Lora Aroyo is a Full Professor and head of the User-Centric Data Science Group (UCDS), Department of Computer ScienceDepartment of Computer Science, VU University Amsterdam. She is involved in several research projects focussed on understanding ambiguity and teaching machines to deal with ambiguity by applying techniques from crowdsourcing and human computation, data science, data quality assessment, and especially hybrid human-AI systems for text and video understanding. She has led major research projects in applying Semantic Web technologies for semantic search, recommendation systems, event-driven access to online multimedia collections, and through these has become a recognized leader in digital humanities, cultural heritage, and interactive TV.
Current projects include:
- ReTV: Re-purposing and re-using digital content across Smart TVs, Web and mobile applications, social media and other emerging platforms
- Capturing Bias: models for bias- and diversity-aware accuracy measures for reliable and explainable big data analysis of media collections
- CrowdTruth: human-assisted computing, specifically targeting workflows for the creation of ground truth data
- DIVE: Event-centric Exploration of Linked Heritage
Past projects include:
- Accurator: Annotating Fashion with Nichesourcing
- SealincMedia: Socially-enriched Access to Linked Cultural Media
- CLARIAH: Common Lab Research Infrastructure for the Arts and Humanities
- ControCurator: discover and understand controversial topics and events
- VISTA-TV: Combining LOD and behavioral information for TV analyses
- PrestoPrime: WAISDA? Crowdsourcing Game for Video Annotation
- NoTube: integration of Web and TV data with the help of semantics
- CHIP: Cultural Heritage Information Personalization
I am working with both IBM Research in NY and IBM CAS in Amsterdam on crowdsourcing ground truth data for the adaptation of the Watson system in medical domain [slides]:
- Dr. Watson: Gamification of Ground Truth Collection for Medical Texts
- Crowd-Watson: Framework for Crowdsourcing Ground Truth Data
- Crowd Truth: Metrics to Evaluate Crowdsourced Ground Truth Data
I am chief scientist at Tagasauris Inc., a New York-based startup that works on machine learning and human-assisted computing strategies to enrich video with precise, meaningful information about its content, and thus improve video search and discovery.
Check also the experimental research facilities in our VU INTERTAIN Lab.