COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Social Psychology Seminar Series (SPSS) > Designing for Collaborative Data Analysis, a Crime Solving story
Designing for Collaborative Data Analysis, a Crime Solving storyAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Melisa B. This talk has been canceled/deleted My research vision is to enable expert and non-experts to successfully make sense of complex world problems. As a Human-Computer Interaction researcher, I iteratively focus on studying how sensemaking is performed to identify challenges in collaborative data analytics, design tools using computational techniques that overcome these challenges and evaluate my designs using human participants to inform subsequent designs. Solving crimes correctly is one such critical and life-altering problem. National Registry at the University of Michigan points out that almost 175 wrongfully incriminated folks were exonerated after having spent a non-trivial amount of their life in prison for crimes they did not commit in 2016 alone. This is 4X the number 10 years ago and continues an upward trend. During my work, I have discovered that sharing information socially, succumbing to cognitive biases, and lack of support afforded by changing interaction paradigms as key challenges in collaborative data analytics. Subsequently, I have iteratively developed multiple tools, including SAVANT REFLECTIVA , CROWDS4ANALYTICS, TEMPORA , and RAMPARTS to overcome these challenges. My approach establishes a research framework for creating rich collaborative data analytic systems by: (1) utilizing human generated analytic artifacts to inform and design the interactions (2) leveraging “off-the-shelf” natural language processing, sensors and crowds creatively to design intelligent data analytic tools, and (3) evaluating the effect of these designs in controlled settings to identify the cost vs. benefit of each design decision. Tesh (Nitesh) Goyal is a researcher at Google, where his collaborative sensemaking research has been used in Google Maps and Web experiences. Tesh’s research develops design approaches to build novel data analytics tools that enhance information sharing, reduce biases using visualizations, minimize distractions using physiological data, and support collaborative problem-solving with crowds. His research has also contributed to the theory of Sensemaking by inventing Sensemaking Translucence as a design metaphor for a mirror that enables self-reflection. He received his MSc in Computer Science from University of California, Berkeley and RWTH Aachen under Prof. John Canny’s advice, prior to receiving his PhD from Cornell University in Information Science where he was advised by Prof. Susan R. Fussell. His research has been supported by German Govt. Fellowship, National Science Foundation, and MacArthur Genius Grant. Frequently collaborating with industry (Google Research, Yahoo Labs, HP Labs, Bloomberg Labs), he has published 10 first-author papers in top-tier HCI conferences and journals (CHI, CSCW , JASIST, ICTD , ICIC and Ubicomp/IMWUT) and has received two best paper honorable nomination awards. This talk is part of the Social Psychology Seminar Series (SPSS) series. This talk is included in these lists:This talk is not included in any other list Note that ex-directory lists are not shown. |
Other listsScience non-Fiction & the Bottom Billion: Evolving Frameworks for a fairer Future Type the title of a new list here ইন্টারনেট মানেই বিশ্বাসযোগ্য নয়Other talksDecision making in the face of uncertainty: improving the evidence base to support landscape decisions Understanding Land Use Change and Supporting Landscape Decision Making Approaches to Modelling Urban Land Use Change in Response to Residential and other Pressures Finite Element Exterior Calculus - 2 Scaling populations and communities Jennifer Lee: A personal selection |