[TOPIC]

BY

[NAME]
[MATRICULATION NUMBER]

A PROJECT PROPOSAL SUBMITTED TO THE

DEPARTMENT OF COMPUTER AND INFORMATION
SCIENCES, COLLEGE OF SCIENCE AND TECHNOLOGY,
COVENANT UNIVERSITY OTA, OGUN STATE.

IN PARTIAL FULFILMENT OF THE REQUIREMENTS FOR

THE AWARD OF THE BACHELOR OF SCIENCE
(HONOURS) DEGREE IN COMPUTER SCIENCE

[DEFENCE MONTH, DEFENCE YEAR]

Note: This page has no number; the next pages have Roman numerals, and the last set has actual numbers.
British English only. APA 7 for citations and references.
 ACKNOWLEDGEMENTS

{This is a sample} My most profound gratitude goes to Almighty God, who has kept me and
sustained me from the very start of my degree until now. To Him be all the glory.

Note: This should not be more than two paragraphs

ii
 TABLE OF CONTENTS

CONTENT PAGES
ACKNOWLEDGEMENTS ii
TABLE OF CONTENTS iii
LIST OF FIGURES vi
LIST OF TABLES vii
ABBREVIATIONS viii
ABSTRACT Error! Bookmark not defined.
CHAPTER ONE: INTRODUCTION 1
1.1. Background Information 1
1.2. Statement of the Problem 1
1.3. Aim and Objectives of the Study 1
1.4. Methodology 2
1.5. Significance of the Study 3
1.6. Limitation of the Study Error! Bookmark not defined.
1.7. Project Outline 3
CHAPTER TWO: LITERATURE REVIEW 4
2.1. Preamble 4
2.2. Review of Chatbots 4
2.3. Review of Chatbots for University Services 4
2.4. Review of Relevant Concepts 5
2.4.1. Artificial Intelligence (AI) 5
2.4.2. Machine Learning 5
2.4.3. Natural Language Processing (NLP) 5
2.4.4. Deep Learning 6
2.4.5. Neural Network 6
2.4.6. Transformers 6
2.5. Review of Related Methods 7
2.5.1. Intent Recognition 8
2.5.2. Entity Recognition Error! Bookmark not defined.
2.5.3. Semantic Similarity Error! Bookmark not defined.
2.5.4. Pattern Matching Error! Bookmark not defined.
iii
 2.5.5. Response Generation Error! Bookmark not defined.
2.6. Review of Existing Systems 8
2.6.1. Erasmus-AI 8
2.6.2. Eaglebot Error! Bookmark not defined.
2.6.3. Question Answering based University Chatbot using Sequence to
Sequence Model Error! Bookmark not defined.
2.6.4. ChatGPT Error! Bookmark not defined.
2.7. Summary of Literature Review 8
CHAPTER THREE: SYSTEM ANALYSIS AND DESIGN Error! Bookmark not defined.
3.1. Preamble Error! Bookmark not defined.
3.2. The Proposed System Error! Bookmark not defined.
3.3. Requirement Analysis Error! Bookmark not defined.
3.3.1. Functional Requirements Error! Bookmark not defined.
3.4. Data Collection Error! Bookmark not defined.
3.4.1. Student Handbook Error! Bookmark not defined.
3.4.2. University Website Error! Bookmark not defined.
3.4.3. Non-Functional Requirements Error! Bookmark not defined.
3.5. Physical Design Error! Bookmark not defined.
3.5.1. Generated Pretrained Transformer (GPT) Model Architecture Error!
Bookmark not defined.
3.5.2. The Proposed System Architecture Error! Bookmark not defined.
3.6. Logical Design Error! Bookmark not defined.
3.6.1. Use Case Diagram Error! Bookmark not defined.
3.6.2. Activity Diagram Error! Bookmark not defined.
3.6.3. Sequence Diagram Error! Bookmark not defined.
3.7. Conceptual Design Error! Bookmark not defined.
CHAPTER FOUR: SYSTEM IMPLEMENTATION AND EVALUATION Error!
Bookmark not defined.
4.1. Preamble Error! Bookmark not defined.
4.2. System Requirements Error! Bookmark not defined.
4.2.1. Hardware Requirements Error! Bookmark not defined.

