MUSICFX: an arbiter of group preferences for computer supported collaborative workouts

By J. F. McCarthy, Theodore D. Anagnost. Conference on Computer Supported Cooperative Work, 2000

305 citations recorded by the source corpus.

Environmental factors affecting shared spaces are typically designed to appeal to the broadest potential audiences they will serve, while ignoring the preferences of the actual inhabitants found in the environment at any given time. Examples of such factors include the lighting, temperature and décor in the common areas of an office building. MUSICFX is a group preference arbitration system that allows the members of a fitness center to influence, but not directly control, one of these shared factors: the selection of music in the fitness center. The system includes a database of member preferences, a badge reader to track who is in the fitness center, and a group preference arbitration algorithm that sorts the 91 genres of music (available via satellite) according to the preferences of the current group of members. MUSICFX has been in daily operation at the fitness center in the Northbrook office of Andersen Consulting since November 1997, and currently has over 800 members enrolled in the system. This video illustrates the impact of MUSICFX in a series of vignettes and describes how the system allocates influence among the inhabitants of the fitness center environment. Further details on the system can be found in our CSCW ’98 paper.

View Paper: https://www.semanticscholar.org/paper/1b51058f4d47a1c1843075342ebde98ccf5114f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Recommendation to Groups (2007, methodology): “The problem of manipulation is illustrated by experience with an early version of the system MUSICFX (McCarthy and Anagnost [27]), one of the earliest group recommender systems, which automatically selected music genres for the music to be played in a fitness studio: Although the system essentially ”
An Efficient Group Recommendation Model With Multiattention-Based Neural Networks (2020, background): “McCarthy and Anagnost [14] gave a group preference arbitration system that allows group members to inﬂuence the selection of music in a group.”
Collaborative Filtering Recommender Systems (2011, background): “The initial trial of theMusicFXsystemfor selectingfitness centerbackgroundmusic allowed an individual to force a music change by giving the current music the minimum rating [92].”
Hybrid Web Recommender Systems (2007, background): “(Since restaurant meals are often taken in groups, the task is effectively one of group recommendation [27].”
TV Program Recommendation for Multiple Viewers Based on user Profile Merging (2006, methodology): “MusicFX (McCarthy and Anagnost 1998) selects background music to suit a group of people in a fitness center.”
Recommender systems: from algorithms to user experience (2012, unknown): “One of the earliest explorations of this idea was the MusicFX recommender by McCarthy and Anagnost (1998) for “work out music” to be played in a gym while people exercise together.”
Recommender Systems (2016, unknown): “Group recommendations have been used in a variety of domains, such as movies [168], television [653], music [412], and travel [52, 272, 413].”
Exploring social influence for recommendation: a generative model approach (2012, background): “The first one creates an aggregated profile for a group based on individual profiles of its group members and makes recommendations based on the aggregated group profile [21, 33].”
Group Recommender Systems: Combining Individual Models (2011, methodology): “In the Ambient Intelligence and MUSICFX scenarios, they experience the music.”