22 September 2017 - Leif Azzopardi: Seminar
Usor Economicus - Modelling Search Interaction using Economics
In this talk, I will describe my efforts in trying to understanding how people interact with search systems and how this has resulted in the development of several economics model of search and search behaviour. These models assume an Economic User (i.e. Usor Economicus), one who inevitably does that by which s/he may obtain the greatest amount of information and knowledge, with the smallest quantity of effort. In this talk, I will first provide an overview of the typically Interactive Information Retrieval process. Then I will introduce an economic model of search, which is derived from production theory. I will show how the model enables us to generate compelling, intuitive and crucially testable hypotheses about the search behaviour of users. They provide insights into how we can manipulate the system and the interface in order to change the behaviour of users. In a series of user experiments, I show how well the models characterise, predict and explain observed behaviours (and where they fall down). I believe the models, not only, provide a concise and compact representation of search and search behaviour, but also provides a strong theoretical basis for future research into Interactive Information Retrieval. Furthermore, these economic models can be developed for all sorts of human computer interactions, and so are likely to provide many more insights into how people use systems and how we should design such systems.
This talk is based on the following papers:
"The economics of interaction", ACM SIGIR 2011, see: http://dl.acm.org/citation.cfm?id=2009923
"How query cost affects search behavior" with Diane Kelly & Kathy Brennan at ACM SIGIR 2013, see: http://dl.acm.org/citation.cfm?id=2484049
"Modeling Interaction with Economic Models of Search" which received an Honorable Mention at ACM SIGIR 2014, see: http://dl.acm.org/citation.cfm?id=2609574
"An analysis of Theories of search and search behaviour" with Guido Zuccon at ACM ICTIR 2015, see: http://dl.acm.org/citation.cfm?id=2809447
"An analysis of the Cost and Benefit of Search Interactions" with Guido Zuccon, at ACM ICTIR 2016, see http://dl.acm.org/citation.cfm?id=2970412
Dr. Leif Azzopardi is a Chancellor's Fellow in Data Science and Associate Professor at the University of Strathclyde, Glasgow within Department of
Computer and Information Science. He leads the Interactive Information Retrieval group within Strathclyde's iSchool. His research focuses on examining the influence and impact of search technology on people and society and is heavily underpinned by theory. He has made numerous contributions in: (i) the development of statistical language models for document, sentence, expert retrieval, (ii) the simulation and evaluation of users and their interactions, (iii) the analysis of systems and retrieval bias using retrievability theory and the (iv) the formalisation of search and search behaviour using economic theory. He has given numerous keynotes, invited talks and tutorials through out the world on retrievability, search economics, and simulation. He is co-author of the Tango with Django (www.tangowithdjango.com<http://www.tangowithdjango.com>) which has seen over 1.5 million visitors. And more recently he has been co-developing resources for IR research with Lucene (www.github.com/lucene4ir/<http://www.github.com/lucene4ir/>), while co-creating evaluation resources for Technology Assisted Reviews as part of the CLEF eHealth Track 2017.
He is an honorary lecturer at the University of Glasgow (where he was previously a Senior Lecturer) and an honorary Adjunct Associate Professor at Queensland University of Technology. He received his Ph.D. in Computing Science from the University of Paisley in 2006, under the supervision of Prof. Mark Girolami and Prof. Keith van Rijsbergen. Prior to that he received a First Class Honours Degree in Information Science from the University of Newcastle, Australia, 2001.