Tutorial: Applying Machine Learning in Behavioral Research

Turgeon, Stéphanie; Lanovaz, Marc J.

doi:10.1007/s40614-020-00270-y

Cited by 33 publications

(22 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have reviewed current meta-analytic methods and advocate for their increased use in applied behavior analysis research and literature reviews. The perspective advanced herein is consistent with a larger movement toward incorporating newer quantitative tools and methods in behavior science and behavior analysis in general (Caron, 2019;Craig & Fisher, 2019;DeHart & Kaplan, 2019;Elliffe & Elliffe, 2019;Falligant et al, 2020;Franck et al, 2019;Friedel et al, 2019;Gilroy et al, 2020;Greene et al, 2017;Jacobs, 2019;Kaplan et al, 2019;Killeen, 2019;Kyonka, 2019;Lanovaz et al, 2020;Levin et al, 2019;Riley et al, 2019;Turgeon & Lanovaz, 2020;Villarreal et al, 2019;Young, 2019). To borrow a quote attributed to Galileo, mathematics is the language of science.…”

Section: Discussionsupporting

confidence: 68%

Meta‐analyses and effect sizes in applied behavior analysis: A review and discussion

Dowdy¹,

Peltier

Tincani³

et al. 2021

J of App Behav Analysis

View full text Add to dashboard Cite

For more than four decades, researchers have used meta-analyses to synthesize data from multiple experimental studies often to draw conclusions that are not supported by individual studies. More recently, single-case experimental design (SCED) researchers have adopted meta-analysis techniques to answer research questions with data gleaned from SCED experiments. Metaanalyses enable researchers to answer questions regarding intervention efficacy, generality, and condition boundaries. Here we discuss meta-analysis techniques, the rationale for their adaptation with SCED studies, and current indices used to quantify the effect of SCED data in applied behavior analysis.

show abstract

Section: Discussionsupporting

confidence: 68%

Meta‐analyses and effect sizes in applied behavior analysis: A review and discussion

Dowdy¹,

Peltier

Tincani³

et al. 2021

J of App Behav Analysis

View full text Add to dashboard Cite

show abstract

“…In the support vector classifier, the algorithm separates the data in higher dimensions (using a hyperplane) to maximize the margin (i.e., separation) between the classes. For more details about these algorithms, we recommend that the reader consult a recent tutorial by Turgeon and Lanovaz (2020) written specifically for behavior analysts.…”

Section: Machine Learning Modelsmentioning

confidence: 99%

Machine Learning to Analyze Single-Case Graphs: A Comparison to Visual Inspection

Lanovaz¹,

Hranchuk²

2021

Preprint

View full text Add to dashboard Cite

Behavior analysts commonly use visual inspection to analyze single-case graphs, but studies on its reliability have produced mixed results. To examine this issue, we compared the Type I error rate and power of visual inspection with a novel approach, machine learning. Five expert visual raters analyzed 1,024 simulated AB graphs, which differed on number of points per phase, autocorrelation, trend, variability, and effect size. The ratings were compared to those obtained by the conservative dual-criteria method and two models derived from machine learning. On average, visual raters agreed with each other on only 73% of graphs. In contrast, both models derived from machine learning showed the best balance between Type I error rate and power while producing more consistent results across different graph characteristics. The results suggest that machine learning may support researchers and practitioners in making less error when analyzing single-case graphs, but further replications remain necessary.

show abstract

“…As a corollary, the fast-paced development of contemporary computational tools of fields as Artificial Intelligence has rapidly changed the landscape of some fields of behavioral science in the last decades, for example, ethology (Dell et al, 2014) and neuroscience (Datta et al, 2019;Mathis et al, 2019;Mathis & Mathis, 2020;Wiltschko et al, 2015). It is time the non-mediational, systematic, parametric (Henton & Iversen, 1975;Schoenfeld & Cole, 1972;Skinner, 1938) and ecological (Silva & Timberlake, 1997;Timberlake, 1994) approaches in the experimental analysis of behavior start to profit from these tools (Turgeon & Lanovaz, 2020).…”

Section: Discussionmentioning

confidence: 99%

Beyond single discrete responses: An integrative and multidimensional analysis of behavioral dynamics assisted by Machine Learning

León

Hernández

López

et al. 2021

Preprint

View full text Add to dashboard Cite

Behavioral systems, understanding it as an emergent system comprising the environment and organism subsystems, includes the spatial dynamics as a basic dimension in natural settings. Nevertheless, under the standard approaches in the experimental analysis of behavior that are based on the single response paradigm and the temporal distribution of these discrete responses, the continuous analysis of spatial behavioral-dynamics has been a scarcely studied field. The technological advancements in computer vision have opened new methodological perspectives for the continuous sensing of spatial behavior. Derived from them, recent studies suggest that there are multiple features embedded in the spatial dynamics of behavior, such as entropy, and that they are affected by programmed stimuli (e.g., schedules of reinforcement), at least, as much as features related to discrete responses. Despite the progress, the characterization of behavioral systems is still segmented, and integrated data analysis and representations between discrete responses and continuous spatial behavior, are exiguous. Machine Learning advancements, such as t-SNE, variable ranking, among others, provide invaluable tools to crystallize an integrated approach for the analysis and representation of multidimensional behavioral-data. Under this rational, the present work: 1) proposes a multidisciplinary approach for the integrative and multilevel analysis of behavioral systems; 2) shows behavioral aspects usually ignored under the standard approaches in the experimental analysis of behavior; and 3) provides sensitive behavioral measures, based on spatial dynamics, and useful data representations for the study of behavioral systems. In order to exemplify and evaluate our approach, the spatial-dynamics of behavior embedded in phenomena relevant to the behavioral science, namely water-seeking behavior and motivational operations, is examined, showing aspects of behavioral systems hidden until now. Keywords: Behavioral systems; spatial-behavioral dynamics; time-based schedules; water-seeking behavior; motivational operations; Machine Learning; t-SNE; entropy

show abstract

Tutorial: Applying Machine Learning in Behavioral Research

Cited by 33 publications

References 38 publications

Meta‐analyses and effect sizes in applied behavior analysis: A review and discussion

Meta‐analyses and effect sizes in applied behavior analysis: A review and discussion

Machine Learning to Analyze Single-Case Graphs: A Comparison to Visual Inspection

Beyond single discrete responses: An integrative and multidimensional analysis of behavioral dynamics assisted by Machine Learning

Contact Info

Product

Resources

About