We look forward to welcoming you to the 12th RecSysNL meetup. Hosted by Elsevier, Amsterdam with two interesting talks, one from industry and one from academia.
Doors open at 18:00h, talks start at 18:30h.
Drinks and pizza will be provided.
"Mixed-initiative Recommender Systems: Towards a Next Generation of Recommender Systems through User Involvement"
Katrien Verbert, KU Leuven
Researchers have become more aware of the fact that effectiveness of recommender systems goes beyond recommendation accuracy. Thus, research on these human factors has gained increased interest, for instance by combining interactive visualization techniques with recommendation techniques to support transparency and controllability of the recommendation process. I will present work on interactive visualizations to enable end-users to interact with recommender systems. The objectives are: 1) to explain the rationale of recommendations as a basis to increase user trust and acceptance of recommendations, and 2) to incorporate user feedback and input into the recommendation process and to help steer it. In addition, I will present several user studies that investigate how such user controllability interacts with personal characteristics such as expertise and visual working memory.
Bio: Katrien Verbert is an Associate Professor at the HCI research group of KU Leuven. She obtained a doctoral degree in Computer Science in 2008 at KU Leuven, Belgium. She was a post-doctoral researcher of the Research Foundation – Flanders (FWO) at KU Leuven. She was an Assistant Professor at TU Eindhoven, the Netherlands and Vrije Universiteit Brussel, Belgium. Her research interests include visualisation techniques, recommender systems, visual analytics, and digital humanities. She has been involved in European projects on these topics, including the EU ROLE, STELLAR, STELA, ABLE, LALA and BigDataGrapes projects. She is also involved in the organisation of conferences and workshops.
"Using heterogenous data to recommend scientific articles and funding opportunities"
Finne Boonen and Minh Le, Elsevier
How do you know if a research article is relevant to you without reading it? What makes a grant a good match for your research needs? Oftentimes, the answer depends on a variety of factors: the objective quality of the paper, the match between a researcher’s interest and the topic of the paper, the career stage of a researcher compared to what is expected by a grant, current trends of the field and many other things. Elsevier, as a global information analytics company, drives solutions that approach such problems for the scientific community using various big data sources and technologies including machine learning. We, for instance, combine click logs, reading history, full-text, and citations using a mixture of recommender system techniques, including learning-to-rank, graph-based keyword extraction, and random walk. In this presentation, we will walk through the techniques we have used and their impact in improving researchers’ experience.
Finne has been a Data Scientist at Elsevier for the last three years and currently is working on the recommenders team. Prior to Elsevier, she held a variety of roles in different companies. Finne Boonen has an M.Sc. in ICT in Business from Leiden University and a bachelor’s in computer science from the Vrije Universiteit Brussel. Finne is interested in mastering the end-to-end development of data products.
Minh Le is a Data Scientist in the Recommenders team at Elsevier. He did a master in Cognitive Sciences and, next to his job at Elsevier, is finishing his PhD at the Vrije Universiteit Amsterdam specializing in Natural Language Processing. He is interested in applied research and general artificial intelligence.