A Wizard-of-Oz Interface and Persona-based Methodology for Collecting Health Counseling Dialog

@article{Kearns2020AWI,
  title={A Wizard-of-Oz Interface and Persona-based Methodology for Collecting Health Counseling Dialog},
  author={William R. Kearns and Neha Kaura and Myra Divina and Cuong Viet Vo and Dong Si and Teresa Ward and Weichao Yuwen},
  journal={Extended Abstracts of the 2020 CHI Conference on Human Factors in Computing Systems},
  year={2020}
}
Health dialog collection is the primary bottleneck for the training and deployment of conversational agents into clinical practice. Current tools for the development of dialog systems are primarily focused on writing intent-slot schemas for natural language understanding and finite-state models of dialog management. However, this is a time-consuming process that can be opaque for clinical teams and the limitations of both approaches are well understood. The health domain presents additional… 

Figures from this paper

Integrating a Voice User Interface into a Virtual Therapy Platform
TLDR
This work is the integration of VUIs into a virtual therapy platform to promote user engagement in self-care practices, and conducted user research with family caregivers and subject matter experts, and designed multiple prototypes with user evaluations.
Wizard-of-Oz Testing as an Instrument for Chatbot Development An experimental Pre-study for Setting up a Recruiting Chatbot Prototype
TLDR
This study investigated chatbots in recruiting, a field within human resource management that is characterized by a high proportion of repetitive and standardized tasks, and applies a Wizard-of-Oz approach in which a basic dialog concept is tested in a very early phase of the project, simulating the chatbot functionality by a human operator.
Understanding Few-Shot Commonsense Knowledge Models
TLDR
This work investigates training commonsense knowledge models in a fewshot setting with limited tuples per commonsense relation in the graph and finds that human quality ratings for knowledge produced from a few-shot trained system can achieve performance within 6% of knowledgeproduced from fully supervised systems.
Self-Care Needs and Technology Preferences Among Parents in Marginalized Communities: Participatory Design Study
TLDR
When coming up with ideas of technologies for self-care, non-Latino parents focused on improving caregiving stress through journaling, daily affirmations, and tracking feelings, while Latino parents focused more on relaxation and entertainment.
On Symbolic and Neural Commonsense Knowledge Graphs
TLDR
It is proposed that manually constructed CSKGs will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents, and a new evaluation framework for testing the utility of KGs based on how effectively implicit knowledge representations can be learned from them is proposed.
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
TLDR
It is proposed that manually constructed CSKGs will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents, and a new evaluation framework for testing the utility of KGs based on how effectively implicit knowledge representations can be learned from them is proposed.
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
TLDR
It is shown that careful prompt engineering and a separately trained critic model allow us to selectively distill high-quality causal commonsense from GPT-3, a general language model, and this leads to a new framework, Symbolic Knowledge Distillation.
Dynamic Neuro-Symbolic Knowledge Graph Construction for Zero-shot Commonsense Question Answering
TLDR
This paper presents a novel approach that generates contextually-relevant symbolic knowledge structures on demand using generative neural commonsense knowledge models and achieves significant performance boosts over pretrained language models and vanilla knowledge models, all while providing interpretable reasoning paths for its predictions.
Paragraph-Level Commonsense Transformers with Recurrent Memory
TLDR
PARA-COMeT, a discourse-aware model that incorporates paragraph-level information to generate coherent commonsense inferences from narratives, outperforms the sentence-level baselines, particularly in generating inferences that are both coherent and novel.

References

SHOWING 1-10 OF 39 REFERENCES
Usability of Conversational Agents by Patients with Inadequate Health Literacy: Evidence from Two Clinical Trials
Embodied Conversational Agents (ECA) are computer-animated characters that simulate face-to-face conversation with patients. These agents can be programmed with best practices in human-human health
Towards an Artificially Empathic Conversational Agent for Mental Health Applications: System Design and User Perceptions
TLDR
A conversational agent that could express empathic support in ways that might approach, or even match, human capabilities is designed and illustrates a novel way for machines to construct nuanced and personalized empathic utterances.
Conversational agents in healthcare: a systematic review
TLDR
The use of conversational agents with unconstrained natural language input capabilities for health-related purposes is an emerging field of research, where the few published studies were mainly quasi-experimental, and rarely evaluated efficacy or safety.
Embodied Conversational Agents in Clinical Psychology: A Scoping Review
TLDR
An overview of the technological and clinical possibilities, as well as the evidence base for ECA applications in clinical psychology, is provided to inform health professionals about the activity in this field of research.
Chat-Bots for People with Parkinson's Disease: Science Fiction or Reality?
TLDR
Initial work on a Parkinson's disease themed chat-bot that interacts with the user relative to their symptoms is presented, and potential dialogues are provided to illustrate the various roles chat-bots can play in the management of Parkinson’s disease.
A Persona is Not A Person : Designing Dialogs With ECAs After Wizard of Oz Simulations
TLDR
Several evaluation studies have been performed on Embodied Conversational Agents, with different aims and methods, but this kind of studies does not yet provide clear suggestions on which conversational style is appropriate for ECAs, in every application domain.
Towards Understanding Emotional Intelligence for Behavior Change Chatbots
TLDR
The design and evaluation of an emotion-aware chatbot that conducts experience sampling in an empathetic manner is presented and it is shown that extraverts preferred the emotion- Aware chatbot significantly more than introverts.
...
1
2
3
4
...