Predicting User Demographics in Social Networks

Add to your list(s) Download to your calendar using vCal

• Dr Nikolaos Aletras, Amazon
• Wednesday 22 February 2017, 12:00-13:00
• Huxley Building, Room 340.

If you have a question about this talk, please contact Matthew G I Douthwaite.

We would like to invite you to this month’s seminar organised by the EPSRC Centre of Doctoral Training (CDT) in High-Performance Embedded and Distributed Systems (HiPEDS). It is our great pleasure to host Dr Nikolaos Aletras who is an Applied Scientist at Amazon working in the Machine Learning Core team. Previously, he worked as a Research Associate at the Department of Computer Science at UCL , Media Futures Group and he completed a PhD in NLP at the Department of Computer Science of the University of Sheffield.

Talk Abstract: Automatically inferring user demographics in social networks is useful for both social science research and a range of downstream applications in marketing and politics. Our main hypothesis is that language use in social networks is indicative of user attributes. This talk presents recent work on inferring a new set of socioeconomic attributes, i.e. occupational class, income and socioeconomic class. We define a predictive task for each attribute where user-generated content is utilised to train supervised non-linear methods for classification and regression, i.e. Gaussian Processes. We show that our models achieve strong predictive accuracy in all of the three demographics while our analysis sheds light to factors that differentiate users between occupations, income level and socioeconomic classes.

This talk is part of the HiPEDS Seminar Series series.

This talk is included in these lists:

• HiPEDS Seminar Series
• Huxley Building, Room 340

Note that ex-directory lists are not shown.