Presentation Title

Who Are You? ...Honestly!

Presenter Information

Zeinab Mahdavifar

Degree Name

Master of Computer Science and Systems (MCSS)

Department

Institute of Technology

Streaming Media

Location

UW Y Center

Start Date

21-5-2015 5:45 PM

End Date

21-5-2015 5:50 PM

Abstract

Online social media has made life easier in many ways. Stay in touch with old classmates (Facebook), find a way to connect to like-minded professionals all over the globe (LinkedIn), and even seek help from fellow humans we could never imagine otherwise to help us (Mechanical Turk)! Social network profiles are never complete. Ascertaining personality traits and accurate determination of age and gender can make such social networks safer and stronger instruments of true collaboration and human connection.

In my talk, I will discuss the predictive models we built with the Social Media group within the Center for Data Science to infer users’ missing or misrepresented attributes. I will also demonstrate how our models use a complex set of links in social networks to predict age and gender accurately. Our model uses publicly available data to find privately accurate information about a user in aid of law enforcement, communal safety and social well-being.

Share

COinS
 
May 21st, 5:45 PM May 21st, 5:50 PM

Who Are You? ...Honestly!

UW Y Center

Online social media has made life easier in many ways. Stay in touch with old classmates (Facebook), find a way to connect to like-minded professionals all over the globe (LinkedIn), and even seek help from fellow humans we could never imagine otherwise to help us (Mechanical Turk)! Social network profiles are never complete. Ascertaining personality traits and accurate determination of age and gender can make such social networks safer and stronger instruments of true collaboration and human connection.

In my talk, I will discuss the predictive models we built with the Social Media group within the Center for Data Science to infer users’ missing or misrepresented attributes. I will also demonstrate how our models use a complex set of links in social networks to predict age and gender accurately. Our model uses publicly available data to find privately accurate information about a user in aid of law enforcement, communal safety and social well-being.