iv
 4.2.2. Software Requirements Error! Bookmark not defined.
4.3. Implementation Tools Error! Bookmark not defined.
4.3.1. Python Error! Bookmark not defined.
4.3.2. Telegram BotFather Error! Bookmark not defined.
4.3.3. PyCharm Error! Bookmark not defined.
4.4. Development Methodology Error! Bookmark not defined.
4.5. Evaluation of the System Error! Bookmark not defined.
4.5.1. Evaluation Discussion Error! Bookmark not defined.
4.6. Program Modules and Interfaces Error! Bookmark not defined.
4.6.1. Telegram Interface Error! Bookmark not defined.
CHAPTER FIVE: SUMMARY, RECOMMENDATION AND CONCLUSION Error!
Bookmark not defined.
5.1. Summary Error! Bookmark not defined.
5.2. Recommendations Error! Bookmark not defined.
5.3. Conclusion Error! Bookmark not defined.
REFERENCES 9

[Note:
1. This table is not auto-generated. You will need to format the generated table
manually to get this outcome. Ensure you save your work well or convert it to PDF
before going to print
2. Use the Video sent earlier to learn how to format your document before generating
this
3. This table should be 1.5 line spacing, likewise your entire work.
4. Check other properties such as spacing before and after, the font type and size,
using your MS Word so you are appropriately guided
5. This table should not have more levels than is stated here.
]

v
 LIST OF FIGURES

FIGURES TITLES OF FIGURES PAGES

2.1 Broad categorization of a chatbot and implementation techniques 9

2.2 Transformer Model Architecture 17

3.1 GPT Architecture 31

3.2 Proposed System Architecture 32

3.3 Use case diagram for proposed System 33

3.4 Activity diagram for proposed System 34

3.5 Sequence diagram for proposed System 35

3.6 Entity Relationship Diagram 36

4.1 User Test Question 1 41

4.2 User Test Question 2 41

4.3 User Test Question 3 42

4.4 User Test Question 4 42

4.5 User Test Question 5 43

4.6 User Test Question 6 44
4.7 Telegram Chatbot Interface 1 46
4.8 Telegram Chatbot Interface 2 46

[Note: This is not auto-generated. You generate and then manually format it into an
invisible table. Same with your List of Tables]

vi
 LIST OF TABLES

TABLES TITLES OF TABLES PAGES

1.1 Objectives-Methodology Mapping Table 4

2.1 Comparison of the three major transformer models 19

4.1 Hardware Requirements Table 38

4.2 Software Requirements Table 39

vii
 ABBREVIATIONS

API Application Programming Interface

AI Artificial Intelligence

NLP Natural Language Processing

GPT Generative Pretrained Transformer

HCI Human Computer Interaction

AIML Artificial Intelligence Mark-up Language

ML Machine Learning

NLU Natural Language Understanding

NLG Natural Language Generation

DNN Deep Neural Network

DRL Deep Reinforcement Learning

RNN Recurrent Neural Network

BERT Bidirectional Encoder Representation from Transformers

KB Knowledge Base

SA Semantic Analysis

NER Named Entity Recognition

viii
 1.CHAPTER ONE

INTRODUCTION

1.1. Background Information

Artificial Intelligence (AI) has transformed our everyday habits through the facilitation of
advanced software and devices known as intelligent agents. These agents are proficient at
executing diverse tasks. Among these, chatbots, a fusion of artificial intelligence and human-
computer interaction (HCI), are an increasing technology (Bansal & Khan, 2018). Computer
programs, called chatbots, are software applications designed to emulate human language—
both written and spoken—during interactions with individuals (Kim et al., 2018).

1.2. Statement of the Problem

Students face various problems in today's dynamic university environment, including

difficulties with administrative procedures, communication breakdowns, and information
availability. (Nguyen et al., 2021) discussed how admissions staff, who were regularly
overwhelmed with questions from applicants, were affected by the regular inquiries from
potential students.

1.3. Aim and Objectives of the Study

The aim of this study is to develop an intelligent chatbot that can provide seamless access to
university services and information retrieval. The chatbot will leverage natural language
processing techniques to engage in human-like dialogue, understand user queries, and deliver
accurate and personalized responses. The objectives include:

(i) To determine the requirements needed for an intelligent chatbot.

(ii) To collect data and prepare the university dataset for training the chatbot.
(iii) To design the components of the intelligent chatbot.
(iv) To implement a model of the intelligent chatbot.
(v) To evaluate the performance of the chatbot.

1
1.4. Methodology

This explains the approach used to conduct the project. It provides a description of the
methods, processes, and tools used.

(i) Examine previously published works on existing systems.

