Software systems are becoming ever more intelligent and more useful, but the way we interact with these machines too often reveals that they don’t actually understand people. Knowledge Representation and Semantic Web focus on the scientific challenges involved in providing human knowledge in machine-readable form.However, we observe that various types of human knowledge cannot yet be captured by machines, especially when dealing with wide ranges of real-world tasks and contexts.
The key scientific challenge is to provide an approach to capturing human knowledge in a way that is scalable and adequate to real-world needs. Human Computation has begun to scientifically study how human intelligence at scale can be used to methodologically improve machine-based knowledge and data management.
Dr. Aroyo's research focuses on understanding human computation for improving how machine-based systems can acquire, capture and harness human knowledge and thus become even more intelligent.
This talk will focus on use cases related to smart culture, (e.g. enrichment of cultural heritage collections of artworks, videos, newspapers, etc.), and will show how the CrowdTruth framework (http://crowdtruth.org) facilitates data collection, processing and analytics of human computation knowledge.
Processing real-world data with the crowd leaves one thing absolutely clear - there is no single notion of truth, but rather a spectrum that has to account for context, opinions, perspectives and shades of grey. CrowdTruth is a new framework for processing of human semantics drawn more from the notion of consensus then from set theory.
4:00 - 5:00 pm: Talk
5:00 - 5:30 Breakout Rooms
About Dr. Lora Aroyo
Dr. Lora Aroyo is a research scientist at Google Research NY working on quality of data in human computation. Previously, she was professor of computer science at the VU University Amsterdam, and has led major research projects in semantic search, recommendation systems, and event-driven access to online multimedia collections.
She is also Chief of Science for a NY-based startup Tagasauris, and the president of the User Modeling community (UM Inc) which serves as a steering committee for the ACM Conference Series “User Modeling, Adaptation and Personalization” (UMAP) part of both SIGCHI and SIGWEB.
She is also member of the ACM SIGCHI conferences board, in her role as the UMAP steering committee chair. She headed the User-centric Data Science group at the Department of Computer Science, Vrije Universiteit Amsterdam, The Netherlands, and was member of the Amsterdam Data Science and the Network Institute.
Dr. Aroyo is involved in a number of research projects and in the organization of conferences, workshops and tutorials focussing on crowdsourcing and human computation, collecting data, data quality assessment, and especially hybrid human-AI systems for understand text, image and video.
Three notable current projects are: (1) CrowdTruth project “Harnessing Disagreement in Crowdsourcing for Ambiguity-aware Gold Standards”, (2) ReTV project “Re-inventing the TV for the Digital Age” and (3) CaptureBias project: “Diversity-aware Analysis of Bias in News Videos“.
She is an ACM member, and a four times holder of IBM Faculty Award for her work on CrowdTruth, Crowdsourcing ground truth data for adapting IBM Watson system to the medical domain & applying Crowdtruth for capturing ambiguity for the purpose of understanding misinformation.
Zoom Meeting - Details will be provided upon registration
(Membership: $30 Annually)