation, we should take this into account.
Eelco designed a very extensive study in the form of a Flask application running on Heroku building on Spotify‘s API that allowed participants to listen to personalized playlists that he manipulated to contain an extreme peak and end, or a smaller peak and end. The peaks and ends were done based on the valence and energy audio features provided by Spotify and in order to investigate the research question he asked users to rate all individual songs in the playlist and the playlist as a whole.
The basics of what he found was that the values of the most intense song and the last song indeed explain additional variance in the playlist evaluation over considering the average value of the individual songs. And there are (naturally) several smaller, interesting findings that can guide us in our future research.
If you’re interested in reading his work, I will add the link here as soon as it is available.
I was asked to join the panel responsible for judging the final presentations in our departments course ‘Mobile Innovation & Marketing’. 12 teams of students pitched ideas for new apps that add value to the customers of businesses in and around Maastricht. People came up with all kind of apps, to help people in gyms, apps to help find a new home for dogs in animal shelters, scooter-sharing, shopping in the supermarket and many others.
And in addition I got to sit in our school’s gorgeous aula, where I’ll be teaching myself from September. Very nice experience!
Today I started working at the Marketing and Supply Chain Management in the School of Business and Economics in Maastricht University and at the Business Innovation and Smart Services (BISS) Institute in Brightlands Campus, Heerlen.
Today I graduated after defending my thesis in front of Joe Konstan, Jürgen Ziegler, Paul de Bra, Maurits Kaptein, and my team of supervisors Martijn Willemsen, Chris Snijders and Mykola Pechenizkiy.
The research in this thesis focused on personalization, and mainly how to bridge the gap between the psychological understanding of systems’ users and the methodological challenges of building systems that personalize.
I spent a week in Tokyo, where I attended the Intelligent User Interfaces (IUI) conference. I co-organized the HUMANIZE, a workshop aimed at incorporating psychological theory in personalized interfaces. If you are interested in this idea, please have a look at the workshop proceedings. And apart from meeting people and learning new thing, I also got to see a bit of Tokyo during the evenings.
Today I gave a presentation on the first Machine Learning Netherlands meetup. I presented my take on adopting a more user-centered perspective in recommender systems, through user feedback.
If you’re interested, find my slides on slideshare. And if you’re interested in joining a Machine Learning Netherlands meetup, go to their meetup page