Thursday, October 17, 2013

Title: Slow Search: Improving Information Retrieval by Including People in the Search Process
Speaker: Jaime Teevan (Microsoft Research) 
Date: Wednesday, October 23
Time: 12-1pm
Room: GHC 8102 

We live in a world where the pace of everything from communication to transportation is getting faster. In recent years a number of “slow movements” have emerged that advocate for reducing speed in exchange for increasing quality. These include the slow food movement, slow parenting, slow travel, and even slow science. We propose the concept of slow search, where search engines use additional time to provide a higher quality search experience than is possible given conventional time constraints. While additional time can be used to identify particularly relevant results within the existing search engine framework, it can also be used to create new search artifacts and enable previously unimaginable user experiences. This talk will focus on how search engines can make use of additional time to employ a resource that is inherently slow: other people. Using crowdsourcing and friendsourcing, I will highlight opportunities for search systems to support new search experiences with high quality result content that takes time to identify.

Jaime Teevan is a Senior Researcher in the Context, Learning, and User Experience for Search (CLUES) Group at Microsoft Research, and an Affiliate Assistant Professor in the Information School at the University of Washington. She studies how people use digital information, particularly as related to their social and temporal context, and builds tools to help better support these information interactions. Jaime was named a Technology Review (TR35) 2009 Young Innovator for her research on personalized search. She co-authored the first book on collaborative Web search, and was Chair of the Web Search and Data Mining (WSDM) 2012 conference. Jaime also edited a book on Personal Information Management (PIM), edited a special issue of Communications of the ACM on the topic, and organized workshops on PIM and query log analysis. She has published numerous technical papers, including several best papers, and received a Ph.D. and S.M. from MIT and a B.S. in Computer Science from Yale University.

Sunday, October 6, 2013

Title: From the individual to the collective: Using the mental map as a tool for finding the city's "Public Image"
Speaker: Justin Cranshaw (CS, CMU)
Date: Wednesday, October 9
Time: 12-1pm
Room: GHC 6501 

All of us are uniquely imprinted by the places we go to and the experiences we have there. In a city, the total sum of these individual experiences of place contributes to the subjective and personal image we each hold in our minds of the city. This image, often called a mental map, shapes and colors how we perceive and interact with the people and places that surround us in an urban landscape. Viewed as a collection, the millions of individual mental maps of the city’s populous embody a wealth of stored local, cultural, and spatial knowledge that, if effectively harnessed, offers immense opportunities for improving how we live in and make sense of cities. 

In this talk, I will present recent research that uses social media as a window through which we can both peer into the individual mental maps of the populous and aggregate them into a collective “public image” of the city. I will discuss methods of algorithmically identifying certain aspects of such a public image, including how to identify organically defined city neighborhood boundaries. I will also discuss the design and initial exploration of a social website to encourage people to share mental maps by building their own personal city guides. Throughout I will touch on applications related to urban design, city governance, community development, local search, and more.

Justin Cranshaw is a School of Computer Science Ph.D. student at CMU in the Computation, Organizations and Society program. His research is in the emerging multi-disciplinary area of urban computing, which seeks to better understand and better engage with urban processes through new forms of ubiquitous and social computation. Justin is a 2013 Facebook Graduate Fellow in Human-Computer Interaction.