scholarly journals An Artificial Intelligence Based Virtual Assistant Using Conversational Agents

2021 ◽  
Vol 14 (09) ◽  
pp. 455-473
Author(s):  
Mehdi Mekni
Keyword(s):  
Artificial Intelligence ◽  
Conversational Agents

A fully automated conversational agent with artificial intelligence capabilities (Youper) for treating depression and anxiety: A nonrandomized feasibility trial (Preprint)

2019 ◽  
Author(s):  
Jose Hamilton Vargas ◽  
Thiago Antonio Marafon ◽  
Diego Fernando Couto ◽  
Ricardo Giglio ◽  
Marvin Yan ◽  
...  
Keyword(s):  
Mental Health ◽  
Artificial Intelligence ◽  
Financial Incentives ◽  
Empirical Support ◽  
Digital Technologies ◽  
Feasibility Trial ◽  
Depression And Anxiety ◽  
Conversational Agents ◽  
Symptoms Of Depression ◽  
Viable Solution

BACKGROUND Mental health conditions, including depression and anxiety disorders, are significant global concerns. Many people with these conditions don't get the help they need because of the high costs of medical treatment and the stigma attached to seeking help. Digital technologies represent a viable solution to these challenges. However, these technologies are often characterized by relatively low adherence and their effectiveness largely remains empirical unverified. While digital technologies may represent a viable solution for this persisting problem, they often lack empirical support for their effectiveness and are characterized by relatively low adherence. Conversational agents using artificial intelligence capabilities have the potential to offer a cost-effective, low-stigma and engaging way of getting mental health care. OBJECTIVE The objective of this study was to evaluate the feasibility, acceptability, and effectiveness of Youper, a mobile application that utilizes a conversational interface and artificial intelligence capabilities to deliver cognitive behavioral therapy-based interventions to reduce symptoms of depression and anxiety in adults. METHODS 1,012 adults with symptoms of depression and anxiety participated in a real-world setting study, entirely remotely, unguided and with no financial incentives, over an 8-week period. Participants completed digital versions of the 9-item Patient Health Questionnaire (PHQ-9) and the 7-item Generalized Anxiety Disorder scale (GAD-7) at baseline, 2, 4, and 8 weeks. RESULTS After the eight-week study period, depression (PHQ-9) scores of participants decreased by 48% while anxiety (GAD-7) scores decreased by 43%. The RCI was outside 2 standard deviations for 93.0% of the individuals in the PHQ-9 assessment and 90.7% in the GAD-7 assessment. Participants were on average 24.79 years old (SD 7.61) and 77% female. On average, participants interacted with Youper 0.9 (SD 1.56) times per week. CONCLUSIONS Results suggest that Youper is a feasible, acceptable, and effective intervention for adults with depression and anxiety. CLINICALTRIAL Since this study involved a nonclinical population, it wasn't registered in a public trials registry.

Primary Care: The Actual Intelligence Required for Artificial Intelligence to Advance Health Care and Improve Health (Preprint)

2021 ◽  
Author(s):  
Winston R. Liaw ◽  
John M Westfall ◽  
Tyler S Williamson ◽  
Yalda Jabbarpour ◽  
Andrew Bazemore
Keyword(s):  
Artificial Intelligence ◽  
Primary Care ◽  
Vital Signs ◽  
Patient Privacy ◽  
Conversational Agents ◽  
Care Needs ◽  
Remote Sensors ◽  
Delivery Platform ◽  
And Training ◽  
Improve Health

UNSTRUCTURED With conversational agents triaging symptoms, cameras aiding diagnoses, and remote sensors monitoring vital signs, the use of artificial intelligence (AI) outside of hospitals has the potential to improve health, according to a recently released report from the National Academy of Medicine. Despite this promise, AI’s success is not guaranteed, and stakeholders need to be involved with its development to ensure that the resulting tools can be easily used by clinicians, protect patient privacy, and enhance the value of the care delivered. A crucial stakeholder group missing from the conversation is primary care. As the nation’s largest delivery platform, primary care will have a powerful impact on whether AI is adopted and subsequently exacerbates health disparities. To leverage these benefits, primary care needs to serve as a medical home for AI, broaden its teams and training, and build on government initiatives and funding.

