Masters students: If you are interested in doing a project in epsilon, please have a look at the possible projects in the WIS group. You could also have a look at my recent publications, as many of these papers are published with students. You can also see the theses I have examined in the past.
I am an Assistant Professor and Delft Technology Fellow in the Web Information Systems group, Faculty of Electrical Engineering, Mathematics and Computer Science 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).

cartoon

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).

Relevant keywords: explanations, natural language generation, human-computer interaction, personalization (recommender systems), intelligent user interfaces, diversity, filter bubbles, responsible data analytics.


Track record: over 60 peer reviewed papers. H-index: 17, most cited article >400 citations, >1900 total (according to Google scholar on the 30/01/20), on the topic of personalized information presentation in different application areas. I have been a member of the ACM since January 2014.

Teaching: Co-teaching one bachelor elective course: Human Computer Interaction with Myrthe Tielman, and co-teaching two Master courses: Information Retrieval with Claudia Hauff; and Crowd Computing with Alessandro Bozzon.

Academic service: I also review for many leading conferences and journals in human-computer interaction (CHI), artificial intelligence (IJCAI-ECAI), and personalization (TiiS). I serve in organizational roles for international conferences and workshops. In addition, I examine PhD dissertations, and review both national and international grant proposals. Further, I contribute to strategic and international scientific discussions relating to responsible data science such as:
  • (Co-organizer) Dagstuhl Seminar: Frontiers of Information Access Experimentation for Research and Education (planned 2021)
  • Dagstuhl Perspectives workshop: Diversity, Fairness, and Data-Driven Personalization in (News) Recommender System (2019)
  • Dagstuhl Perspectives workshop: Performance Modeling and Prediction in IR/NLP/Recsys (2018)
  • ZiF workshop on Explanation and Understanding in the Age of Algorithms (2018)

News:

2020

30th of March Our paper ``Eliciting User Preferences for Personalized Explanations for Video Summaries'' with Oana Intel 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)

30th of January Invited to give a conference keynote at the International Conference on Research Challenges in Information Science (CORE rank: B), rescheduled for September! Title: ``Explainable AI is not yet understandable AI''

23rd of January Congratulations to PhD candidate Shabnam Najafian for her accepted student consortium paper, and poster paper, at IUI'2020!