Keynote Speakers

Pankaj Gupta

Twitter, Inc.

Modeling user interests in Twitter

Twitter provides an efficient way for people to stay informed about their interests and discover what is happening in their world right now. More than half a billion Tweets are sent every day on virtually
every topic imaginable, and a user can follow anyone else without requiring a reciprocal relationship. At Twitter, we want to make  discovery of interesting users to follow and
interesting tweets to read and engage with easy, relevant and personalized. In this talk, I will describe the kinds of data we use and models we build in order to predict and evaluate
users' interests. I will also talk about how we use these interests for the purposes of personalization and recommendations in the Twitter platform.


Pankaj Gupta leads a world-class team consisting of a mix of engineers and data scientists. He is responsible for many personalization/relevance/discovery/recommendation products and technologies at Twitter. Before transitioning to engineering management, he was technical lead of the "Who to Follow" recommendation product and system at Twitter as well as a few other graph-related technologies that are widely used today in many Twitter features. Pankaj holds a PhD in computer science from Stanford university. 

Daniel Tunkelang

Head of Query Understanding

Social Search in a Professional Context

Social networks bring a new dimension to search. Instead of looking for web pages or text documents, LinkedIn members search a world of entities connected by a rich graph of relationships. Search is a fundamental part of the LinkedIn ecosystem, as it helps our members find and be found. Unlike most search applications, LinkedIn's search experience is highly personalized: two LinkedIn members performing the same search query are likely to see completely different results. Delivering the right results to the right person depends on our ability to leverage our each member's unique professional identity and network.  In this talk, I'll describe the kinds of search behavior we see on LinkedIn, and some of the approaches we've taken to help our members address their information needs. 

Daniel Tunkelang leads LinkedIn's efforts around query understanding. Before that, he built and led LinkedIn's product data science team. He previously led a local search quality team at Google and was a founding employee of Endeca (acquired by Oracle in 2011). He has written a textbook on faceted search, and is a recognized advocate of human-computer interaction and information retrieval (HCIR). He has a PhD in Computer Science from CMU, as well as BS and MS degrees from MIT.