Professor Justin Zobel is Head of the University of Melbourne's Department of Computing & Information Systems. He received his PhD from the University of Melbourne and for many years was based at RMIT University, where he led the Search Engine group. In the research community, Professor Zobel is best known for his role in the development of algorithms for efficient web search. His current research areas include search, bioinformatics, fundamental algorithms and data structures, and compression. He is an author of three texts on postgraduate study and research methods (Writing for Computer Science, How To Write a Better Thesis, and How To Write A Better Minor Thesis) and is an associate editor of Information Processing & Management and Information Retrieval.
http://people.eng.unimelb.edu.au/jzobel/

AG 1, AG 2, AG 3, AG 4, AG 5, SWS, RG1, MMCI   Info

Public Audience

English

90 Minutes

Saarbrücken

Accurate measurement of experimental outcomes is a key element of science. We use measurement to make observations and to confirm or disprove hypotheses, and thus appropriate tools are required if scientific knowledge is to progress. However, even in fields with systems of measurement that are well-established, such as information retrieval (the discipline underpinning search engines), entire programs of research can be confounded by the limitations or misuse of measures. This talk reviews examples from IR of how poor measures and measurement processes have led to incorrect, ill-defined, or unjustified conclusions. These examples are a demonstration of the challenges of achieving robust outcomes in computing research.

Petra Schaaf

5000

--email hidden

passcode not visible

logged in users only