I am a Full Professor in Explainable AI at Maastricht University, and a visiting Professor at TU Delft.
I am the PI of the Epsilon lab; it contributes to shaping the field of human-computer interaction in web information systems for decision support such as recommender systems, specifically on automatically generated explanations
and explanation interfaces (cartoon by Erwin Suvaal from CVIII ontwerpers).
As algorithmic decision-making becomes prevalent across many sectors it is important to help users understand why certain decisions are being proposed. Explanations are needed when there is a large knowledge gap between human and systems, or when joint understanding is only implicit. This type of joint understanding is becoming increasingly important for example when news providers, and social media systems; such as Twitter and Facebook; filter and rank the information that people see.
To link the mental models of both systems and people our work develops ways to supply users with a level of transparency and control that is meaningful and useful to them. We develop methods for generating and interpreting rich meta-data that helps bridge the gap between computational and human reasoning (e.g., for understanding subjective concepts such as diversity and credibility). We also develop a theoretical framework for generating better explanations (as both text and interactive explanation interfaces), which adapts to a user and their context. To better understand the conditions for explanation effectiveness, we look at when to explain
(e.g., surprising content, lean in/lean out, risk, complexity); and what to adapt to
(e.g., group dynamics, personal characteristics of a user).
explanations, natural language generation, human-computer interaction, personalization (recommender systems), intelligent user interfaces, diversity, filter bubbles, responsible data analytics.
9th of October
Currently hiring tenure trackers and postdocs to work on explainable AI!
15th of September
Congrats to Jody Liu and Tim Draws on their accepted paper at the ICDM'2020 SENTIRE workshop titled ``Helping users discover perspectives: Enhancing opinion mining with joint topic models''. This is a result of Jody's excellent Masters thesis!
15th of Sept.
Looking forward to giving a conference keynote at the International Conference on Research Challenges in Information Science (CORE rank: B)! Title: ``Explainable AI is not yet understandable AI''
26th of August
Congrats to Boning Gong on his masters work accepted at the CARS 2020 Workshop at ACM RecSys: ``Contextual Personalized Re-Ranking of Music Recommendations through Audio Features''. Joint work with Mesut Kaya.
26th of August
Congrats to Tim Draws for the first accepted paper of his PhD: ``Assessing Viewpoint Diversity in Search Results Using Ranking Fairness Metrics''. To appear at the BIAS 2020 Workshop at ECML PKDD. With Ujwal Gadiraju, Alessandro Bozzon, and Benjamin Timmermans
23rd of July
Full paper with Mesut Kaya and Derek Bridge titled ``Ensuring Fairness in Group Recommendations by Rank-Sensitive Balancing of Relevance'' has been accepted at Recsys'20 as a Long Paper
29th of May
Full paper accepted at ACM Hypertext 2020 titled: ``You do not decide for me! Evaluating Explainable Group Aggregation Strategies for Tourism''. With Shabnam Najafian, Oana Inel, Daniel Herzog, and Sihang Qiu.
20th of April
Our paper ``Motivated Numeracy and Active Reasoning in a Western European Sample" has been accepted to the journal of Behavioural Public Policy, with Paul Connor, Emily Sullivan, and Mark Alfano (to appear).
9th of April
Our paper ``On the merits and pitfalls of introducing a digital platform to aid conservation management: Volunteer data submission and the mediating role of volunteer coordinators'' was accepted to the Journal of Enviornmental Management ( IF = 4.865, currently open access
), with Koen Arts et al.
30th of March
Our paper ``Eliciting User Preferences for Personalized Explanations for Video Summaries'' with Oana Inel and Lora Aroyo has been accepted at UMAP 2020!
30th of March
New report of Dagstuhl Perspectives Workshop Diversity, Fairness, and Data-Driven Personalization in (News) Recommender Systems
, full manifesto to follow.
30th of March
Job opening: NLP post-doc position on linguistic measures of diversity of viewpoint on Twitter (email for informal inquiries)
23rd of January
Congratulations to PhD candidate Shabnam Najafian for her accepted student consortium paper, and poster paper, at IUI'2020!