Human-Computer Interaction Institute
School of Computer Science
Carnegie Mellon University
Combining human and machine intelligence
to scale up sensemaking and innovation
google scholar : cv
We spend 1 trillion hours a year making sense of the web -- about two Wikipedias worth of work each hour. At Carnegie Mellon's Knowledge Accelerator we build systems to help individuals collect, organize, and make decisions with online information, and to help others with similar needs build on their work instead of starting from scratch.
We rely on reviews to make good decisions but they can be overwhelming to read through. Skeema pulls reviews together so you can figure out how each option stacks up on the criteria you care about in ~90% less time.
Bento is a new paradigm for web search on mobile devices that replaces conventional tabbed browsing with dynamic projects and workspaces that solve tab overload.
Developers spend significant time exploring tradeoffs between different solutions. Unakite is a Chrome extension that reduces the cost of capturing tradeoff information by 45% and speeds up subsequent developers' understanding by ~3x.
SearchLens lets users build up a collection of composable and reusable "Lenses" that search reviews for their different latent interests and generate personalized interfaces with visual explanations that promote transparency and enable in-depth exploration.
Stitches together information across many pages to generate articles rated better than top 10 Google results. Demonstrates how a crowdsourcing system can scaffold a big picture view even when each individuals only sees a small part of the whole
Some of the greatest innovations in history have been made by finding analogical inspirations across distant fields. However, the explosion of information means that today it is difficult to explore a single field, let alone find useful connections across fields. We use crowdsourcing and AI to accelerate analogical innovation in science, technology, and design.
Summarizes multiple threads of our work using crowdsourcing and AI to scale up the search for distant inspirations that can increase creative innovation
Introduces an approach to using RNNs to extract vector representations of purposes and mechanisms of products at scale, enabling finding analogical inspirations that increase creative ideation by ~3x
Decomposes analogical innovation into parts that can be distributed across multiple minds to make idea generation more efficient and effective.
How can we use crowdsourcing to accomplish complex and creative tasks such as writing, synthesizing knowledge, or journalism?
The Future of Crowd Work
Crowdsourcing User Studies with Mechanical Turk
How can we create sociotechnical architectures that motivate and coordinate thousands of individuals doing complex work?
Harnessing the Wisdom of Crowds in Wikipedia
The Polymath Project
Collaborative Problem Solving on MathOverflow
He says, She says: Conflict and Coordination in Wikipedia
Can You Ever Trust a Wiki?
Effectiveness of Shared Leadership in Online Communities
Your Process is Showing
A Market in Your Social Network
The Cognitive Atlas
Power of the Few vs. Wisdom of the Crowd
Aniket "Niki" Kittur is a Professor in the Human-Computer Interaction Institute at Carnegie Mellon University. His research on crowd-augmented cognition looks at how we can augment the human intellect using crowds and computation. He has authored and co-authored more than 70 peer-reviewed papers, 15 of which have received best paper awards or honorable mentions. Dr. Kittur is a Kavli fellow, has received an NSF CAREER award, the Allen Newell Award for Research Excellence, major research grants from NSF, NIH, Google, and Microsoft, and his work has been reported in venues including Nature News, The Economist, The Wall Street Journal, NPR, Slashdot, and the Chronicle of Higher Education. He received a BA in Psychology and Computer Science at Princeton, and a PhD in Cognitive Psychology from UCLA.
This web page was made with Mobirise