Activity- -Based Serendipitous Recommendations Based Serendipitous Recommendations Activity with the Magitti Mobile Leisure Guide with the Magitti Mobile Leisure Guide System Codename: Magitti Designed and Prototyped by PARC for Dai Nippon Printing Co. Ltd. Presenters • Victoria Bellotti • Bo Begole The Other Co ‐ authors Ed H. Chi, Nicolas Ducheneaut, Ellen Isaacs, Ji Fang, Tracy King, Mark W. Newman, Kurt Partridge, Bob Price, Paul Rasmussen, Michael Roberts, Diane J. Schiano, Alan Walendowski
Overview Recommendation Server Infer Activity • Background Filter and Rank Model Preferences Database Items and motivating fieldwork Context: Time, Location, etc. Restaurants, stores, events, etc. Preferences: Sushi, Bookstores, etc. • System design Feedback Mobile Feedback Device • Evaluation Local Area Consumer 2
About Dai Nippon Printing Co. Ltd. • DNP is a world leader in printing technology and solutions • Affected by the shift from paper to Traditional digital media Publishing The Past: People carried magazines The Present: Most Japanese use a mobile phone to browse the Web and read/write E ‐ mail • DNP asked PARC to develop core technology for new, consumer ‐ friendly digital media • All design to be driven by real need motivated a lot of work to identify: • Best target users Modern • Best solution for their needs Publishing 3
Contextual Publishing Concept Development Discover Discover Technology Technology Fieldwork 1 Fieldwork 1 Fieldwork 2 Fieldwork 2 Finalized Finalized Target Target Brainstorm Brainstorm Choose Choose Confirm Confirm Concept Concept Users Users Proposal Proposal Best Idea Best Idea and Refine and Refine Assess many markets Share background Interviews, Evaluate design Future domain info observations, mock ‐ up in situ technology analysis and scenario feedback Personas bring customer to life Develop scenarios and obtain feedback Leisure guide concept proposal, “Magitti” Brainstorm design ideas Analyze results Refine design based Refine on user feedback concept design Choose the best Young Adults Activity-Aware What to Build 4 at Leisure Leisure Guide
Details: Persona Exploration • Activities • Develop day ‐ in ‐ the ‐ life scenarios (use resources such as magazines) • Role ‐ play day ‐ in ‐ the ‐ life (use props for realism and fun) • Goals • Develop empathy for end ‐ user customer • Find hidden needs • Foster creativity 5
Details: Brainstorm to Generate Ideas • Work as a team • Repeated process • No criticism • First, issues and constraints • No ownership • Then design ideas • Play off others’ ideas • Opportunities to present, reflect & • Interpreters in mixed teams critique • Small teams and “choreography” so • With DNP we covered everyone • Features and user experience • Can reach board • Business models • Can make changes • Competition 6
Details: Developing the Fruit of Our Labor • Clustering to combine many ideas • Take the 5 best • Develop scenarios for each one • Test with prospective user representatives in Tokyo • Choose best ‐ received • Develop mock ‐ up • Test again with user representatives in Tokyo • Develop final concept 7
Many User Studies During Concept Development and Early System Development Features Content Venue database Activity type Interaction Informing Design of Informing Design of classification prediction Form-factor style Functions Coordination Identity Social factors Leisure activity Leisure activity Planning in leisure Transportation venue types type timing & Information Knowledge popularity probability sources of locale Technology use Media Fashion Leisure activity Leisure activity type Information use Leisure activity types type locations desired frequency Correlating Analysis: increasing abstraction Analysis: increasing abstraction Classifying Coding Counting Observation 370 activity, time 3000 activity & reminders Practices Needs Priorities Problems & location reports time reports Time Time Survey Data Data responses Diary 40 Transcripts 670 Responses 10 Transcripts 1000’s of Photos Notes Location entries Observation In-depth Surveys Focus Activity Mobile-phone interviews Groups Sampling Diaries Study Methods 8 Study Methods
