Affiliation:
1. The University of Melbourne, Parkville, Victoria, Australia
Abstract
The discipline of information retrieval (IR) has a long history of examination of how best to measure performance. In particular, there is an extensive literature on the practice of assessing retrieval systems using batch experiments based on collections and relevance judgements. However, this literature has only rarely considered an underlying principle: that measured scores are inherently incomplete as a representation of human activity, that is, there is an innate gap between measured scores and the desired goal of human satisfaction. There are separate challenges such as poor experimental practices or the shortcomings of specific measures, but the issue considered here is more fundamental - straightforwardly, in batch experiments the human-machine gap cannot be closed. In other disciplines, the issue of the gap is well recognised and has been the subject of observations that provide valuable perspectives on the behaviour and effects of measures and the ways in which they can lead to unintended consequences, notably Goodhart's law and the Lucas critique. Here I describe these observations and argue that there is evidence that they apply to IR, thus showing that blind pursuit of performance gains based on optimisation of scores, and analysis based solely on aggregated measurements, can lead to misleading and unreliable outcomes.
Publisher
Association for Computing Machinery (ACM)
Subject
Hardware and Architecture,Management Information Systems
Reference46 articles.
1. Improvements that don't add up
2. User Variability and IR System Evaluation
3. F. G. Boudinot and J. Wilson . Does a proxy measure up? A framework to assess and convey proxy reliability. Climate Past, 16 , 2020 . doi: 0.5194/cp-16-1807-2020. F. G. Boudinot and J. Wilson. Does a proxy measure up? A framework to assess and convey proxy reliability. Climate Past, 16, 2020. doi: 0.5194/cp-16-1807-2020.
4. Using massive online choice experiments to measure changes in well-being
Cited by
3 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Simulating Users in Interactive Web Table Retrieval;Proceedings of the 32nd ACM International Conference on Information and Knowledge Management;2023-10-21
2. The Information Retrieval Experiment Platform;Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval;2023-07-18
3. Report on the Dagstuhl Seminar on Frontiers of Information Access Experimentation for Research and Education;ACM SIGIR Forum;2023-06