In the thesis, Pirkka Åman explores music recommendation systems and suggests new discovery strategies that make use of context information, information describing the listener’s situation. The ethical cornerstone of the thesis is to support cultural diversity by influencing music recommendations towards non-obvious and non-mainstream music. Åman believes that one way to achieve serendipitous – new, good, and often surprising – musical discoveries is to offer people ways to augment urban environments with music.

FRIDAY 12 JANUARY 2018 from 12:00
Lecture hall 822, ARABIA
Aalto University School of Arts, Design and Architecture
Hämeentie 135 C, 00560, Helsinki

M.Soc.Sci. Pirkka Åman will defend his thesis Musical Serendipity. Designing for Contextual Music Recommendation and Discovery. on Friday 12 January 2018.

Opponent: PhD François Pachet, Spotify

Custos: prof. Lily Díaz-Kommonen

Discussion will be in English.

More information

In the thesis, Pirkka Åman explores music recommendation systems and suggests new discovery strategies that make use of context information, information describing the listener’s situation. The ethical cornerstone of the thesis is to support cultural diversity by influencing music recommendations towards non-obvious and non-mainstream music. Åman believes that one way to achieve serendipitous – new, good, and often surprising – musical discoveries is to offer people ways to augment urban environments with music.

Today, almost all music that has been recorded is available online. The problem for music lovers is finding the most interesting music from the catalogs of millions of tracks. One way to approach the problem is to include some kind of context information to recommendations, for example, location, time, social context or activity.

The author presents concepts and prototypes showcasing the potential uses of context information and analyzes interactions and context information used in commercial services and research prototypes. The results of the thesis show that involving context factors in music recommendation can lead to rewarding user experiences and serendipitous discoveries. The focus of music discovery is in urban environments where the field studies where conducted. The field study participants felt that the discovery of music and events improved the quality of the everyday life, showing the potential for similar commercial services.

On a more abstract level, the ethical undercurrent of the work is promoting cultural diversity as well as co-creation of urban environments with music-related applications. Through the concepts and prototypes, the author aimed to empower people by offering means to modify their environments by creating, experiencing and sharing virtual, augmented layers of music and other media content.

While the results show that the users indeed experienced serendipity in many ways, it can not be proven that context-aware music recommendations necessarily lead to cultural diversity. Instead, design implications are given to help designers and researchers of future systems to build rewarding and enjoyable context-aware content services, especially to enrich urban environments. The implications include:

Supporting open meaning-making through combinations of different media content and places;
Visual and interactive UI elements that communicate the system logic or explain why a recommendation was made;
Positive restrictions, such as allowing the content to be available only when the user is near a certain location or within a defined time window;
Supporting serendipity can be approached in many ways, for example by combining music with an activity, a location, certain time or an identity, which may result in serendipitous discoveries of not only music but the cultural layers of urban environments as well.
The work helps in opening new directions in the domain of social media since there are few studies conducted on music and social media services from the contextual point of view. Furthermore, various context-aware services (e.g. mobile shopping, advertising, travel and lifestyle applications) that sense people’s activity or location may benefit from the work.

Welcome!