(ii) Collect data from the university website, student handbook, and FAQs.
Cleaning and pre-processing the data using Panda and Natural Language
Processing tools, i.e., Natural Language Toolkit and Spacy.

[NOTE: EACH METHODOLOGY PER OBJECTIVE SHOULD BE PRESENTED IN A

DETAILED WAY TO SHOW YOU PROPERLY UNDERSTAND THE STEPS AND
PROCEDURES INVOLVED AND THEY ARE VIABLE]

Table 1.1: Objectives-Methodology Mapping Table

S/N OBJECTIVES METHODOLOGY

1. To determine the requirements Literature Review and Existing Systems
needed for an intelligent (i) Examine previously
chatbot. published works on
existing systems.
(ii) Search for academic
papers, articles, and
journals on intelligent
chatbots, focusing on the
requirements and features
of successful chatbot
systems.
2. To collect data and prepare the Data Gathering and Pre-processing
university dataset for training (i) Identify the sources of data,
the chatbot. such as the university
website, student handbook,
FAQs.
(ii) Extract data from these
sources, including
information on courses,
admission procedures,
campus facilities, student
services, academic policies.

2
 (iii) Remove any irrelevant
information, correct errors,
and standardize the format
of the data.

1.5. Significance of the Study

This study suggests techniques for generating intelligent responses and improving user
experience on university chatbot through the personalization of machine learning and natural
language processing.

(i) There is provision of timely information and services to faculty, staff, and
students.

1.6. Project Outline

This research is broken down into five chapters. The first chapter will cover the project's
background, the problem statement, the study's aims and objectives, the implementation
method, the study's significance, and its limitations.

[Note:

1. There must be a preamble before every form of listing or another heading. That is
the pattern in every chapter.
2. Note the name of the headings here. You can have more, but these must be
included.
3. You do not need to put the limitation of the study in your Mini Defence Chapter
One, but it will be there for your final defence since that is a summary of the entire
work.
4. Note the way the Table is formatted and the placement of the Table caption.
5. Check other properties on MS Word. You can also copy and paste into this.
6. Your methodology for your Mini defence would be more detailed than this. The
pattern here is okay for your final defence only.
]

3
 2.CHAPTER TWO

LITERATURE REVIEW

2.1. Preamble

The introduction of digital solutions has brought about a revolution in the education sector,
as institutions use them more frequently to improve communication and expedite information
sharing. This study aims to develop a chatbot specifically designed to handle university
information and address the current challenges of students and faculty with information
retrieval.

2.2. Review of Chatbots

Chatbots are interactive or conversational agents that respond to users promptly. In today's
technologically advanced society, chatbots are increasingly utilised to enhance student
engagement through communication and numerous other activities, mainly dependent on
online platforms (Okonkwo & Ade-Ibijola, 2021). Figure 2.1 shows the different categories
of chatbots.

Figure 2.1: Broad categorization of a chatbot and implementation techniques

Source: https://www.bing.com/images/search

In the year 1950, Alan Turing presented an inquiry into the possibility of a computer program
engaging in dialogue with a collective of individuals without them detecting that their
conversational counterpart was non-human.

2.3. Review of Chatbots for University Services

Sharma (2015) suggested a chatbot system for college inquiries that was created using
artificial intelligence algorithms. The bot interprets user messages and evaluates user queries.
The proposed system is a web-based application with two user types: regular and admin
users. The artificial intelligence algorithms employed by the system will provide relevant
responses to the user.

4
 Existing works highlighted two major approaches to developing chatbots depending on
techniques and algorithms used: Pattern matching and Machine learning approaches. The
machine learning approach is applied in this research project by using natural language
processing (NLP) to extract the content from user input.

2.4. Review of Relevant Concepts

The concepts that are related to this project are discussed in this section.

2.4.1. Artificial Intelligence (AI)

Artificial intelligence is a specific domain in computer science that is committed to

advancing machines with the capacity to imitate human behaviour and cognitive processes.

Currently, artificial intelligence is arguably the most fascinating and difficult area of study.
Artificial Intelligence will soon take the spotlight and influence every aspect of our daily
lives (Khanna et al., 2015).

2.4.2. Machine Learning

Machine learning is the discipline of study that enables computers to learn without explicit
programming.

The domains of supply chain management, consumer services, and the diagnosis of intricate
system malfunctions are among the many industries that have been greatly impacted by
machine learning (Pugliese et al., 2021).

