MusicFX: An Arbiter of Group Preferences for Computer Supported Collaborative Workouts (CSCW98)

Loading...

Flash Player 9 (or above) is needed to view presentations.
We have detected that you do not have it on your computer. To install it, go here.

0 comments

Post a comment

    Post a comment
    Embed Video
    Edit your comment Cancel

    Favorites, Groups & Events

    MusicFX: An Arbiter of Group Preferences for Computer Supported Collaborative Workouts (CSCW98) - Presentation Transcript

    1. MusicFX: An Arbiter of Group Preferences for Computer Supported Collaborative Workouts Joe McCarthy Ted Anagnost Andersen Consulting Center for Strategic Technology Research
    2. Outline
      • UbiComp & Intelligent Environments
      • The MusicFX System
      • Evaluating Group Preference Arbitration
      • Future Work
    3. Ubiquitous Computing
      • Proliferation of networked devices
        • phones, TVs, cam's, mic's, microwaves, refrigerators...
      • Distribution of computing resources
        • portable, wearable, embedded
      • New paradigm of computing
        • input/output ( foreground ) --> sense/respond ( background )
    4. Intelligent Environments
      • “ UbiComp in a box”
        • Interconnected, cooperating devices
        • Concentrated in a small area (e.g., one room)
      • Redefining HCI
        • users --> inhabitants
    5. Observation 1
      • Most UbiComp applications focus on single individuals in multiple spaces
        • Active Badge: open doors, teleporting
        • ParcTab: information access, email
      • What about multiple inhabitants in a single, shared space ?
    6. Observation 2
    7. Music in the Fitness Center (FX)
      • Popular in the Complaint Department
        • 25% of “feedback” focused on music
      • RSI: Repetitive Song Injury
        • 3 stations played, 91 available (DMX)
      • Squeaky Wheels
        • Vocal minority prevails over silent majority
      • Hangovers
        • This morning’s music = last night’s music
    8. Four Issues for any Intelligent Environment
      • Who’s here?
      • What are they doing?
      • What are their preferences?
      • What can I do to help?
    9. Four Issues for MusicFX
      • Who’s here?
        • Members who login [badge reader]
      • What are they doing?
        • Working out while listening to music
      • What are their preferences?
        • Diverse (to say the least)
      • What can I do to help?
        • Play “good” music
    10. The MusicFX System
      • Database of musical preferences
      • Group Preference Arbitration algorithm
        • Group Preference Calculation
        • Candidate Identification
        • Weighted Random Selection operator
    11. Music Preference Database
      • 275 fitness center members
      • 91 musical genres (DMX stations)
      • 5-point rating scale
        • +2 = I love this music
        • +1 = I like this music
        • 0 = I don’t mind this music
        • -1 = I dislike this music
        • -2 = I hate this music
    12. Group Preference Arbitration
      • Group Preference Calculation
      • Candidate Identification
      • Weighted Random Selection
    13. Group Preference Calculation
      • Where
      • GP i = G roup P reference for genre i
      • IP i,j = I ndividual P reference of person j for genre i
      • N = N umber of inhabitants
    14. Candidate Identification
      • Sort genre list by GP i
      • Remove any undesireable genre
        • Individual Preference Filter
      • Candidates are the first M genre
        • Group Preference Filter
    15. Weighted Random Selection
      • Calculate weights for candidates
      • Probabilistically select genre according to W i
    16. An example
    17. Environmental Events
      • Member entrance
        • Login (badge reader)
      • Member exit
        • Timeout (90 minutes)
      • Individual Preference Update
      • System Parameter Adjustment
        • Individual / Group Preference Filter, Maximum Play Time
      • Maximum Play Time Elapsed
    18. The Success of MusicFX
      • Daily operation since November 1997
      • Poll results (after 6 weeks)
        •  : increased variety, having some influence
        •  : abrupt changes, occasional “bad” music
    19. Evaluating Group Preference Arbitration
      • Calculate the “goodness” of MusicFX
      • Estimate the “goodness” of old scheme
      • Compare the old with the new
    20. The “Goodness” of MusicFX
      • Individual Satisfaction rating ( IS )
        • Time i,j = time person j spent listening to genre i
        • IP i,j = person j ’s Individual Preference for genre i
    21. The “Goodness” of MusicFX
      • Overall Satisfaction rating ( OS )
        • For all N members
    22. Individual Satisfaction for all 275 FX Members
    23. The “Goodness” of the Old Days
      • Three genres ( n=3 )
        • Hottest Hits, Power Hits, Dance
        • Assume each person listened to each genre 1/3 of the total time spent working out
    24. Comparing the Old with the New
      • Overall Satisfaction
        • “ Old scheme”: 0.44
        • MusicFX: 0.64
          • 8% higher (statistically significant)
    25. Average Individual Preferences
    26. Top 10 Stations
    27. MusicFX Anecdotes
      • Veto power & IPF
      • Uncommon variety
      • The Polka incident
      • The Chinese Music incident
    28. The Future of MusicFX
      • Better awareness of inhabitants
      • Alternative rating/voting schemes
      • Alternative arbitration schemes
    29. Individual Satisfaction after 6 months (Avg: 0.64)
    30. Average Preferences after 6 months (Avg: -0.39 to -0.50)
    31. Future Group Preference Applications

    + gumptiongumption, 3 years ago

    custom

    1446 views, 0 favs, 1 embeds more stats

    MusicFX is an example of an active environment that more

    More info about this document

    CC Attribution-NonCommercial-ShareAlike LicenseCC Attribution-NonCommercial-ShareAlike LicenseCC Attribution-NonCommercial-ShareAlike License

    Go to text version

    • Total Views 1446
      • 1444 on SlideShare
      • 2 from embeds
    • Comments 0
    • Favorites 0
    • Downloads 49
    Most viewed embeds
    • 2 views on http://interrelativity.com

    more

    All embeds
    • 2 views on http://interrelativity.com

    less

    Flagged as inappropriate Flag as inappropriate
    Flag as inappropriate

    Select your reason for flagging this presentation as inappropriate. If needed, use the feedback form to let us know more details.

    Cancel
    File a copyright complaint
    Having problems? Go to our helpdesk?

    Categories