标题：Exploring Factors Associated with Voucher Program for Speech Language Therapy for the Preschoolers of Parents with Communication Disorder using Weighted Random Forests
期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：5
页码：12-17
DOI：10.14569/IJACSA.2019.0100503
出版社：Science and Information Society (SAI)
摘要：It is necessary to identify the demand level of consumers and recognize the support target priority based on it in order to provide efficient services with a limited budget. This study provided baseline data for spreading the use of consumer-oriented voucher service by exploring factors associated with the demand of the Voucher Program for Speech Language Therapy for preschool children. This study were analyzed 212 guardians living with children (≤5 years old) who resided in Seoul from Aug 11 to Oct 9, 2015. The outcome variable was defined as the demand (i.e., required and not required) of the Voucher Program for Speech Language Therapy. The results of the developed prediction model were compared with the results of a decision tree based on classification and regression tree (CART). The prediction performance of the developed model was evaluated using a confusion matrix. Among the 212 subjects, 112 (52.8%) responded that the Voucher Program for Speech Language Therapy was necessary. The weighted random forest-based model predicted five variables (i.e., whether preschooler caregiving services were used or not, economic activity after childbirth, the awareness of Seoul’s welfare counselor operation, mean monthly living expenses, and whether welfare related information was obtained) as the variables associated with the demand of the Voucher Program for Speech Language Therapy and the accuracy was 72.1%. It is needed to develop systematic policies to expand consumer-oriented language therapy services based on the developed prediction model for the Voucher Program for Speech Language Therapy.
关键词：Weighted random forests; CART; speech language therapy; prediction model; voucher program
