|
 Innovations in Verbal Behavior Analytics |
| Monday, May 27, 2024 |
| 3:00 PM–3:50 PM |
| Convention Center, 100 Level, 105 AB |
| Area: VBC/AUT; Domain: Applied Research |
| Chair: Robert C. Pennington (OCALI) |
| CE Instructor: Robert C. Pennington, Ph.D. |
| Abstract: Verbal behavior extends the speaker’s ability to operate on the environment by transcending the boundaries of mechanical reinforcement across time and space. Moreover, a fluent speaking repertoire presupposes the establishment of one’s own self identity. The use of modern technology has led to various judgmental aids that may facilitate behavior-analytic intervention for individuals with autism and related disorders, for whom verbal behavior is a core deficit. This symposium focuses on the future of verbal behavior research and intervention through the use of: (1) Telehealth technologies to enhance the outreach and dissemination of behavior-analytic intervention, (2) Novel ways of producing stimuli for the visual analysis of developing verbal behavior repertories, and (3) Artificial intelligence to facilitate discrimination training between children with autism who will and will not develop verbal behavior. Across three papers, we describe a series of technological innovations along with their implications for enhancing behavior-analytic intervention for individuals with autism. |
| Instruction Level: Intermediate |
| Keyword(s): artificial intelligence, parent training, verbal behavior, visual analysis |
| Target Audience: Participants should already be familiar with the elementary verbal operants described by Skinner (1957). |
| Learning Objectives: At the conclusion of the presentation, participants will be able to: (1) Identify features of effective telehealth parent training for families from culturally and linguistically diverse backgrounds; (2) Explain how different visual analyses serve as judgmental aids for making data-based decisions; (3) Describe the limitations of deep neural networks for making predictions about human behavior. |
| |
| Becoming a Verbal Behaviorist: Parent to Teacher |
| JANET SANCHEZ ENRIQUEZ (The University of North Carolina at Charlotte) |
| Abstract: Researchers and advocacy organizations in the field of ASD have increased their emphasis on evidence-based practices over the last two decades. Despite these recommendations and the extensive and readily accessible resources for determining best practices in ASD in recent years, difficulties remain for families to accurately identify and apply these research-based practices in natural contexts (Wilkinson, 2016). Parent-implemented interventions are a firmly grounded, evidence-based practice. Numerous studies have demonstrated the effectiveness of these interventions in improving communication, social interaction, and overall developmental outcomes in children with ASD. By equipping parents with the tools, strategies, and support they need, these interventions harness the power of the family unit to facilitate language-rich learning opportunities and connections. This study examines the effectiveness of a verbal behavior caregiver coaching package, Parent-Mediated Referent-Based Instruction (PM-RBI), on parents' fidelity in implementing these procedures and uses a phenomenological interview to reveal the lived experiences of two Mexican families participating in PM-RBI. Potential challenges, future suggestions, and implications for research and practice will be discussed. |
| |
| Seeing Verbal Behavior |
| ALONZO ALFREDO ANDREWS (The University of Texas at San Antonio) |
| Abstract: A distinguishing advantage of behavior analytic practice for clinicians and researchers is the ongoing graphic displaying of data for review, most generally involving line graphs. At a university-based behavior lab, designing interventions to develop balanced, primary verbal operant repertoires of children with autism spectrum disorder to promote verbal fluency, pie charts were used to present proportionality of topographically similar responses under different sources of control, i.e., the mand, echoic, tacts, and sequelic conditions, as revealed by a verbal operant experimental (VOX) analysis. Initially, before the current app, data sheets visually guided the systematic transfer of stimulus control across operants. Porter and Niksiar (2018) suggested that radar charts can be used to provide comparisons across mechanical properties, such as biological structures, and this multidimensional visual analysis is presently being employed for performance mapping of verbal behavior. This presentation will review a series of alternative graphic representations to direct efficient verbal behavior instruction. |
| |
| Predicting Echoic Control With Artificial Intelligence |
| Chris Ninness (Behavioral Software Systems), LEE MASON (Cook Children's Child Study Center) |
| Abstract: Among the heterogeneous population of individuals with autism, as many as ? are functionally nonverbal. The failure to develop functional language has been attributed to a paucity of resources for families combined with a lack of direct services, and a dearth of research on individuals with profound autism. However, even with early intensive behavioral intervention some children with autism will continue to present with significant language deficits. The ability to develop phrase speech - consisting of non-echoed, spontaneous utterances of three or more words - is a critical milestone of language development. For children with autism, who do not show typical language development, a growing body of literature supports the use of echoic prompts toward the development of other verbal operants. Consequently, the ability to discriminate between individuals that will and will not develop an echoic repertoire would be helpful for behavior analysts and other service providers. With the help of a deep neural network, we created a machine learning model to predict the extent to which children with autism will echo the verbal behavior of others. Here we present the results of our predictive model, implications for treatment, and questions about how artificial intelligence may shape the future of behavior-analytic intervention. |
|
| |