Keynote Speakers
Trust in Human-technology Teams: from Decision-support to Generative AI
Speaker: Shlomo Berkovsky, Macquarie University, Australia
Abstract: Human users are being increasingly supported by technology in a wide range of tasks and domains. Over the recent decades, the technologies have evolved dramatically: from simple decision-support tools, through recommender systems, to Generative AI. Nonetheless, the asymmetry of the human-technology teams remains stable; namely, the efficiency of the technology is generally superior to the human’s, while the decisions (in particular, mission-critical) are predominantly made by the human. This brings to the fore the need for accurate modeling and adaptive calibration of human trust in such collaborative teams, to ensure harmonious human-technology interaction and effective functioning of the team as a whole. This talk will overview the research into trust in human-technology teams, and discuss open challenges and future directions in the light of the recent advent and wide dissemination of Generative AI.
Bio: Shlomo Berkovsky is a computer scientist, with theoretical and applied expertise in areas related to human-centric application of AI. His original research areas include user modeling and personalized technologies and he currently leads the Clinical AI and Sensing Technologies stream at the Centre for Health Informatics at Macquarie University. The stream focuses on the use of AI methods to develop personalized predictions of diagnosis and care, and studies how sensors can be deployed to predict medical conditions, and how clinicians interact with health technologies. He has a sustained record of research leadership, evidenced by publications at top outlets, editorship of the ACM TiiS journal, conference best paper awards, keynote talks and tutorials, sustained research funding stream, and leading research programs.
On the Challenges of Podcast & Audiobook Search and Recommendation in Spotify
Speaker: Claudia Hauff
Abstract: Online music streaming is enjoying ever-growing popularity over the past decades, enabled by the abundance of music content in digital format and online streaming services. More and more streaming services are now expanding their catalogs and support music and podcasts as well as audiobooks on the same platform. This setup requires an extreme level of personalization to be able to recommend and search for content effectively. In this talk I will go over some of the challenges we encountered in that process.
Bio: Claudia Hauff is a Staff Research Scientist at Spotify, based in the Netherlands. She has a PhD (2010 from the University of Twente) in Information Retrieval and was a faculty member at TU Delft, for 10 years, leading a team of junior researchers on a wide range of IR topics including conversational search, collaborative search, search as learning and neural IR. Claudia has been at Spotify since 2021, working on a range of search and recommendation problems.
Human Control in Daily Environment Automations
Speaker: Fabio Paternò, CNR-ISTI, HIIS Laboratory, Italy
Abstract: How people interact with digital technologies is currently caught between the Internet of Things and Artificial Intelligence. Such technological trends provide great opportunities, new possibilities, but there are also risks and new problems. There can be intelligent services that eventually generate actions that do not match the real user needs. The introduced automations can generate unwanted effects. People may have difficulties understanding how to personalize the automatically generated automations. Thus, a fundamental challenge is how to provide tools that allow users to control and configure smart environments consisting of hundreds of interconnected devices, objects, and appliances. This means designing tools that allow people to obtain “humanations” (automations that users can understand and modify). This talk will discuss concepts and methods that can be useful to address the core challenges of human control over automations involving people, objects, devices, and intelligent services. The goal is to identify innovative approaches to support end users, even without programming experience, to understand, create or modify the automations in their daily environments, augmenting the human capacity to manage automations through effective interaction modalities, relevant analytics, understandable explanations, and intelligent recommendations. In this perspective, I will discuss how trigger-action programming can be a useful connection point between the wide variety of technologies and implementation languages considered and people without programming experience, and how it can be supported by recommender systems. However, it also presents nuances that may become apparent and critical in complex and realistic cases, generating undesired effects. Aspects that should be considered carefully include temporal aspects of triggers and actions, configuring smart environments with multiple active automations, and security and privacy issues. I will also discuss some experiences in application domains, such as the smart home, the opportunities provided by interaction modalities such as conversational agents and mobile augmented reality, how to provide explanations to make the behavior of the smart space more transparent, and possible future research directions.
Bio: Fabio Paternò is a Research Director at the C.N.R.-ISTI in Pisa, where he coordinates the Laboratory on Human Interfaces in Information Systems (HIIS). He teaches Interface Design and Usability Evaluation at the Humanistic Informatics course at the University of Pisa. His research focuses mainly on the field of human interaction with computers (HCI), in which he was one of the pioneers in Italy, with the aim of introducing computational support to improve usability, accessibility and user experience in various contexts. He has contributed significantly to areas such as model-based design of interactive applications, methods and tools for automatically supporting usability evaluation, accessibility, cross-device and migratory user interfaces, and end-user development. His research has always aimed at deepening and intertwining both theoretical and practical innovative aspects, with attention to possible social implications. Fabio is passionate about research that can have an impact that responds to the needs of society and is conducted in multidisciplinary environments. He has led numerous national and international interdisciplinary projects, always aiming to integrate different perspectives for effective solutions. His current research interests include interactive smart spaces, accessibility, human-robot interaction, and human-centered artificial intelligence. Most of his scientific activity took place at an international level. He has coordinated several European and also national projects. The results are reported in over three hundred publications in international conferences, books and journals. Fabio has held various leadership roles in major international conferences in the human-computer interaction area, and is currently co-chair of the ACM Intelligent User Interfaces 2025 conference. Among various awards, he has been named ACM Distinguished Scientist, IFIP Fellow, and member of the SIGCHI Academy.