ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Conversational Agents: Goals, Technologies, Vision and Challenges | JoVE Visualize

Home
Research Domains
Information And Computing Sciences

Conversational Agents: Goals, Technologies, Vision and Challenges

Merav Allouch¹, Amos Azaria¹, Rina Azoulay²

¹Computer Science Department, Ariel University, Ariel 40700, Israel.

Sensors (Basel, Switzerland)|December 28, 2021

View abstract on PubMed

Summary

Conversational agents (CAs) are increasingly used across many sectors. This review details their enabling technologies, applications, and future research directions, including moral and security considerations.

Area of Science:

Artificial Intelligence
Human-Computer Interaction
Natural Language Processing

Background:

Conversational agents (CAs) are now ubiquitous in daily life.
Their technology has matured, enabling diverse applications across commercial, healthcare, educational, and personal domains.

Purpose of the Study:

To describe successful application areas and core technologies for CA development.
To categorize CAs by abilities and domains.
To identify tools, datasets, and future research directions.

Main Methods:

Review of current CA technologies, including natural language processing, deep learning, and emotional integration.
Analysis of CA evaluation technologies and publicly available datasets.
Categorization of CAs based on capabilities and application domains.

Main Results:

CAs leverage NLP, deep learning, and emotional AI for human communication.
Key tools and datasets for CA development and evaluation are identified.
Future research is needed for moral and security issues.

Conclusions:

This review provides a comprehensive overview of CA concepts, building blocks, and applications.
It categorizes CAs and outlines resources for their development and evaluation.
Identified future research areas focus on ethical and security challenges.

Keywords:

conversational agents

Human-centred Computing

Collaborative And Social Computing

Conversational Agents: Goals, Technologies, Vision And Challenges

human–agent interaction

smart environments