Tutorial: Applying Machine Learning in Behavioral Research
- PDF / 1,452,255 Bytes
- 27 Pages / 439.37 x 666.142 pts Page_size
- 84 Downloads / 229 Views
ORIGINAL RESEARCH
Tutorial: Applying Machine Learning in Behavioral Research Stéphanie Turgeon 1 & Marc J. Lanovaz 1,2 Accepted: 9 October 2020/ Published online: 10 November 2020 # Association for Behavior Analysis International 2020
Abstract Machine-learning algorithms hold promise for revolutionizing how educators and clinicians make decisions. However, researchers in behavior analysis have been slow to adopt this methodology to further develop their understanding of human behavior and improve the application of the science to problems of applied significance. One potential explanation for the scarcity of research is that machine learning is not typically taught as part of training programs in behavior analysis. This tutorial aims to address this barrier by promoting increased research using machine learning in behavior analysis. We present how to apply the random forest, support vector machine, stochastic gradient descent, and k-nearest neighbors algorithms on a small dataset to better identify parents of children with autism who would benefit from a behavior analytic interactive web training. These step-by-step applications should allow researchers to implement machine-learning algorithms with novel research questions and datasets. Keywords Artificial intelligence . Behavior analysis . Machine learning . Tutorial
Machine learning is a subfield of artificial intelligence that specializes in using data to make predictions or support decision making (Raschka & Mirjalili, 2019). One specific use of machine learning is solving classification problems. A classification problem occurs when trying to predict a categorical outcome (Bishop, 2006). Examples in behavior analysis include what is the function of a behavior (attention, escape, nonsocial, or tangible), whether a behavior is occurring at a given moment, whether an independent variable is changing a behavior or whether a treatment is likely to be This article was written in partial fulfillment of the requirements for the PhD degree in Psychoeducation at the Université de Montréal by Stéphanie Turgeon.
* Marc J. Lanovaz [email protected]
1
École de psychoéducation, Université de Montréal, C.P. 6128, succursale Centre-Ville, Montreal, QC H3C 3J7, Canada
2
Centre de recherche de l’Institut universitaire en santé mentale de Montréal, Montreal, QC, Canada
698
Perspectives on Behavior Science (2020) 43:697–723
effective for a given individual. Supervised machine learning is well suited to provide solutions to these types of classification problems and support decision making. In supervised machine learning, an algorithm (i.e., computerized instructions) trains a model using past observations to predict outcomes on new samples. In recent years, supervised machine-learning algorithms have been studied as useful aids to support decision making in multiple fields such as medicine, pharmacology, education, and health care (Coelho and Silveira, 2017; Miotto, Wang, Wang, Jiang, and Dudley, 2018). Some examples include identifying breast cancer (Rajaguru &
Data Loading...
