BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Recommending Social Events from Mobile Phone Location Data - Danie
 le Quercia (University of Cambridge)
DTSTART:20101104T160000Z
DTEND:20101104T170000Z
UID:TALK26358@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Cities offer thousands of social events a day\, and it is diff
 icult for dwellers to make choices. The combination of mobile phones and r
 ecommender systems can change the way one deals with such abundance. Mobil
 e phones with positioning technology are now widely available\, making it 
 easy for people to broadcast their whereabouts and recommender systems can
  now identify patterns in people's movements. We have carried out a study 
 of the relationship between preferences for social events and geography\, 
 the first of its kind in a large metropolitan area. We have sampled locati
 on estimations of one million mobile phone users in Greater Boston\, combi
 ned the sample with social events in the same area\, and inferred the soci
 al events attended by 2\,519 residents. Upon this data\, we have tested a 
 variety of algorithms for recommending social events. We found that the mo
 st effective algorithm recommends events that are popular among residents 
 of an area. The least effective\, instead\, recommends events that are geo
 graphically close to the area. This last result has interesting implicatio
 ns for location-based services that emphasize recommending nearby events.\
 n\nblog post: http://tinyurl.com/36zjb88\n\npaper: http://tinyurl.com/32u2
 dpe\n
LOCATION:FW26\, Computer Laboratory\, William Gates Builiding
END:VEVENT
END:VCALENDAR