2.4.3. Natural Language Processing (NLP)

The area of artificial intelligence known as Natural language processing is concerned with
how computers can manipulate text or speech in natural language.

They consist of Natural Language Understanding, which advances the goal of

comprehending a text, and Natural Language Generation, which presents the duty of
generating the text that is typically performed by Artificial Neural Networks (ANNs)
(Adamopoulou & Moussiades, 2020b).

(i) Natural Language Understanding (NLU)

5
It serves as a technique for integrating natural user interfaces, such as chatbots, into practical
applications. Natural language understanding (NLU) aims to comprehend user inputs
expressed in natural language, even if they are unstructured, and deliver appropriate
outcomes based on the user's intent.

(ii) Natural Language Generation (NLG)

It is a component of Natural Language Processing that uses non-linguistic representations to

produce text responses in natural language as a result of the semantic web paradigm's
machine-processability. Natural Language Generation is regarded as a semantic/conceptual
representation of recent research (Atmauswan & Abdullahi, 2022).

2.4.4. Deep Learning

Deep learning has become increasingly important in data processing and analysis recently.
Highly efficient reading and analysis of input data is achieved by neural networks. To
develop a chatbot with a deep learning algorithm that can accurately mimic human behaviour
Artificial Intelligence is required.

2.4.5. Neural Network

Neural networks are massively parallel distributed processors with an innate ability to store
and make use of experimental knowledge. The network learns through experience, just like
the human brain does, and the strength of its connections stores the knowledge it gains.

2.4.6. Transformers

Transformer is an encoder-decoder architecture that illustrates an extremely efficient neural

network architecture for natural language processing applications.

In the same manner, the decoder network has six layers as well. It does, however, consist of
three blocks, the first and third of which are essentially identical to the two blocks found in
the encoder network. (Csaky, 2019). The transformer model architecture is shown in Figure
2.2.

6
 Figure 2.2: Transformer Model Architecture

Source: https://www.bing.com/

The three major transformer-based models are:

(i) Bidirectional Encoder Representation from Transformers (BERT): It is a

bidirectional deep Transformer encoder that can recognize and pick up word
structures with context awareness (Wu et al., 2024). It is a technique for pre-
training language representations.
(ii) Generative pre-training (GPT): It was the first model to use unidirectional
transformers as the foundation for the GPT of language models, showcasing
the remarkable potential of pre-training approaches for a range of downstream
applications (Fitria, 2023).
(iii) Text-to-Text Transformer (T5): T5 uses a text-to-text format with up to
billions of parameters, pre-trained on a sizable dataset taken from the internet,
to handle a variety of natural language understanding tasks. Table 2.1
compares the three transformer models.

Table 2.2: Comparison of the three major transformer models

S/N FEATURE BERT T5 GPT

1. Model Type Transformer-based Transformer-based Transformer-
encoder encoder-decoder based decoder
2. Pre-training Masked Language Seq2Seq Tasks Autoregressive
Objective Model (MLM) Language Model

The comparison above shows that GPT-based models may be particularly suitable for
developing a chatbot due to their ability to generate natural language, coherent text, and
understanding of context.

2.5. Review of Related Methods

The methods that have been used in existing works are discussed in this section.

7
2.5.1. Intent Recognition

2.6. Review of Existing Systems

This section discusses the existing chatbot systems and the methods used in their
development.

2.6.1. Erasmus-AI

ERASMUS is a Facebook chatbot designed to provide comprehensive answers to questions

about colleges.

2.7. Summary of Literature Review

The literature review examines how chatbots are emerging in educational environments, with
an emphasis on how they are being used to provide information about universities. The
primary focus emphasizes how technology is becoming more important in academic settings
for improving communication and expediting information access. The proposed chatbot will
make use of machine learning and natural language processing for development.

[Note

1. Firstly, it is obvious this has been hugely edited, this is not the expected length of
your LR.
2. Note the numbering pattern.
3. Your headings should not go beyond the third level.
4. For your numbering, especially if you have to number under another numbering
the order is this: (i), (A), (1), (a). You start in that order and list the list under it in
that order.
5. There should be a preamble before every list
6. Every Table and figure must be mentioned before it appears in your writeup
7. Note the placement of the caption for the Figure, different from that of the Table.
8. Do not group Tables and Figures together when mentioning them, state them
individually, even in Chapter 3 and Chapter 4.
9. Check other properties on MS Word to be sure you are on the right path.
10. Your heading titles would defer from this one depending on your work.
]
8
 REFERENCES

