An official website of the United States government
Health coaching helps patients achieve personalized and lifestyle-related goals, effectively managing chronic conditions and alleviating mental health issues. It is particularly beneficial, however cost-prohibitive, for low-socioeconomic status populations due to its highly personalized and labor-intensive nature. In this paper, we propose a neuro-symbolic goal summarizer to support health coaches in keeping track of the goals and a text-units-text dialogue generation model that converses with patients and helps them create and accomplish specific goals for physical activities. Our models outperform previous state-of-the-art while eliminating the need for predefined schema and corresponding annotation. We also propose a new health coaching dataset extending previous work and a metric to measure the unconventionality of the patient’s response based on data difficulty, facilitating potential coach alerts during deployment.
more »
« less
Summarizing Behavioral Change Goals from SMS Exchanges to Support Health Coaches
Regular physical activity is associated with a reduced risk of chronic diseases such as type 2 diabetes and improved mental well-being. Yet, more than half of the US population is insufficiently active. Health coaching has been successful in promoting healthy behaviors. In this paper, we present our work towards assisting health coaches by extracting the physical activity goal the user and coach negotiate via text messages. We show that information captured by dialogue acts can help to improve the goal extraction results. We employ both traditional and transformer-based machine learning models for dialogue acts prediction and find them statistically indistinguishable in performance on our health coaching dataset. Moreover, we discuss the feedback provided by the health coaches when evaluating the correctness of the extracted goal summaries. This work is a step towards building a virtual assistant health coach to promote a healthy lifestyle.
more »
« less
- Award ID(s):
- 1838770
- PAR ID:
- 10298068
- Date Published:
- Journal Name:
- Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue,
- Page Range / eLocation ID:
- 276-289
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Our goal is to develop and deploy a virtual assistant health coach that can help patients set realistic physical activity goals and live a more active lifestyle. Since there is no publicly shared dataset of health coaching dialogues, the first phase of our research focused on data collection. We hired a certified health coach and 28 patients to collect the first round of human-human health coaching interaction which took place via text messages. This resulted in 2853 messages. The data collection phase was followed by conversation analysis to gain insight into the way information exchange takes place between a health coach and a patient. This was formalized using two annotation schemas: one that focuses on the goals the patient is setting and another that models the higher-level structure of the interactions. In this paper, we discuss these schemas and briefly talk about their application for automatically extracting activity goals and annotating the second round of data, collected with different health coaches and patients. Given the resource-intensive nature of data annotation, successfully annotating a new dataset automatically is key to answer the need for high quality, large datasets.more » « less
-
Lack of physical activity has been linked to several chronic diseases. Health coaching is successful to help patients engage in healthier behaviors, but is resource intensive. Our goal is to develop a virtual health coach. In this paper, we discuss one component of our work, automatically summarizing goals set by patients during health coaching conversations that we collected and annotated. In turn, our goal summarization pipeline consists of a slot-value prediction model followed by a model that captures the higher-level conversation flow of the dialogues. We report a detailed evaluation that shows measures used for summarization such as BLEU and ROUGE, do not work well for our task.more » « less
-
Mathematics coaching differs significantly from mathematics teaching, and many coaches transi- tion to the role directly from teaching with limited opportunities to learn to work effectively with teachers. Although coach professional develop- ment can provide one source of support for coach- es’ learning, coaches might also benefit from close work with other accomplished facilitators of teach- ers’ learning, such as district mathematics leaders. This study analyzed interviews with 15 district mathematics leaders to understand whether and how they supported school-based mathematics coaches. We found 13 of 15 leaders worked closely with coaches to support them, and we identified seven ways they did so (e.g., classroom visits with coaches). Our findings have significance for re- search on district leadership and district leaders’ support for coaches.more » « less
-
This paper will share the development and refinement of a coaching program for high school computer science teachers focused on equity. Two midwest organizations developed coach professional development, selected teachers (coachees), and facilitated a coaching program during the academic year. Two cohorts of the coaching program, serving 20 coaches and 30 coachees, were offered over the course of two and a half years. Working as a researcher-practitioner partnership, the organizations used evaluation and research data to inform improvements during the program offerings and between the first and second cohort. The paper will describe the coaching professional development content and format, the coach professional learning community and activities, and the coach-coachee meetings and other supports and changes made.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
