Offline evaluation of rankings is a core problem in the field of Information Retrieval (IR). Many evaluation metrics have been defined to evaluate the effectiveness of IR systems, not only for ad-hoc retrieval, but also for more complex scenarios which may require diversifying the exposure of different aspects  (e.g., multiple facets of a given information need) or viewpoints (e.g., arguments in favor or against a particular controversial topic). A question that is not trivial to answer is: which evaluation metric should we use? In this talk, I will revisit some ideas from search result diversification and fairness-aware ranking to discuss differences and similarities between these two scenarios by characterizing effectiveness evaluation metrics and understand their suitability for these particular scenarios and others.



Dr. Damiano Spina is a Senior Lecturer and a DECRA Research Fellow at RMIT University, School of Computing Technologies.

Dr. Spina is a member of the RMIT Research Centre for Information Discovery and Data Analytics (CIDDA), an Associate Investigator at the ARC Centre of Excellence for Automated Decision-Making and Society (ADM+S), and a research collaborator with RMIT FactLab. His research expertise is in the field of Information Retrieval (IR) and Text Analytics. In particular, his research focuses on interactive information retrieval and evaluation of information access systems.

Dr. Spina completed his PhD in Computer Science in 2014 (UNED, Spain). He has published more than 40 peer-reviewed scientific publications, including papers at conferences such as SIGIR, ECIR, CIKM, and CHIIR, as well as journal articles in IP&M, TOIS, and JASIST. He serves as editorial board member for IP&M and is an active Program Committee member of various IR and Text Analytics conferences. He is the recipient of the 2021 RMIT Award for Research Impact (Technology).





Assoc. Prof. Gianluca Demartini

This session will be conducted in hybrid mode.
UQ St Lucia Campus venue: 46-442 or via Zoom: https://uqz.zoom.us/j/89362232168

About Data Science Seminar

This seminar series will be run as weekly sessions and is hosted by ITEE Data Science.