ABSTRACT:

Social media platforms encourage users to provide short biographies or descriptions of themselves, providing a mechanism for self identity or to define how they represent themselves to others.    We have assembled a seven+ year longitudinal corpus observing how the self-descriptions of millions of people on Twitter change and evolve.   This provides a unique resource to study notions of self-identity.

I report on the general infrastructure behind this developing data resource, and the observations of social behavior that can be made using it:

·       By studying user references to employment, we can document career progressions, and demonstrate that higher status jobs disproportionately become part of self-identity, more so than highly paid jobs.

·       In the United States, there has been a steady trend towards increased expression of political identities, at the expense of religious identity.

·       We measure the power of self-descriptions to predict user attributes, including which celebrities they are likely to follow.

I will also review my previous work in computational social science, including several tools we have developed of potential interest to researchers in a variety of fields:

·       Polyglot: a system for multilingual NLP entity recognition and sentiment analysis.

·       NamePrism: a tool for inferring ethnicity/nationality from names.

·       DeepWalk: a technique for turning network data into features for regression and other predictive models.

This talk represents work with my collaborators Jason Jones, Dakota Handzlik, and Xingzhi Guo.

Biography: Steven Skiena is Distinguished Teaching Professor of Computer Science and Director of the Institute for AI-Driven Discovery and Innovation at Stony Brook University.  His research interests include data science, bioinformatics, and algorithms.  He is the author of six books, including "The Algorithm Design Manual",   "The Data Science Design Manual", and "Who's Bigger: Where Historical Figures Really Rank", and over 150 technical papers. 

Skiena received his B.S. in Computer Science from the University of Virginia and his Ph.D. in Computer Science from the University of Illinois in 1988.   He is a Fellow of the American Association for the Advancement of Science (AAAS), a current and former Fulbright scholar, and recipient of the University of Virginia Engineering Distinguished Alumni Award (WahooWa!), the ONR Young Investigator Award and the IEEE Computer Science and Engineer Teaching Award.   More info is available at http://www.cs.stonybrook.edu/~skiena/.

For further information please contact giovanni.tardino@unibocconi.it