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.

As such 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: 16, most cited article ~340 citations, >1600 total (according to Google scholar on the 16/06/19), 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 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 initiatives and events focused on responsible data science such as:
  • Serving on the Management team for Delft Design for Values
  • Organizing seminars within Delft Data Science on Trusted Data Analytics.
  • Attending strategic and international scientific discussions:
    • Dagstuhl Perspectives workshops on Diversity, Fairness, and Data-Driven Personalization in (News) Recommender System (2019, planned)
    • Dagstuhl Perspectives workshops on Performance Modeling and Prediction in IR/NLP/Recsys (2018)
    • ZiF workshop on Explanation and Understanding in the Age of Algorithms (2018)

News:

2019

14th of June Job opening: NLP post-doc position on linguistic measures of diversity on Twitter.

14th of June Joined the User Modeling and User-Adapted Interaction (UMUAI) editorial board, which is the main Journal of Personalization Research! (ISI@5 years 2015 3.234)

7th of June Excited to give a keynote at the FairUMAP workshop titled: ``Toward Measuring Viewpoint Diversity in News Consumption''

7th of June Paper accepted to the User Modeling and User-Adapted Interaction (Journal): ``Effects of Personal Characteristics in Control-oriented User Interfaces for Music Recommender Systems'', with Yucheng Jin, Nyi Nyi Htun, and Katrien Verbert.

7th of June Paper accepted to ROME workshop at SIGIR: Annotating Credibility: Identifying and Mitigating Bias in Credibility Datasets. With Dimitrios Bountouridis, Mykola Makhortykh, Emily Sullivan, Jaron Harambam, and Claudia Hauff.

10th of April Paper accepted to ExHum workshop at UMAP: Reading News with a Purpose: Explaining User Profiles for Self-Actualization. This is a result of our collaboration with FDMediagroep at the ICT with Industry event.

27th of March PhD studentship opening on "Representing diverse views for polarized topics online". This is a project with IBM Benelux, funded by CLICK_NL. Feel free to ping me with informal inquiries. (Position now FILLED, but new openings coming up!)

14th of March Accepted full paper to the UMAP Conference: ContextPlay: User Control for Context-Aware Music Recommendation. With Yucheng Jin, Nyi Nyi Htun, and Katrien Verbert.

17th of January. Accepted journal submission in UMUAI: A Methodology for Creating and Validating Psychological Stories for Conveying and Measuring Psychological Traits. With Kirsten A. Smith, Matt Dennis, and Judith Masthoff.

17th of January. Looking forward to the ICT with Industry workshop, and working with FD Mediagroep on Explanations for News.


2018

22nd of October Full paper accepted to FAT* conference. SIREN: A Simulation Framework for Understanding the Effects of Recommender Systems in Online News Environments. Lead by Dimitrios Bountouridis et al.

4th of September. Journal paper accepted to IEEE Transactions on Software Engineering (TSE) journal: "Does Reviewer Recommendation Help Developers?". With Vladimir Kovalenko, Evgeny Pasynkov, Christian Bird, and Alberto Bacchelli

4th of September. Three papers accepted to the IntRS workshop, and 1 paper accepted to the RecTour workshop at ACM Recsys'18.

30th of July. It's official! We are one of two teams working with Twitter on measuring conversational health (2/230 proposals accepted) . Official Twitter announcement . Official TU Delft announcement .

12th of July. Full paper accepted to Recsys with Yucheng Jin and Katrien Verbert: Effects of Personal Characteristics on Music Recommender Systems with Different Levels of Controllability (17% acceptance rate)

27th of June. Great turn out (~100 registrations) for our Delft Data Science event on Trusted Data Analytics. Speaker profiles and presentations here.

18th of June. Paper accepted to SIGIR workshop on ExplainAble Recommendation and Search (EARS): Explaining Credibility in News Articles using Cross-Referencing, with Dimitrios Bountouridis, Monica Marrero, and Claudia Hauff.

4th of June. Joined the Delft Design for Values Management team. DDFV's mission is to bring together, integrate, and expand existing practices and expertise at Delft University of Technology in the field of design for values. In this role, I am excited to share lessons learned within design for Responsible Data Science, and learn from colleagues about best practices in other departments at our university.

18th of May. Congratulations to PhD candidate Shabnam Najafian for her paper accepted to UMAP Late breaking results: Generating Consensus Explanations for Group Recommendations.

16th of May. Paper accepted to UMAP workshop on Fairness in User Modeling, Adaptation and Personalization: Same, Same, but Different: Algorithmic Diversification of Viewpoints in News, with Emily Sullivan, Dror Guldin, Sihang Qiu, Daan Odjik, Reza Aditya Permadi, and Andreas Christian Pangaribuan

19th of April. Summary of The Dagstuhl Perspectives Workshop on Performance Modeling and Prediction, with Ferro et al, accepted for publication in the SIGIR Forum (June)!

13th of April. Effects of Individual Traits on Diversity-aware Music Recommender User Interfaces, full paper accepted to UMAP. With Yucheng Jin and Katrien Verbert