A Change Talk Model for Abstinence Based on Web-Based Anonymous Gambler Chat Meeting Data by Using an Automatic Change Talk Classifier: Development Study (Preprint)

• DOI: 10.2196/preprints.24088
• Publication Date: 2020-09-09T15:55:30Z
• Authors: Kenji Yokotani
• Keywords: 03 medical and health sciences; 0302 clinical medicine; 12. Responsible consumption

<sec> <title>BACKGROUND</title> Change and sustain talks (negative positive comments) on gambling have been relevant for determining gamblers’ outcomes but they not used to clarify the abstinence process in anonymous gambler meetings. </sec> <title>OBJECTIVE</title> The aim of this study was develop a change talk model based data extracted from web-based chat meetings by using an automatic classifier. <title>METHODS</title> This registry internet. author accessed Japan sampled 1.63 million utterances (two-sentence texts) 267 abstinent gamblers who remained at least three years 1625 nonabstinent gamblers. classifier automatically classified into talks. <title>RESULTS</title> Abstinent showed higher proportions lower probability compared with abstinence, involving talks, through use support vector machine radial basis kernel function. also indicated individual evaluation scores ideal proportion all participants according their previous utterances. <title>CONCLUSIONS</title> Abstinence likelihood among can be increased providing personalized values indicating optimal Moreover, may help prevent severe mental, social, financial problems caused disorder.