Natural Language Processing and Cloud Computing in Disease Prevention and Management

Natural Language Processing and Cloud Computing in Disease Prevention and Management

Ricardo Ferreira, Pedro Gregório, Luis Coelho, Sara Seabra Reis
DOI: 10.4018/978-1-6684-5260-8.ch010
OnDemand:
(Individual Chapters)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

Recent studies show the high prevalence of the use of messaging platform and its growth trend, especially in younger populations (Figueroa Jacinto and Arndt 2018). Messaging apps are used not only to communicate and stay in touch with family and friends, but also to access services. Interactions with commercial purposes, such as making purchases, seeking out assistance and customer support, providing feedback or making reservations are already widely used, but legal and healthcare related areas also present prominent growth (Eeuwen 2017). In this chapter it is our objective to explore how technologies such as natural language processing, speech recognition, text-to-speech, machine learning, and cloud computing can be integrated to develop high quality chatbots for healthcare purposes. Additionally, we will cover an application case based on COVID-19 prevention and management.
Chapter Preview
Top

Human-Machine Interaction Based On Natural Language

Speech and language are the most natural way of interaction between humans and the idea of having a similar interaction with a machine has been around for many years. The first mention of a chatbot comes in 1950, when English computer scientist Alan Turing (1912-1954), a renowned British mathematician and computer scientist, and was also a pioneer in AI (Levesque 2017), asks the famous question “Can machines think?”. Created by Joseph Weizenbaum, in 1966, at the Massachusetts Institute of Technology, Eliza was the first chatbot to be publicly known. Eliza was able to communicate with humans based on hand-made scripts and accepting only text as input. This chatbot could not be said to understand the conversation, since it was limited to searching for appropriate responses, based on pattern matching, combined with a few of patterns, combined with some clever phrases (Shum, He, and Li 2018). One of ELIZA's applications was DOCTOR, which simulated a person-centered therapy approach in which a psychotherapist talks with a patient and devises responses based on what the patient himself tells him. Briefly, this form of therapy aimed to provide clients with a set of therapeutic conditions in which they can reconnect with their own real, individual experiences and valuation processes, moving away from a reliance on external judgments.

Complete Chapter List

Search this Book:
Reset