Overview
The “Women in RecSys” tradition started in 2014 to foster diversity in the RecSys community. This year, we offer three ways for the community to unite and celebrate female role models in RecSys through physical and virtual networking events.
The well-established “Women in RecSys Breakfast” provides an opportunity for those attending in person and identifying as females to share the challenges and successes of working within our community and exchange experiences.
To further highlight the research contributions of women in the RecSys community, we will award up to six “Women in RecSys Journal Paper of the Year Awards.” This award will come with a free RecSys registration and the opportunity to present the respective journal paper at the main conference.
This year’s events are co-hosted by Ashmi Banerjee (Technical University of Munich, Germany), Li Chen (Hong Kong Baptist University, China), Karlijn Dinnissen (Utrecht University, Netherlands), and Elena V. Epure (Deezer, France). More details about each event can be found in the corresponding tabs.
When: September 8th (Monday), 2025, 10:00 am (CEST)
To participate in the Women in RecSys 2025 Online Keynote, please provide your contact information through this form, and we will send you the Zoom link.
Livestream URL here.
Dr. Pearl Pu
Senior Scientist and Maître d’Enseignement
École Polytechnique Fédérale de Lausanne (EPFL), Switzerland
Title
Building Empathetic AI: Reflections on Experimental Design and the Future of AI
Abstract
Empathy is at the heart of human relationships, enabling us to understand and share the emotions of others. But how can we translate such a deeply human trait into artificial intelligence? In this talk, I’ll begin by highlighting our contributions to this field, including user experiments that study emotional interactions, annotation studies refining emotional insights, and tools such as the MEED framework, PEACE model, and EDOS dataset, which have advanced empathetic response generation. Building on these foundations, I’ll explore the psychological and philosophical underpinnings of empathy, focusing on how theories such as simulation theory and theory of mind can inform the creation of AI systems capable of true emotional understanding. We’ll examine key constructs of empathy—affective, cognitive, and compassionate—and discuss how these elements can move AI beyond surface-level interactions. We describe a future where empathy in AI redefines human-technology relationships, bridging the gap between artificial and general intelligence and fostering collaboration, trust, and a more compassionate digital future.
About the Speaker
Pearl Pu leads the Human-Computer Interaction (HCI) Group in the School of Computer and Communication Sciences at EPFL (Swiss Federal Institute of Technology in Lausanne). Her research spans human-computer interaction, recommender systems, empathetic dialog generation using language models, and AI ethics.
She serves on the steering committee of the ACM Conference on Recommender Systems, is an ACM Distinguished Speaker, and sits on the boards of the UKRI CDT in AI for Medical Diagnosis and Care and the Harvard Data Science Review, among several other scientific journals. She has played key roles in the research community, including chairing major ACM conferences such as Electronic Commerce, Recommender Systems, and Adaptive Hypermedia, and serving on program committees for IJCAI, AAAI, The Web Conference, CHI, and many others.
Her honors include 14 Swiss National Science Foundation Research Awards, 3 Swiss Government Technology Innovation Awards, and a US NSF CAREER Award. A co-founder of three startups, she received the 2008 Rising Star Award from Sina.com and the 2014 Worldwide Innovation Challenge Award from the French president. She was named a EurAI Fellow in 2021.
Journal Paper of the Year Awards
This award will be given at the RecSys 2025 conference to women-authored journal papers that have distinguished themselves due to their innovativeness and scientific rigor.
The committee may select up to six winning journal papers depending on the number of nominated papers. The winning papers will each receive one free registration to RecSys 2025 to present their work during the conference and be acknowledged on the RecSys 2025 website.
We will have two submission categories: junior and senior. Individuals who have graduated with a Ph.D. within the past five years or are currently pursuing their Ph.D. will qualify as juniors, while those with more than five years of experience will be categorized as seniors.
An invited committee consisting of prominent researchers representing different areas of expertise will be established to judge the merits of nominated papers and make recommendations to the Women in RecSys committee.
The winner(s) must attend the RecSys 2025 conference.
Qualification/nomination details: The first or last author should be a woman researcher to qualify. The nominated journal paper must have a RecSys focus and must have been published between 30 April 2024 and 30 April 2025 (online pre-publication is acceptable). Each person can nominate only one paper. Self-nominations are allowed. If a paper qualifies for both the junior and the senior track, it can only be nominated once.
Submission details: The paper details and a PDF file of the article should be submitted by 30 April 2025 via EasyChair.
Nominations Submission Deadline: 30 April 2025 15 May 2025 deadline extended!
Notifications Deadline: 30 June 2025 (tentative)
