BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Twitter\, Demographics and Emotions: Inferring Perceived User Prop
 erties from Emotional Tone and User-Environment Emotional Contrast - Svitl
 ana Volkova\, PhD Candidate\, Center for Language and Speech Processing\, 
 Johns Hopkins
DTSTART:20150316T110000Z
DTEND:20150316T120000Z
UID:TALK58421@talks.cam.ac.uk
CONTACT:Chan Yin Wah Fiona
DESCRIPTION:In this study we investigate the relationships between a varie
 ty of automatically inferred latent user properties\, opinions and emotion
 s on a large sample of users in online social network.  We first correlate
  user demographics and personality with the emotional profile emanating fr
 om user tweets. We then analyse the relationships between predicted user p
 roperties and user-environment emotional contrast estimated over various n
 eighbourhoods including friends\, retweeted and mentioned users. \nWe demo
 nstrate that many perceived user demographic traits correlate with the emo
 tional contrast between users and their neighbours. We show that users pre
 dicted to be single or those with lower income tend to amplify sad tweets\
 , but older users or those with children dampen them\; users satisfied wit
 h life dampen angry tweets whereas users dissatisfied with life amplify th
 em\; optimists amplify joyful tweets while pessimists dampen them. Based o
 n these correlations\, we show that it s possible to accurately predict a 
 range of perceived demographic traits for a given user\, based solely on t
 he emotional tone emanating from that user and his neighbours.
LOCATION:2nd Floor Seminar Room\, Department of Psychology\, Downing Site\
 , Cambridge
END:VEVENT
END:VCALENDAR