Modern Chatbot Systems: A Technical Review

Lokman, Abbas Saliimi; Ameedeen, Mohamed Ariff

doi:10.1007/978-3-030-02683-7_75

Cited by 54 publications

(23 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Given their interactive nature since they were first launched in early 2016, chatbots have been extensively used for a wide range of purposes across different sectors, facilitated by a shift in the communication landscape. The younger generation, in particular, seems to keener on engaging in shorter messaging exchanges (e.g., text/voice message) rather than opting for longer, direct forms of communication (e.g., phone call) (Lokman & Ameedeen, 2018). Some predictions suggest that, from the users' perspective, chatbots will change the way people interact with data, while, from a business perspective, they will reduce service providers' motivation to invest in apps, prioritizing instead chatbots as a channel for reaching out to users (Brandtzaeg & Følstad, 2018).…”

Section: Introductionmentioning

confidence: 99%

“It’s on its way”: Chatbots applied for online food delivery services, social or task-oriented interaction style?

Cicco

Silva

Alparone

2020

Journal of Foodservice Business Research

View full text Add to dashboard Cite

Research has yet to explore the spread of chatbots into the foodservice delivery sector and its impact on the customer's experience, especially in a moment when the Internet seems to be the tool to meet needs associated with being physically apart. In order to fill this gap, the present study addresses the implications that chatbots' interaction styles have for younger consumers using this channel for conversational online food delivery (OFD) services. Specifically, this study provides theoretical and practical insights into whether the conversational design of chatbots can influence social, affective, and behavioral intent outcomes. The study adopts an experimental design to investigate the effects of a social-versus task-oriented interaction style chatbot on the level of social presence and trust (social outcomes), perceived enjoyment (affective outcome), and intention to use the conversational OFD service in the future (behavioral intent outcome). Findings from a sample of 171 participants show that the interaction with the chatbot set up with a social-oriented interaction style increased users' perception of social presence and perceived enjoyment, while it did not have any direct and significant effect on trust and intention to use. The study further supports the role of social presence, trust, and perceived enjoyment as mediators between the chatbot's interaction style and the intention to use the conversational OFD service.

show abstract

Section: Introductionmentioning

confidence: 99%

“It’s on its way”: Chatbots applied for online food delivery services, social or task-oriented interaction style?

Cicco

Silva

Alparone

2020

Journal of Foodservice Business Research

View full text Add to dashboard Cite

show abstract

“…Chatbots can be developed in several ways [24][25][26]. One approach is to write out the basic conversations, including responses to user inputs, and then continue to refine the conversations based on user and chatbot inputs.…”

Section: Chatbot Developmentmentioning

confidence: 99%

The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study

Chan¹,

Fitzsimmons‐Craft²,

Smith³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

Background Chatbots have the potential to provide cost-effective mental health prevention programs at scale and increase interactivity, ease of use, and accessibility of intervention programs. Objective The development of chatbot prevention for eating disorders (EDs) is still in its infancy. Our aim is to present examples of and solutions to challenges in designing and refining a rule-based prevention chatbot program for EDs, targeted at adult women at risk for developing an ED. Methods Participants were 2409 individuals who at least began to use an EDs prevention chatbot in response to social media advertising. Over 6 months, the research team reviewed up to 52,129 comments from these users to identify inappropriate responses that negatively impacted users’ experience and technical glitches. Problems identified by reviewers were then presented to the entire research team, who then generated possible solutions and implemented new responses. Results The most common problem with the chatbot was a general limitation in understanding and responding appropriately to unanticipated user responses. We developed several workarounds to limit these problems while retaining some interactivity. Conclusions Rule-based chatbots have the potential to reach large populations at low cost but are limited in understanding and responding appropriately to unanticipated user responses. They can be most effective in providing information and simple conversations. Workarounds can reduce conversation errors.

show abstract

“…A chatbot is a form of a computer system that lets humans use natural human language to interact with computers. Some examples of modern chatbot systems are AliMe, DeepProbe, SuperAgent, MILABOT, and RubyStar [38]. ELIZA is the first chatbot developed by Professor Joseph Weizenbaum at the Massachusetts Institute of Technology.…”

Section: Overview Of Chatbotmentioning

confidence: 99%

Machine Learning in Healthcare Communication

2021

View full text Add to dashboard Cite

Machine learning (ML) is a study of computer algorithms for automation through experience. ML is a subset of artificial intelligence (AI) that develops computer systems, which are able to perform tasks generally having need of human intelligence. While healthcare communication is important in order to tactfully translate and disseminate information to support and educate patients and public, ML is proven applicable in healthcare with the ability for complex dialogue management and conversational flexibility. In this topical review, we will highlight how the application of ML/AI in healthcare communication is able to benefit humans. This includes chatbots for the COVID-19 health education, cancer therapy, and medical imaging.

show abstract

Modern Chatbot Systems: A Technical Review

Cited by 54 publications

References 18 publications

“It’s on its way”: Chatbots applied for online food delivery services, social or task-oriented interaction style?

“It’s on its way”: Chatbots applied for online food delivery services, social or task-oriented interaction style?

The Challenges in Designing a Prevention Chatbot for Eating Disorders: Observational Study

Machine Learning in Healthcare Communication

Contact Info

Product

Resources

About