A proposed chatbot framework for COVID-19

Eslam Amer; Ahmed Hazem; Omar Farouk; Albert Louca; Youssef Mohamed; Michel Ashraf

doi:10.1109/MIUCC52538.2021.9447652

A proposed chatbot framework for COVID-19

Eslam Amer, Ahmed Hazem, Omar Farouk, Albert Louca, Youssef Mohamed, Michel Ashraf

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In recent years, chatbots have gained traction in a variety of fields, including health care, education, marketing, cultural heritage, support networks, entertainment, and many others. To manage the large number of user requests during pandemics, chatbots have become a must-have piece of equipment. In this paper, we present a smart chatbot system that can communicate with people and provide them with answers about the COVID-19. To tackle the popular role of question answering, our model used the pre-trained Google BERT language model. On top of the BERT, we add two architectural phases for the question-answering task. The first step is a text classification technique that employs the BERT Transformer to categorise text input into various categories based on the meaning of the words themselves. The actual application of the BERT model, as well as the query domain for answers, is the second step. Our proposed system is trained and tested on Stanford University's SQuAD V2.0, a well-known question-answering dataset.

Original language	English
Title of host publication	2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021
Editors	Ayman Bahaa-Eldin, Ashraf AbdelRaouf, Nada Ayman Mostafa Shorim, Randa Osama Mohamed Rashad, Shereen Essam Elbohy
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	263-268
Number of pages	6
ISBN (Electronic)	9781665412438
ISBN (Print)	9781665429535
DOIs	https://doi.org/10.1109/MIUCC52538.2021.9447652
Publication status	Published - 26 May 2021
Event	2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021 - Cairo, Egypt Duration: 26 May 2021 → 27 May 2021

Conference

Conference	2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021
Country/Territory	Egypt
City	Cairo
Period	26/05/21 → 27/05/21

Keywords

BERT
Chatbot
COVID-19
SQuAD.

Access to Document

10.1109/MIUCC52538.2021.9447652

Cite this

Amer, E., Hazem, A., Farouk, O., Louca, A., Mohamed, Y., & Ashraf, M. (2021). A proposed chatbot framework for COVID-19. In A. Bahaa-Eldin, A. AbdelRaouf, N. A. M. Shorim, R. Osama Mohamed Rashad, & S. E. Elbohy (Eds.), 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021 (pp. 263-268). Article 9447652 Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MIUCC52538.2021.9447652

Amer, Eslam ; Hazem, Ahmed ; Farouk, Omar et al. / A proposed chatbot framework for COVID-19. 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021. editor / Ayman Bahaa-Eldin ; Ashraf AbdelRaouf ; Nada Ayman Mostafa Shorim ; Randa Osama Mohamed Rashad ; Shereen Essam Elbohy. Institute of Electrical and Electronics Engineers Inc., 2021. pp. 263-268

@inproceedings{50280523394e4c8ea657f9a7ba0c3986,

title = "A proposed chatbot framework for COVID-19",

abstract = "In recent years, chatbots have gained traction in a variety of fields, including health care, education, marketing, cultural heritage, support networks, entertainment, and many others. To manage the large number of user requests during pandemics, chatbots have become a must-have piece of equipment. In this paper, we present a smart chatbot system that can communicate with people and provide them with answers about the COVID-19. To tackle the popular role of question answering, our model used the pre-trained Google BERT language model. On top of the BERT, we add two architectural phases for the question-answering task. The first step is a text classification technique that employs the BERT Transformer to categorise text input into various categories based on the meaning of the words themselves. The actual application of the BERT model, as well as the query domain for answers, is the second step. Our proposed system is trained and tested on Stanford University's SQuAD V2.0, a well-known question-answering dataset.",

keywords = "BERT, Chatbot, COVID-19, SQuAD.",

author = "Eslam Amer and Ahmed Hazem and Omar Farouk and Albert Louca and Youssef Mohamed and Michel Ashraf",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE. Noissn.; 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021 ; Conference date: 26-05-2021 Through 27-05-2021",