Affective Agents in E-Learning Platforms

2012 ◽  
pp. 1225-1233
Author(s):  
Christos N. Moridis ◽  
Anastasios A. Economides
Keyword(s):  
Artificial Intelligence ◽  
Learning Environments ◽  
Intelligent Agents ◽  
Intelligent Agent ◽  
Human Learning ◽  
Human Reasoning ◽  
Conversational Agents ◽  
Emotional Aspects ◽  
E Learning ◽  
Learning Platforms

During recent decades there has been an extensive progress towards several Artificial Intelligence (AI) concepts, such as that of intelligent agent. Meanwhile, it has been established that emotions play a crucial role concerning human reasoning and learning. Thus, developing an intelligent agent able to recognize and express emotions has been considered an enormous challenge for AI researchers. Embedding a computational model of emotions in intelligent agents can be beneficial in a variety of domains, including e-learning applications. However, until recently emotional aspects of human learning were not taken into account when designing e-learning platforms. Various issues arise when considering the development of affective agents in e-learning environments, such as issues relating to agents’ appearance, as well as ways for those agents to recognize learners’ emotions and express emotional support. Embodied conversational agents (ECAs) with empathetic behaviour have been suggested to be one effective way for those agents to provide emotional feedback to learners’ emotions. There has been some valuable research towards this direction, but a lot of work still needs to be done to advance scientific knowledge.

Essential Features and Critical Issues With Educational Chatbots

2021 ◽  
pp. 246-262
Author(s):  
Jeremy Riel
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Formal Learning ◽  
Automated Systems ◽  
Conversational Agents ◽  
Teacher Instruction ◽  
Practical Applications ◽  
Significant Potential ◽  
Critical Issues ◽  
Future Work

Conversational agents, also known as chatbots, are automated systems for engaging in two-way dialogue with human users. These systems have existed in one form or another for at least 60 years but have recently demonstrated significant potential with advances in machine learning and artificial intelligence technologies. The use of conversational agents or chatbots for education can potentially reduce costs and supplement teacher instruction in transformative ways for formal learning. This chapter examines the design and status of chatbots and conversational agents for educational purposes. Common design functions and goals of educational chatbots are described, along with current practical applications of chatbots for educational purposes. Finally, this chapter considers issues about pedagogical commitments, ethics, and equity to suggest future work in the field.

scholarly journals Voice Assistant vs. Chatbot – Examining the Fit Between Conversational Agents’ Interaction Modalities and Information Search Tasks

2021 ◽  
Author(s):  
Christine Rzepka ◽  
Benedikt Berger ◽  
Thomas Hess
Keyword(s):  
Artificial Intelligence ◽  
Laboratory Experiment ◽  
Customer Service ◽  
Information Search ◽  
Search Task ◽  
Cognitive Effort ◽  
Research Model ◽  
Conversational Agents ◽  
Search Tasks ◽  
Task Technology Fit

AbstractOwing to technological advancements in artificial intelligence, voice assistants (VAs) offer speech as a new interaction modality. Compared to text-based interaction, speech is natural and intuitive, which is why companies use VAs in customer service. However, we do not yet know for which kinds of tasks speech is beneficial. Drawing on task-technology fit theory, we present a research model to examine the applicability of VAs to different tasks. To test this model, we conducted a laboratory experiment with 116 participants who had to complete an information search task with a VA or a chatbot. The results show that speech exhibits higher perceived efficiency, lower cognitive effort, higher enjoyment, and higher service satisfaction than text-based interaction. We also find that these effects depend on the task’s goal-directedness. These findings extend task-technology fit theory to customers’ choice of interaction modalities and inform practitioners about the use of VAs for information search tasks.

