Recommender systems for literature selection: A competition between decision making and memory models
Details
Serval ID
serval:BIB_D799AC238FF1
Type
Inproceedings: an article in a conference proceedings.
Collection
Publications
Institution
Title
Recommender systems for literature selection: A competition between decision making and memory models
Title of the conference
Proceedings of the 31st Annual Conference of the Cognitive Science Society
Publisher
Austin, TX: Cognitive Science Society
ISBN
978-1-61567-407-7
Publication state
Published
Issued date
2009
Peer-reviewed
Oui
Editor
Taatgen N. A., van Rijn H.
Pages
2914-2919
Language
english
Abstract
We examine the ability of five cognitive models to predict what publications scientists decide to read. The cognitive models are (i) the Publication Assistant, a literature recommender system that is based on a rational analysis of memory and the ACT-R cognitive architecture; (ii-iv) three simple decision heuristics, including two lexicographic ones called take-the-best and naïveLex, as well as unit-weight linear model, and (v) a more complex weighted-additive decision strategy called Franklin’s rule. In an experiment with scientists as participants, we pit these models against (vi) multiple regression. Among the cognitive models, take-the-best best predicts most scientists’ literature preferences best. Altogether, the study shows that individual differences in scientific literature selection may be accounted for by different decision-making strategies.
Keywords
Recommender system, ACT-R, Rational analysis, Simple heuristics, Take-the-best, Literature search
Create date
25/10/2011 15:41
Last modification date
20/08/2019 16:57