year = "2021",

month = may,

day = "26",

doi = "10.1109/MIUCC52538.2021.9447652",

language = "English",

isbn = "9781665429535",

pages = "263--268",

editor = "Ayman Bahaa-Eldin and Ashraf AbdelRaouf and Shorim, {Nada Ayman Mostafa} and {Osama Mohamed Rashad}, Randa and Elbohy, {Shereen Essam}",

booktitle = "2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

}

Amer, E, Hazem, A, Farouk, O, Louca, A, Mohamed, Y & Ashraf, M 2021, A proposed chatbot framework for COVID-19. in A Bahaa-Eldin, A AbdelRaouf, NAM Shorim, R Osama Mohamed Rashad & SE Elbohy (eds), 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021., 9447652, Institute of Electrical and Electronics Engineers Inc., pp. 263-268, 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021, Cairo, Egypt, 26/05/21. https://doi.org/10.1109/MIUCC52538.2021.9447652

A proposed chatbot framework for COVID-19. / Amer, Eslam; Hazem, Ahmed; Farouk, Omar et al.
2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021. ed. / Ayman Bahaa-Eldin; Ashraf AbdelRaouf; Nada Ayman Mostafa Shorim; Randa Osama Mohamed Rashad; Shereen Essam Elbohy. Institute of Electrical and Electronics Engineers Inc., 2021. p. 263-268 9447652.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - A proposed chatbot framework for COVID-19

AU - Amer, Eslam

AU - Hazem, Ahmed

AU - Farouk, Omar

AU - Louca, Albert

AU - Mohamed, Youssef

AU - Ashraf, Michel

PY - 2021/5/26

Y1 - 2021/5/26

N2 - In recent years, chatbots have gained traction in a variety of fields, including health care, education, marketing, cultural heritage, support networks, entertainment, and many others. To manage the large number of user requests during pandemics, chatbots have become a must-have piece of equipment. In this paper, we present a smart chatbot system that can communicate with people and provide them with answers about the COVID-19. To tackle the popular role of question answering, our model used the pre-trained Google BERT language model. On top of the BERT, we add two architectural phases for the question-answering task. The first step is a text classification technique that employs the BERT Transformer to categorise text input into various categories based on the meaning of the words themselves. The actual application of the BERT model, as well as the query domain for answers, is the second step. Our proposed system is trained and tested on Stanford University's SQuAD V2.0, a well-known question-answering dataset.

AB - In recent years, chatbots have gained traction in a variety of fields, including health care, education, marketing, cultural heritage, support networks, entertainment, and many others. To manage the large number of user requests during pandemics, chatbots have become a must-have piece of equipment. In this paper, we present a smart chatbot system that can communicate with people and provide them with answers about the COVID-19. To tackle the popular role of question answering, our model used the pre-trained Google BERT language model. On top of the BERT, we add two architectural phases for the question-answering task. The first step is a text classification technique that employs the BERT Transformer to categorise text input into various categories based on the meaning of the words themselves. The actual application of the BERT model, as well as the query domain for answers, is the second step. Our proposed system is trained and tested on Stanford University's SQuAD V2.0, a well-known question-answering dataset.

KW - BERT

KW - Chatbot

KW - COVID-19

KW - SQuAD.

UR - http://www.scopus.com/inward/record.url?scp=85111379653&partnerID=8YFLogxK

U2 - 10.1109/MIUCC52538.2021.9447652

DO - 10.1109/MIUCC52538.2021.9447652

M3 - Conference contribution

AN - SCOPUS:85111379653

SN - 9781665429535

SP - 263

EP - 268

BT - 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021

A2 - Bahaa-Eldin, Ayman

A2 - AbdelRaouf, Ashraf

A2 - Shorim, Nada Ayman Mostafa

A2 - Osama Mohamed Rashad, Randa

A2 - Elbohy, Shereen Essam

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021

Y2 - 26 May 2021 through 27 May 2021

ER -

Amer E, Hazem A, Farouk O, Louca A, Mohamed Y, Ashraf M. A proposed chatbot framework for COVID-19. In Bahaa-Eldin A, AbdelRaouf A, Shorim NAM, Osama Mohamed Rashad R, Elbohy SE, editors, 2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021. Institute of Electrical and Electronics Engineers Inc. 2021. p. 263-268. 9447652 doi: 10.1109/MIUCC52538.2021.9447652

A proposed chatbot framework for COVID-19

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this