SCHEDULE
The workshop will take place online on March 14. All times below are in CET.
15:00-15:10 Welcome
15:10-15:40 Keynote #1 (Kirstine Wilfred Christensen, DBC)
15:40-15:50 Q&A + discussion
15:50-16:00 Break
16:00-16:30 Keynote #2 (Miriam Redi, Wikimedia Research)
16:30-16:40 Q&A + discussion
16:40-17:00 Break
17:00-17:20 Paper #1
17:20-17:40 Paper #2
17:40-18:10 Q&A + panel discussion
18:10-19:00 Closing discussion + draft statement
ACCEPTED PAPERS
- A Conversationalist Approach to Information Quality in Information Interaction and Retrieval. Frans van der Sluis (PDF)
- Visualisation to Aid Decision-Making for Time-Quality Tradeoffs. Ryan Burton and Kevyn Collins-Thompson (PDF)
KEYNOTE #1: Kirstine Wilfred Christensen (DBC)
Title: How to recommend a good book – in a library setting
Abstract: I will give a talk about how the premise for recommending fiction books in a physical library setting has changed and how addressing this issue from a digital perspective calls for a different kind of metadata than is traditionally assigned and used in library systems. I will present a project where we’ve worked with assigning more subjective and appealing metadata to books to improve the quality of the metadata that helps the user in being inspired to new reader experiences. I will present some of the issues with the way this metadata has been assigned and how this affects a recommender system.
Bio: Kirstine Wilfred Christensen is a metadata specialist working at DBC Digital A/S. She graduated from the Royal School of Library and Information Science and the IT-University of Copenhagen with a degree in Library and Information Science in 2008. She has worked 10 years as a programmer with data analysis, information retrieval and optimizing metadata for search in the library sector. In 2019 she was appointed Lead Developer and is currently working with the AI team at DBC Digital. A small but growing machine learning team that focuses on building recommenders and suggesters for use in library systems and related fields.
KEYNOTE #2: Miriam Redi (Wikimedia Research)
Title: The Science of Knowledge Equity – Research at Wikimedia
Abstract: Knowledge equity is a foundational principle of the Wikimedia movement. It drives efforts to break down the social, political, and technical barriers preventing people from accessing free knowledge. In this talk, we will see how computer vision and natural language processing can support knowledge equity and help improve the quality of content on Wikipedia. We will look at research that can help us identify, measure and bridge knowledge gaps in Wikimedia projects. We will dive into research that studies Wikipedia through the lenses of its readers, and technologies that bridge content gaps in Wikipedia and Wikidata with a machine-in-the-loop approach.
Bio: Miriam Redi is a Research Manager at the Wikimedia Foundation and Visiting Research Fellow at King’s College London. Formerly, she worked as a Research Scientist at Yahoo Labs in Barcelona and Nokia Bell Labs in Cambridge. She received her PhD from EURECOM, Sophia Antipolis. She conducts research in social multimedia computing, working on fair, interpretable, multimodal machine learning solutions to improve knowledge equity.