From Fieldwork: Who Are the Users • Japanese youth are especially receptive to new technology • 19 ‐ 25 year ‐ olds spend 1.5 times more time in leisure activities than 16 ‐ 19 year ‐ olds or 26 ‐ 33 year ‐ olds • Less school and work pressure • Ideal target for our design • Still very, very busy • School, jobs and little sleep • Relaxation is a priority • The system should do the work • Want to know what others think • Value opinions of real people • Include end ‐ user content 9
From Fieldwork: What do they Do? • Outings often involve meeting friends • Often at “halfway point” far from homes • Eager for local and localized info • Unfamiliar with locations they visit • Open to suggestions • May not plan the main activity • May not plan follow ‐ on activities • Motivation for Magitti 60 • A city ‐ guide that assists in 50 exploration 40 30 Ratings of “How well I know this neighborhood” 20 given by 170 young people stopped on the 10 streets in diverse neighborhoods in Tokyo 0 1 2 3 4 5 6 7 10 1 = Not at All 7 = Extremely Well
Overview Recommendation Server Infer Activity • Background Filter and Rank Model Preferences Database Items and motivating fieldwork Context: Time, Location, etc. Restaurants, stores, events, etc. Preferences: Sushi, Bookstores, etc. • System design Mobile Device • Evaluation Local Area Consumer 11
Details 12 Map Pie Menu User Interface
Akiko and Charles in “Any” Mode Recommendations differ based on Personal Preferences Akiko “Any” Mode Charles “Any” Mode Magitti inferring “Eat” 13
Implicit Interaction: User Informs Magitti’s Modeling as a Side Effect of Purposeful Action When user selects “Change Activity” to get more targeted recommendations, Magitti uses that selection to improve its model of user preferences 14
Demo Video 15
Activity Information Utility EAT Straits Cafe 0.77 Recommendable Recommendable EAT Fuki Sushi 0.64 Items Items Filtering Filtering and and SEE J. Gallery 0.60 Restaurant Reviews Restaurant Reviews Ranking Ranking EAT Tamarine 0.57 Store Descriptions Store Descriptions Parks Descriptions Parks Descriptions DO Sam’s Salsa 0.39 Movie Listings Movie Listings EAT Bistro Elan 0.38 Museum Events Museum Events Magazine Articles Magazine Articles BUY Apple Store 0.33 … … EAT Spalti 0.31
Context History Context History • Time • Prior population • Time • Prior population • • Location Location patterns patterns • • Email analysis Email analysis • • User Queries User Queries • Calendar analysis • User Locations • Calendar analysis • User Locations Eat What you Buy are doing See Do now Read Activity Information Utility EAT Straits Cafe 0.77 Recommendable Recommendable EAT Fuki Sushi 0.64 Items Items Filtering Filtering and and SEE J. Gallery 0.60 Restaurant Reviews Restaurant Reviews Ranking Ranking EAT Tamarine 0.57 Store Descriptions Store Descriptions Parks Descriptions Parks Descriptions DO Sam’s Salsa 0.39 Movie Listings Movie Listings EAT Bistro Elan 0.38 Museum Events Museum Events Magazine Articles Magazine Articles BUY Apple Store 0.33 … … EAT Spalti 0.31
Personal Preferences Context History Personal Preferences Context History • Explicit preferences • Time • Prior population • Explicit preferences • Time • Prior population • • Rating of items inspected Rating of items inspected • • Location Location patterns patterns • • Analysis of content read Analysis of content read • • Email analysis Email analysis • • User Queries User Queries • Behavior; where/when/what • Calendar analysis • User Locations • Behavior; where/when/what • Calendar analysis • User Locations Eat What you Buy What What are doing See you like you like Do now Read Activity Information Utility EAT Straits Cafe 0.77 Recommendable Recommendable EAT Fuki Sushi 0.64 Items Items Filtering Filtering and and SEE J. Gallery 0.60 Restaurant Reviews Restaurant Reviews Ranking Ranking EAT Tamarine 0.57 Store Descriptions Store Descriptions Parks Descriptions Parks Descriptions DO Sam’s Salsa 0.39 Movie Listings Movie Listings EAT Bistro Elan 0.38 Museum Events Museum Events Magazine Articles Magazine Articles BUY Apple Store 0.33 … … EAT Spalti 0.31
Recommend
More recommend
