mobile “context-awareness” @neal_lathia computer laboratory, university of cambridge mobcom workshop
“by 2025, when most of today’spsychology undergraduates will bein their mid-30s, more than 5billion people on our planet will beusing ultra-broadband, sensor-richsmartphones far beyond theabilities of today’s iPhones,Androids, and Blackberries.” Miller
my research:how can we leverage thedata that they capture?what applications can thisdata support?
data challengesusing data collecting data learning from data
“mobile devices and the mobile internetrepresent an extremely challengingsearch environment. Limited screenspace, restricted text-input andinteractivity and impatient users allconspire...” Church & Smyth
“...data harvesting through mobilephones still presents a variety ofchallenges […] energy consumption isstill very high for both data transmissionand resource-intensive localcomputation...” Rachuri et al. (2011)
as a result,modern-day applications do not take fulladvantage of devices potentialcapabilitiesbut still,...
foursquare check-in: context-augmented?location + time + place features +social network + history + likesdata:35,000,000 check-ins from 925,000 userswe ask:(a) where will users go next? (b) what newplaces will users visit?
(a) where will users go next?we examine the performance of a variety of features encodedin the mobile check-in, and their ability to accurately rank thenext place a user will go to.we measure ranking quality using the Average PercentileRank, where: 0 = terrible, 1 = perfect. Noulas, Scellato, Lathia, Mascolo (2012)
(a) where will users go next?random 0.5user history 0.68categorical preference 0.84social fltering 0.61popular places 0.86geographically close 0.78category hour 0.56category day 0.57place hour 0.76place day 0.79decision tree 0.94 Noulas et al. (2012)
(a) where will users go next?random 0.5user history 0.68categorical preference 0.84social fltering 0.61popular places 0.86geographically close 0.78category hour 0.56category day 0.57place hour 0.76place day 0.79decision tree 0.94 Noulas et al. (2012a)
follow-up work:why consider each check-in in isolation? Noulas et al. (2012b)
what would we like to support?(1: learning) recommender systems(2: collecting) social psychology research(3: using) transport information systems
inferssensed “in the reportedcontext moment” mood (responds)
what kind of problem is this?device + application + user... combinedin the following: just the sensors
data collection for mobile appssense sleep energy-accuracy trade-off
(5) what happens if we succeed? depressed inactive ?
References:G. Adomavicius, A. Tuzhilin. “Context-Aware Recommender Systems.” In Recommender SystemsHandbook.M. Bazire, P. Brezillon. “Understanding Context Before Using it.” In 5th International Conference onModeling and Using Context, 2005.K. Church, B. Smyth. “Who, What, Where, & When: A New Approach to Mobile Search.” In IUI 2008.N. Lathia et al. “Individuals Among Commuters: Building Personalised Transport InformationServices from Fare Collection Systems” In Pervasive and Mobile Computing, 2012.A. Noulas, S. Scellato, N. Lathia, C. Mascolo. “Mining User Mobility Features for Next PlacePrediction in Location-based Services.” In IEEE International Conference on Data Mining 2012a.A. Noulas, S. Scellato, N. Lathia, C. Mascolo. “A Random Walk Around the City: New VenueRecommendation in Location-Based Social Networks.” In International Conference on SocialComputing 2012b.G. Miller. “The Smartphone Psychology Manifesto.” In Perspectives on Psychological Science 7(3).2012.D. Quercia, N. Lathia, F. Calabrese, G. Di Lorenzo, J. Crowcroft. “Recommending Social Events fromMobile Phone Location Data.” In IEEE ICDM 2010, Sydney, Australia.K. Rachuri et al. “SociableSense: Exploring the Trade-Offs of Adaptive Sampling and ComputationOff oading for Social Sensing.” In MobiCom 2011. lK. Rachuri et al. “METIS: Exploring Mobile Phone Sensing Off oading for Eff ciently Supporting l iSocial Sensing Applications.” To appear, 2013.Applications: http://www.emotionsense.org, http://www.tubestar.co.uk