BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Detecting User Polarization in Social Media
DTSTART:20180711T140000
DTEND:20180711T160000
DTSTAMP:20260511T081214Z
UID:0e97120f7a8176b4d183f77e4206749c8657f2f048c2402291a0a656
CATEGORIES:Conferences - Seminars
DESCRIPTION:Tugrulcan Elmas\nEDIC candidacy exam\nExam president: Prof. Ro
 bert West\nThesis advisor: Prof. Karl Aberer\nCo-examiner: Prof. Pierre Di
 llenbourg\n\nAbstract\nDue to homophily principle\, people only link thems
 elves to likewise people\, which leads to political polarization. Previous
  works indicate this phenomena is observed in Twitter users' retweets and 
 hashtag usage. Polarization is detrimental\, but it is helpful in predicti
 ng political orientation of users as users are coherent in their thoughts 
 and behavior in Twitter.\n\nWe survey papers which exploit this phenomena 
 by predicting political orientation by content and retweet behavior and pr
 opose our framework which will extend them by considering and taking advan
 tage of all user features available.\n\nBackground papers\n\nPolitical pol
 arization on twitter\, by M. D. Conover\, et al.\nValidation of Twitter op
 inion trends with national polling aggregates: Hillary Clinton vs Donald T
 rump\, by Bovet\, A.\, et al.\nBiaswatch: A lightweight system for discove
 ring and tracking topic-sensitive opinion bias in social media\, by Lu\, H
 .\, et al.\n\n 
LOCATION:BC 03 https://plan.epfl.ch/?room==BC%2003
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR