
Recommendation as generalization: Using big data to evaluate cognitive models.
Author(s) -
David Bourgin,
Joshua T. Abbott,
Thomas L. Griffiths
Publication year - 2021
Publication title -
journal of experimental psychology. general
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 2.521
H-Index - 161
eISSN - 1939-2222
pISSN - 0096-3445
DOI - 10.1037/xge0000995
Subject(s) - generalization , computer science , psycinfo , construct (python library) , big data , machine learning , cognition , scale (ratio) , artificial intelligence , the internet , data science , recommender system , data mining , world wide web , psychology , programming language , mathematical analysis , physics , mathematics , medline , quantum mechanics , neuroscience , political science , law
The explosion of data generated during human interactions online presents an opportunity for psychologists to evaluate cognitive models outside the confines of the laboratory. Moreover, the size of these online data sets can allow researchers to construct far richer models than would be feasible with smaller in-lab behavioral data. In the current article, we illustrate this potential by evaluating 3 popular psychological models of generalization on 2 web-scale online data sets typically used to build automated recommendation systems. We show that each psychological model can be efficiently implemented at scale and in certain cases can capture trends in human judgments that standard recommendation systems from machine learning miss. We use these results to illustrate the opportunity Internet-scale data sets offer to psychologists and to underscore the importance of using insights from cognitive modeling to supplement the standard predictive-analytic approach taken by many existing machine learning approaches. (PsycInfo Database Record (c) 2020 APA, all rights reserved).