Machine Learning to Detect Vocal Stereotypy - Improving Duration-Based Measures - Behavior Modification

Aug 3, 2026

Upload by Aurelia

Direct observation is a cornerstone of behavior science, yet it can be difficult to implement in real-world settings such as classrooms or homes. Machine learning offers a way to automate behavioral observation and measurement. Using previously published data, the study developed and tested models to automatically measure the duration of vocal stereotypy in eight children with autism. Models achieved high session-by-session correlations (≥0.90) and improved metrics compared with the original report.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages25

Reading Time1 h 3 min

AccessFree to download

Abstract

Introduction

Challenges of direct behavioral measurement

Use of machine learning in behavior science

Basics of supervised machine learning

Labeled datasets and generalization

Article Machine Learning to Detect Vocal Stereotypy: Improving DurationBased Measures Behavior Modification 1–25 © The Author(s) 2025 Article reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/01454455251380510](DOI: 10.1177/01454455251380510)[ ](DOI: 10.1177/01454455251380510)[journals.sagepub.com/home/bmo](journals.sagepub.com/home/bmo) Ali Reza Omrani 1,2, Marc J. Lanovaz3,4, and Davide Moroni 1 Abstract Direct observation is a process central to behavior science, but its implementation may be challenging in some contexts (e.g., classrooms, homes). One potential solution to improve the feasibility of conducting behavioral observation and measurement involves machine learning. Using previously published data, we developed and tested novel models to automatically measure the duration of vocal stereotypy in eight children with autism. In addition to accuracy and the kappa statistic, we examined session-by-session correlations between values measured by machine learning and those recorded by a human observer. Nearly all our models produced high correlations (i.e., .90 or more) and resulted in better metrics than those reported by the original study. The next step is for researchers to test the models on novel datasets to examine the generalizability of our findings. Keywords artificial intelligence, behavior detection, machine learning, measurement, neural network, vocal stereotypy 1 National Research Council of Italy, Pisa, Italy 2Università Campus Bio-Medico di Roma, Rome, Italy 3Université de Montréal, QC, Canada 4Institut Universitaire en Déficience Intellectuelle et en Trouble du Spectre de l’Autisme, Trois-Rivières, QC, Canada Corresponding Author: Marc J. Lanovaz, École de Psychoéducation, Université de Montréal, C. P. 6128, Succursale Centre-Ville, Montreal, QC H3C 3J7, Canada. [Email: marc.lanovaz@umontreal.ca](Email: marc.lanovaz@umontreal.ca) Introduction A thorough approach to the delivery of behavioral services involves repeated observation and measurement of behavior before, during, and following treatment (Kazdin, 2019). Although this approach to assessment ensures that the beneficiaries of behavioral services receive effective treatment, the repeated measurement of behavior using human observers remains a process that can be challenging in practice and in research. For example, parents, teachers, and even technicians may struggle to measure behavior consistently while simultaneously implementing interventions with high integrity (Bottiniet al., 2021) . Similarly, tasks such as tending to other children may interfere with data collection, especially for parents and teachers. For complex behavior, a more rigorous method involves recording the behavior on video for subsequent scoring or having an observer dedicated exclusively to data collection. However, using human observers to measure behavior from video recordings remains a costly endeavor as some additional time must be reserved for data collection (Dufour et al., 2020). Moreover, researchers must hire a second observer to make the results more believable by monitoring interobserver agreement, regardless of who is collecting the data (Hausmanet al., 2022) . To make data collection easier to implement and less costly, practitioners and researchers may use discontinuous measures, but these methods may produce less precise results (Falligant & Vetter, 2020; Leblanc et al., 2020) . Thus, collecting data presents many challenges to those who must carry it out on a daily basis. One potential solution to improve the feasibility of measuring behavior involves the use of artificial intelligence, or more specifically, machine learning. A subfield of artificial intelligence, machine learning trains computer algorithms to identify and use patterns from different sources of data, such as video recordings (Hu et al., 2023) . In supervised machine learn

FAQs

Why is direct observation challenging in some contexts?

Direct observation can be difficult to implement consistently in settings like classrooms and homes, where measurement must occur alongside intervention delivery and day-to-day responsibilities.

How does the study use machine learning to measure vocal stereotypy?

The models use previously published labeled data to automatically estimate the duration of vocal stereotypy, and the study evaluates performance using accuracy and kappa along with session-by-session correlations.

What do the results show about the models’ agreement with human observers?

Nearly all tested models produced high correlations between machine-measured and human-recorded values (about .90 or higher), along with better metrics than those reported in the original study.

Aug 3, 2026

Upload by Aurelia