Publication Date

2017

Document Type

Thesis

Committee Members

Paul Bender (Committee Member), Dean A. Bricker (Committee Member), Yong Pei (Advisor), Mateen M. Rizki (Committee Member)

Degree Name

Master of Science (MS)

Abstract

Motivational Interviewing (MI) has been proved to be an effective Screening, Brief Intervention, and Referral to Treatment (SBIRT) technique. It is an evidence-based practice used to identify, reduce, and prevent problematic use, abuse, and dependence on alcohol and illicit drugs. It emphasizes on patient-centered counseling approach that can help resolve their ambivalence through a non-confrontational, goal-oriented style for eliciting behavior change from the patient, almost like patients talk themselves into change. This approach provokes less resistance and stimulates the progress of patients at their own pace towards deciding about planning, making and sustaining positive behavioral change. Thus, training medical professionals to provide supportive care and adapt MI techniques plays a major role in not only improving their skills but also has follow-on impacts for patients to a large extent. The training, such as workshops (Role-plays and videos), help professionals learn about MI to improve the quality and effectiveness of counseling and consultations with patients. In this thesis research, we have developed an android based performance assessment system to assist the MI training by providing objective assessment and instantaneous feedback to the trainee about his or her performance and progress through the training sessions. It also provides the trainers with evidence to develop individually customized training sessions to address the specific needs of each trainee in order to achieve improved outcome from the training. In our prototype design, we have explored the use of automatic speech recognition, grammar-based MI analysis in a mobile/cloud hybrid solution. Particularly, we have extended the Android’s voice command interface to support the automatic scripting of a long-time conversation. Furthermore, we have assembled a user-friendly system which only uses smartphone/tablet and can be easily used by professionals without hassle. Through our experimental studies, our system has demonstrated sufficient accuracy and robustness to distinct between a good and bad interview, and has potential to grow into an effective assessment tool for MI training and practice.

Page Count

107

Department or Program

Department of Computer Science and Engineering

Year Degree Awarded

2017

Download


Share

COinS