In this paper, we study the effect of commonsense and domain knowledge while generating responses in counseling conversations using retrieval and generative methods for knowledge integration. We propose a pipeline that collects domain knowledge through web mining, and show that retrieval from both domain-specific and commonsense knowledge bases improves the quality of generated responses. We also present a model that incorporates knowledge generated by COMET using soft positional encoding and masked self-attention.We show that both retrieved and COMET-generated knowledge improve the system’s performance as measured by automatic metrics and also by human evaluation. Lastly, we present a comparative study on the types of knowledge encoded by our system showing that causal and intentional relationships benefit the generation task more than other types of commonsense relations.

/pdf/knowledge-enhanced-reflection-generation-for-counseling-3twpvhxr.pdf

Knowledge Enhanced Reflection Generation for Counseling Dialogues

Background Motivational interviewing (MI) can increase health-promoting behaviors and decrease health-damaging behaviors. However, MI is often resource intensive, precluding its use with people with limited financial or time resources. Mobile health–based versions of MI interventions or technology-delivered adaptations of MI (TAMIs) might increase reach. Objective We aimed to understand the characteristics of existing TAMIs. We were particularly interested in the inclusion of people from marginalized sociodemographic groups, whether the TAMI addressed sociocontextual factors, and how behavioral and health outcomes were reported. Methods We employed the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines for scoping reviews to conduct our scoping review. We searched PubMed, CINAHL, and PsycInfo from January 1, 1996, to April 6, 2022, to identify studies that described interventions incorporating MI into a mobile or electronic health platform. For inclusion, the study was required to (1) describe methods/outcomes of an MI intervention, (2) feature an intervention delivered automatically via a mobile or electronic health platform, and (3) report a behavioral or health outcome. The exclusion criteria were (1) publication in a language other than English and (2) description of only in-person intervention delivery (ie, no TAMI). We charted results using Excel (Microsoft Corp). Results Thirty-four studies reported the use of TAMIs. Sample sizes ranged from 10 to 2069 participants aged 13 to 70 years. Most studies (n=27) directed interventions toward individuals engaging in behaviors that increased chronic disease risk. Most studies (n=22) oversampled individuals from marginalized sociodemographic groups, but few (n=3) were designed specifically with marginalized groups in mind. TAMIs used text messaging (n=8), web-based intervention (n=22), app + text messaging (n=1), and web-based intervention + text messaging (n=3) as delivery platforms. Of the 34 studies, 30 (88%) were randomized controlled trials reporting behavioral and health-related outcomes, 23 of which reported statistically significant improvements in targeted behaviors with TAMI use. TAMIs improved targeted health behaviors in the remaining 4 studies. Moreover, 11 (32%) studies assessed TAMI feasibility, acceptability, or satisfaction, and all rated TAMIs highly in this regard. Among 20 studies with a disproportionately high number of people from marginalized racial or ethnic groups compared with the general US population, 16 (80%) reported increased engagement in health behaviors or better health outcomes. However, no TAMIs included elements that addressed sociocontextual influences on behavior or health outcomes. Conclusions Our findings suggest that TAMIs may improve some health promotion and disease management behaviors. However, few TAMIs were designed specifically for people from marginalized sociodemographic groups, and none included elements to help address sociocontextual challenges. Research is needed to determine how TAMIs affect individual health outcomes and how to incorporate elements that address sociocontextual factors, and to identify the best practices for implementing TAMIs into clinical practice.

/pdf/technology-delivered-adaptations-of-motivational-mo2p1tsi.pdf

Technology-Delivered Adaptations of Motivational Interviewing for the Prevention and Management of Chronic Diseases: Scoping Review

Summary Objectives : Owing to the rapid progress of natural language processing (NLP), the role of NLP in the medical field has radically gained considerable attention from both NLP and medical informatics. Although numerous medical NLP papers are published annually, there is still a gap between basic NLP research and practical product development. This gap raises questions, such as what has medical NLP achieved in each medical field, and what is the burden for the practical use of NLP? This paper aims to clarify the above questions. Methods : We explore the literature on potential NLP products/services applied to various medical/clinical/healthcare areas. Results : This paper introduces clinical applications (bedside applications), in which we introduce the use of NLP for each clinical department, internal medicine, pre-surgery, post-surgery, oncology, radiology, pathology, psychiatry, rehabilitation, obstetrics, and gynecology. Also, we clarify technical problems to be addressed for encouraging bedside applications based on NLP. Conclusions : These results contribute to discussions regarding potentially feasible NLP applications and highlight research gaps for future studies.

/pdf/natural-language-processing-from-bedside-to-everywhere-34rfilt5.pdf

Natural Language Processing: from Bedside to Everywhere

Background Engagement with smartphone apps for smoking cessation tends to be low. Chatbots (ie, software that enables conversations with users) offer a promising means of increasing engagement. Objective We aimed to explore smokers’ experiences with a quick-response chatbot (Quit Coach) implemented within a popular smoking cessation app and identify factors that influence users’ engagement with Quit Coach. Methods In-depth, one-to-one, semistructured qualitative interviews were conducted with adult, past-year smokers who had voluntarily used Quit Coach in a recent smoking cessation attempt (5/14, 36%) and current smokers who agreed to download and use Quit Coach for a minimum of 2 weeks to support a new cessation attempt (9/14, 64%). Verbal reports were audio recorded, transcribed verbatim, and analyzed within a constructivist theoretical framework using inductive thematic analysis. Results A total of 3 high-order themes were generated to capture users’ experiences and engagement with Quit Coach: anthropomorphism of and accountability to Quit Coach (ie, users ascribing human-like characteristics and thoughts to the chatbot, which helped foster a sense of accountability to it), Quit Coach’s interaction style and format (eg, positive and motivational tone of voice and quick and easy-to-complete check-ins), and users’ perceived need for support (ie, chatbot engagement was motivated by seeking distraction from cravings or support to maintain motivation to stay quit). Conclusions Anthropomorphism of a quick-response chatbot implemented within a popular smoking cessation app appeared to be enabled by its interaction style and format and users’ perceived need for support, which may have given rise to feelings of accountability and increased engagement.

