Can Doğan, Marín Rebeca A, Georgiou Panayiotis G, Imel Zac E, Atkins David C, Narayanan Shrikanth S
Department of Computer Science, University of Southern California.
Department of Psychiatry and Behavioral Sciences, University of Washington.
J Couns Psychol. 2016 Apr;63(3):343-350. doi: 10.1037/cou0000111. Epub 2016 Jan 18.
The dissemination and evaluation of evidence-based behavioral treatments for substance abuse problems rely on the evaluation of counselor interventions. In Motivational Interviewing (MI), a treatment that directs the therapist to utilize a particular linguistic style, proficiency is assessed via behavioral coding-a time consuming, nontechnological approach. Natural language processing techniques have the potential to scale up the evaluation of behavioral treatments such as MI. We present a novel computational approach to assessing components of MI, focusing on 1 specific counselor behavior-reflections, which are believed to be a critical MI ingredient. Using 57 sessions from 3 MI clinical trials, we automatically detected counselor reflections in a maximum entropy Markov modeling framework using the raw linguistic data derived from session transcripts. We achieved 93% recall, 90% specificity, and 73% precision. Results provide insight into the linguistic information used by coders to make ratings and demonstrate the feasibility of new computational approaches to scaling up the evaluation of behavioral treatments.
针对药物滥用问题的循证行为治疗的传播与评估依赖于对咨询师干预措施的评估。在动机性访谈（MI）中，这种指导治疗师运用特定语言风格的治疗方法，其熟练度是通过行为编码来评估的——这是一种耗时且非技术性的方法。自然语言处理技术有潜力扩大对诸如动机性访谈等行为治疗的评估。我们提出了一种评估动机性访谈组成部分的新颖计算方法，重点关注一种特定的咨询师行为——回应，它被认为是动机性访谈的关键要素。利用来自3项动机性访谈临床试验的57个疗程，我们在最大熵马尔可夫建模框架中，使用从疗程记录中获取的原始语言数据自动检测咨询师的回应。我们实现了93%的召回率、90%的特异性和73%的精确率。研究结果为编码人员进行评分时所使用的语言信息提供了见解，并证明了新的计算方法在扩大行为治疗评估规模方面的可行性。
