Coping With Plenitude: A Computational Approach to Selecting the Right Algorithm
Sociological Methods & Research · 2023-11 · 52 (4) · 1838-1882
DOI: 10.1177/00491241211031273 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sociological Methods & Research, online erschienen am 13.09.2021. Verfasst von Ramina Sotoudeh und 1 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 35 Literaturangaben.
Abstract (Originalsprache)
Sociologists increasingly face choices among competing algorithms that represent reasonable approaches to the same task, with little guidance in choosing among them. We develop a strategy that uses simulated data to identify the conditions under which different methods perform well and applies what is learned from the simulations to predict which method will perform best on never-before-seen empirical data sets. We apply this strategy to a class of methods that group respondents to attitude surveys according to whether they share construals of a given domain. This allows us to identify the relative strengths and weaknesses of the methods we consider, including relational class analysis, correlational class analysis, and eight other such variants. Results support the “no free lunch” view that researchers should abandon the quest for one best algorithm in favor of matching algorithms to kinds of data for which each is most appropriate and provide direction on how to do so.
Zitieren
APA
Sotoudeh, R., & DiMaggio, P. (2023). Coping With Plenitude: A Computational Approach to Selecting the Right Algorithm. Sociological Methods & Research, 52(4), 1838-1882. https://doi.org/10.1177/00491241211031273
Vancouver
Sotoudeh R, DiMaggio P. Coping With Plenitude: A Computational Approach to Selecting the Right Algorithm. Sociological Methods & Research. 2023;52(4):1838-1882. doi:10.1177/00491241211031273
BibTeX
@article{Sotoudeh2023,
author = {Sotoudeh, Ramina and DiMaggio, Paul},
title = {Coping With Plenitude: A Computational Approach to Selecting the Right Algorithm},
journal = {Sociological Methods & Research},
year = {2023},
volume = {52},
number = {4},
pages = {1838--1882},
doi = {10.1177/00491241211031273}
}
EUVIMED