Exploring Users’ Experiences With a Quick-Response Chatbot Within a Popular Smoking Cessation Smartphone App: Semistructured Interview Study

Background Given the growing significance of conversational agents (CAs), researchers have conducted a plethora of relevant studies on various technology- and usability-oriented issues. However, few investigations focus on language use in CA-based health communication to examine its influence on the user perception of CAs and their role in delivering health care services. Objective This review aims to present the language use of CAs in health care to identify the achievements made and breakthroughs to be realized to inform researchers and more specifically CA designers. Methods This review was conducted by following the protocols of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) 2020 statement. We first designed the search strategy according to the research aim and then performed the keyword searches in PubMed and ProQuest databases for retrieving relevant publications (n=179). Subsequently, 3 researchers screened and reviewed the publications independently to select studies meeting the predefined selection criteria. Finally, we synthesized and analyzed the eligible articles (N=11) through thematic synthesis. Results Among the 11 included publications, 6 deal exclusively with the language use of the CAs studied, and the remaining 5 are only partly related to this topic. The language use of the CAs in these studies can be roughly classified into six themes: (1) personal pronouns, (2) responses to health and lifestyle prompts, (3) strategic wording and rich linguistic resources, (4) a 3-staged conversation framework, (5) human-like well-manipulated conversations, and (6) symbols and images coupled with phrases. These derived themes effectively engaged users in health communication. Meanwhile, we identified substantial room for improvement based on the inconsistent responses of some CAs and their inability to present large volumes of information on safety-critical health and lifestyle prompts. Conclusions This is the first systematic review of language use in CA-based health communication. The results and limitations identified in the 11 included papers can give fresh insights into the design and development, popularization, and research of CA applications. This review can provide practical implications for incorporating positive language use into the design of health CAs and improving their effective language output in health communication. In this way, upgraded CAs will be more capable of handling various health problems particularly in the context of nationwide and even worldwide public health crises.

/pdf/language-use-in-conversational-agent-based-health-2xq5cifb.pdf

Language Use in Conversational Agent–Based Health Communication: Systematic Review

Background: At any given time, most smokers in a population are ambivalent with no motivation to quit. Motivational interviewing (MI) is an evidence-based technique that aims to elicit change in ambivalent smokers. MI practitioners are scarce and expensive, and smokers are difficult to reach. Smokers are potentially reachable through the web, and if an automated chatbot could emulate an MI conversation, it could form the basis of a low-cost and scalable intervention motivating smokers to quit.
Objective: The primary goal of this study is to design, train, and test an automated MI-based chatbot capable of eliciting reflection in a conversation with cigarette smokers. This study describes the process of collecting training data to improve the chatbot’s ability to generate MI-oriented responses, particularly reflections and summary statements. The secondary goal of this study is to observe the effects on participants through voluntary feedback given after completing a conversation with the chatbot.
Methods: An interdisciplinary collaboration between an MI expert and experts in computer engineering and natural language processing (NLP) co-designed the conversation and algorithms underlying the chatbot. A sample of 121 adult cigarette smokers in 11 successive groups were recruited from a web-based platform for a single-arm prospective iterative design study. The chatbot was designed to stimulate reflections on the pros and cons of smoking using MI’s running head start technique. Participants were also asked to confirm the chatbot’s classification of their free-form responses to measure the classification accuracy of the underlying NLP models. Each group provided responses that were used to train the chatbot for the next group.
Results: A total of 6568 responses from 121 participants in 11 successive groups over 14 weeks were received. From these responses, we were able to isolate 21 unique reasons for and against smoking and the relative frequency of each. The gradual collection of responses as inputs and smoking reasons as labels over the 11 iterations improved the F1 score of the classification within the chatbot from 0.63 in the first group to 0.82 in the final group. The mean time spent by each participant interacting with the chatbot was 21.3 (SD 14.0) min (minimum 6.4 and maximum 89.2). We also found that 34.7% (42/121) of participants enjoyed the interaction with the chatbot, and 8.3% (10/121) of participants noted explicit smoking cessation benefits from the conversation in voluntary feedback that did not solicit this explicitly.
Conclusions: Recruiting ambivalent smokers through the web is a viable method to train a chatbot to increase accuracy in reflection and summary statements, the building blocks of MI. A new set of 21 smoking reasons (both for and against) has been identified. Initial feedback from smokers on the experience shows promise toward using it in an intervention.

/pdf/engaging-unmotivated-smokers-to-move-toward-quitting-design-1wgjyeticu.pdf

Fahad Almusharraf

Papers

Engaging Unmotivated Smokers to Move Toward Quitting: Design of Motivational Interviewing–Based Chatbot Through Iterative Interactions