An official website of the United States government
Automatic coding patient behaviors is essential to support decision making for psychotherapists during the motivational interviewing (MI), a collaborative communication intervention approach to address psychiatric issues, such as alcohol and drug addiction. While the behavior coding task has rapidly adapted language models to predict patient states during the MI sessions, lacking of domain-specific knowledge and overlooking patient-therapist interactions are major challenges in developing and deploying those models in real practice. To encounter those challenges, we introduce the Chain-of- Interaction (CoI) prompting method aiming to contextualize large language models (LLMs) for psychiatric decision support by the dyadic interactions. The CoI prompting approach systematically breaks down the coding task into three key reasoning steps, extract patient engagement, learn therapist question strategies, and integrates dyadic interactions between patients and therapists. This approach enables large language models to leverage the coding scheme, patient state, and domain knowledge for patient behavioral coding. Experiments on real-world datasets can prove the effectiveness and flexibility of our prompting method with multiple state-of-the-art LLMs over existing prompting baselines. We have conducted extensive ablation analysis and demonstrate the critical role of dyadic interactions in applying LLMs for psychotherapy behavior understanding.
more »
« less
Observing Dialogue in Therapy: Categorizing and Forecasting Behavioral Codes
Automatically analyzing dialogue can help understand and guide behavior in domains such as counseling, where interactions are largely mediated by conversation. In this paper, we study modeling behavioral codes used to asses a psychotherapy treatment style called Motivational Interviewing (MI), which is effective for addressing substance abuse and related problems. Specifically, we address the problem of providing real-time guidance to therapists with a dialogue observer that (1) categorizes therapist and client MI behavioral codes and, (2) forecasts codes for upcoming utterances to help guide the conversation and potentially alert the therapist. For both tasks, we define neural network models that build upon recent successes in dialogue modeling. Our experiments demonstrate that our models can outperform several baselines for both tasks. We also report the results of a careful analysis that reveals the impact of the various network design tradeoffs for modeling therapy dialogue.
more »
« less
- Award ID(s):
- 1822877
- PAR ID:
- 10110322
- Date Published:
- Journal Name:
- Computational linguistics - Association for Computational Linguistics
- ISSN:
- 0891-2017
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In this demonstration, in collaboration with licensed therapists, we introduce an AI therapist that takes advantage of the smart-home environment to screen day-to-day functioning and infer mental wellness of an occupant. Our system can assess a user's daily functioning and mental wellness based on a combination of direct conversation with users and information obtained from smart home devices using psychological rubrics proposed in [1]. We demonstrate that our system can converse with a user in a natural way (through a smartphone or smart speaker) and analyze a user's response semantically and sentimentally. In addition, we show that our system can provide preliminary interventions to help improve the user's wellness. In particular, when abnormal behavior is detected during the conversation or by smart home devices, the system provides psychotherapeutic consolations during the conversation and will check on the occupant's condition by actuating a home robot.more » « less
-
Collaborative tasks often begin with partial task knowledge and incomplete initial plans from each partner. To complete these tasks, agents need to engage in situated communication with their partners and coordinate their partial plans towards a complete plan to achieve a joint task goal. While such collaboration seems effortless in a human-human team, it is highly challenging for human-AI collaboration. To address this limitation, this paper takes a step towards collaborative plan acquisition, where humans and agents strive to learn and communicate with each other to acquire a complete plan for joint tasks. Specifically, we formulate a novel problem for agents to predict the missing task knowledge for themselves and for their partners based on rich perceptual and dialogue history. We extend a situated dialogue benchmark for symmetric collaborative tasks in a 3D blocks world and investigate computational strategies for plan acquisition. Our empirical results suggest that predicting the partner's missing knowledge is a more viable approach than predicting one's own. We show that explicit modeling of the partner's dialogue moves and mental states produces improved and more stable results than without. These results provide insight for future AI agents that can predict what knowledge their partner is missing and, therefore, can proactively communicate such information to help their partner acquire such missing knowledge toward a common understanding of joint tasks.more » « less
-
null (Ed.)Asking clarifying questions in response to ambiguous or faceted queries has been recognized as a useful technique for various information retrieval systems, in particular, conversational search systems with limited bandwidth interfaces. Analyzing and generating clarifying question have been recently studied in the literature. However, accurate utilization of user responses to clarifying questions has been relatively less explored. In this paper, we propose a neural network model based on a novel attention mechanism, called multi source attention network. Our model learns a representation for a user-system conversation that includes clarifying questions. In more detail, with the help of multiple information sources, our model weights each term in the conversation. In our experiments, we use two separate external sources, including the top retrieved documents and a set of different possible clarifying questions for the query. We implement the proposed representation learning model for two downstream tasks in conversational search; document retrieval and next clarifying question selection. We evaluate our models using a public dataset for search clarification. Our experiments demonstrate significant improvements compared to competitive baselines.more » « less
-
Kolawole, Olatunji Matthew (Ed.)Persons living with human immunodeficiency virus (HIV) have a disproportionately higher burden of human papillomavirus infection (HPV)-related cancers. Causal factors include both behavioral and biological. While pharmaceutical and care support interventions help address biological risk of coinfection, as social conditions are common drivers of behaviors, structural interventions are key part of behavioral interventions. Our objective is to develop a joint HIV-HPV model to evaluate the contribution of each factor, to subsequently inform intervention analyses. While compartmental modeling is sufficient for faster spreading HPV, network modeling is suitable for slower spreading HIV. However, using network modeling for jointly modeling HIV and HPV can generate computational complexities given their vastly varying disease epidemiology and disease burden across sub-population groups. We applied a recently developed mixed agent-based compartmental (MAC) simulation technique, which simulates persons with at least one slower spreading disease and their immediate contacts as agents in a network, and all other persons including those with faster spreading diseases in a compartmental model, with an evolving contact network algorithm maintaining the dynamics between the two models. We simulated HIV and HPV in the U.S. among heterosexual female, heterosexual male, and men who have sex with men (men only and men and women) (MSM), sub-populations that mix but have varying HIV burden, and cervical cancer among women. We conducted numerical analyses to evaluate the contribution of behavioral and biological factors to risk of cervical cancer among women with HIV. The model outputs for HIV, HPV, and cervical cancer compared well with surveillance estimates. Model estimates for relative prevalence of HPV (1.67 times) and relative incidence of cervical cancer (3.6 times), among women with HIV compared to women without, were also similar to that reported in observational studies in the literature. The fraction attributed to biological factors ranged from 22–38% for increased HPV prevalence and 80% for increased cervical cancer incidence, the remaining attributed to behavioral. The attribution of both behavioral and biological factors to increased HPV prevalence and cervical cancer incidence suggest the need for behavioral, structural, and pharmaceutical interventions. Validity of model results related to both individual and joint disease metrics serves as proof-of-concept of the MAC simulation technique. Understanding the contribution of behavioral and biological factors of risk helps inform interventions. Future work can expand the model to simulate sexual and care behaviors as functions of social conditions to jointly evaluate behavioral, structural, and pharmaceutical interventions for HIV and cervical cancer prevention.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