scholarly journals Acceptability of artificial intelligence (AI)-led chatbot services in healthcare: A mixed-methods study

2019 ◽  
Vol 5 ◽  
pp. 205520761987180 ◽  
Author(s):  
Tom Nadarzynski ◽  
Oliver Miles ◽  
Aimee Cowie ◽  
Damien Ridge
Keyword(s):  
Artificial Intelligence ◽  
Cyber Security ◽  
Online Survey ◽  
Mixed Methods Study ◽  
Conversational Agents ◽  
Structured Interviews ◽  
Perceived Utility ◽  
Internet Users ◽  
It Skills ◽  
Engagement Intervention

Background Artificial intelligence (AI) is increasingly being used in healthcare. Here, AI-based chatbot systems can act as automated conversational agents, capable of promoting health, providing education, and potentially prompting behaviour change. Exploring the motivation to use health chatbots is required to predict uptake; however, few studies to date have explored their acceptability. This research aimed to explore participants’ willingness to engage with AI-led health chatbots. Methods The study incorporated semi-structured interviews (N-29) which informed the development of an online survey (N-216) advertised via social media. Interviews were recorded, transcribed verbatim and analysed thematically. A survey of 24 items explored demographic and attitudinal variables, including acceptability and perceived utility. The quantitative data were analysed using binary regressions with a single categorical predictor. Results Three broad themes: ‘Understanding of chatbots’, ‘AI hesitancy’ and ‘Motivations for health chatbots’ were identified, outlining concerns about accuracy, cyber-security, and the inability of AI-led services to empathise. The survey showed moderate acceptability (67%), correlated negatively with perceived poorer IT skills OR = 0.32 [CI95%:0.13–0.78] and dislike for talking to computers OR = 0.77 [CI95%:0.60–0.99] as well as positively correlated with perceived utility OR = 5.10 [CI95%:3.08–8.43], positive attitude OR = 2.71 [CI95%:1.77–4.16] and perceived trustworthiness OR = 1.92 [CI95%:1.13–3.25]. Conclusion Most internet users would be receptive to using health chatbots, although hesitancy regarding this technology is likely to compromise engagement. Intervention designers focusing on AI-led health chatbots need to employ user-centred and theory-based approaches addressing patients’ concerns and optimising user experience in order to achieve the best uptake and utilisation. Patients’ perspectives, motivation and capabilities need to be taken into account when developing and assessing the effectiveness of health chatbots.

scholarly journals Zhorai: Designing a Conversational Agent for Children to Explore Machine Learning Concepts

2020 ◽  
Vol 34 (09) ◽  
pp. 13381-13388
Author(s):  
Phoebe Lin ◽  
Jessica Van Brummelen ◽  
Galit Lukin ◽  
Randi Williams ◽  
Cynthia Breazeal
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Young Children ◽  
Mental Models ◽  
Small Groups ◽  
Smart Devices ◽  
The Novel ◽  
Conversational Agent ◽  
Conversational Agents ◽  
Limited Knowledge

Understanding how machines learn is critical for children to develop useful mental models for exploring artificial intelligence (AI) and smart devices that they now frequently interact with. Although children are very familiar with having conversations with conversational agents like Siri and Alexa, children often have limited knowledge about AI and machine learning. We leverage their existing familiarity and present Zhorai, a conversational platform and curriculum designed to help young children understand how machines learn. Children ages eight to eleven train an agent through conversation and understand how the knowledge is represented using visualizations. This paper describes how we designed the curriculum and evaluated its effectiveness with 14 children in small groups. We found that the conversational aspect of the platform increased engagement during learning and the novel visualizations helped make machine knowledge understandable. As a result, we make recommendations for future iterations of Zhorai and approaches for teaching AI to children.

Sign in / Sign up

Export Citation Format

Share Document