Adamopoulou, E., & Moussiades, L. (2020a). An Overview of Chatbot Technology. In IFIP

Advances in Information and Communication Technology: Vol. 584 IFIP (Issue June).
Springer International Publishing. https://doi.org/10.1007/978-3-030-49186-4_31

Adamopoulou, E., & Moussiades, L. (2020b). Chatbots: History, technology, and

applications. Machine Learning with Applications, 2(October), 100006.
https://doi.org/10.1016/j.mlwa.2020.100006

Agus Santoso, H., Anisa Sri Winarsih, N., Mulyanto, E., Wilujeng Saraswati, G., Enggar
Sukmana, S., Rustad, S., Syaifur Rohman, M., Nugraha, A., & Firdausillah, F. (2018).
Dinus Intelligent Assistance (DINA) Chatbot for University Admission Services. In
Proceedings - 2018 International Seminar on Application for Technology of
Information and Communication: Creative Technology for Human Life, iSemantic 2018.
https://doi.org/10.1109/ISEMANTIC.2018.8549797

Al-Amin, M., Shazed Ali, M., Salam, A., Khan, A., Ali, A., Ullah, A., Alam, N., &
Chowdhury, S. K. (2024). History of generative Artificial Intelligence (AI) chatbots:
past, present, and future development. February.
https://doi.org/10.48550/arXiv.2402.05122

Atmauswan, P. S., & Abdullahi, A. M. (2022). Intelligent Chatbot For University

Information System Using Natural Language Approach. Albukhary Social Business
Journal, 3(2), 59–64. https://doi.org/10.55862/asbjv3i2a007

Bahani, M., Ouaazizi, A. El, & Maalmi, K. (2023). The effectiveness of T5, GPT-2, and
BERT on text-to-image generation task. Pattern Recognition Letters, 173(June), 57–63.
https://doi.org/10.1016/j.patrec.2023.08.001

Bansal, H., & Khan, R. (2018). A Review Paper on Human Computer Interaction.
International Journal of Advanced Research in Computer Science and Software
Engineering, 8(4), 53. https://doi.org/10.23956/ijarcsse.v8i4.630

Brandtzaeg, P. B., & Følstad, A. (2017). Why people use chatbots. Lecture Notes in
Computer Science (Including Subseries Lecture Notes in Artificial Intelligence and

9
 Lecture Notes in Bioinformatics), 10673 LNCS(November), 377–392.
https://doi.org/10.1007/978-3-319-70284-1_30

Chamorro-Atalaya, O., Huarcaya-Godoy, M., Durán-Herrera, V., Nieves-Barreto, C., Suarez-

Bazalar, R., Cruz-Telada, Y., Alarcón-Anco, R., Huayhua-Mamani, H., Vargas-Diaz,
A., & Balarezo-Mares, D. (2023). Application of the Chatbot in University Education:
A Systematic Review on the Acceptance and Impact on Learning. International Journal
of Learning, Teaching and Educational Research, 22(9), 156–178.
https://doi.org/10.26803/ijlter.22.9.9

Chen, Y., Li, L., Li, W., Guo, Q., Du, Z., & Xu, Z. (2023). AI Computing Systems An
Application-Driven Perspective. https://doi.org/https://doi.org/10.1016/C2021-0-02950-
3

Choudhary, P., & Chauhan, S. (2023). An intelligent chatbot design and implementation
model using long short-term memory with recurrent neural networks and attention
mechanism. Decision Analytics Journal, 9(October), 100359.
https://doi.org/10.1016/j.dajour.2023.100359

Costa, P. (2018). Conversing with personal digital assistants: On gender and artificial
intelligence. Journal of Science and Technology of the Arts, 10(3 Special Issue), 59–72.
https://doi.org/10.7559/citarj.v10i3.563

Csaky, R. (2019). Deep Learning Based Chatbot Models. ArXiv Preprint ArXiv:1908.08835,
November 2017. https://doi.org/10.13140/RG.2.2.21857.40801

Deepika, N. M., Bala, M. M., & Kumar, R. (2021). WITHDRAWN: Design and
implementation of intelligent virtual laboratory using RASA framework. Materials
Today: Proceedings. https://doi.org/10.1016/j.matpr.2021.01.226

Devlin, J., Chang, M.-W., Lee, K., Google, K. T., & Language, A. I. (2018). BERT: Pre-
training of Deep Bidirectional Transformers for Language Understanding. Naacl-Hlt
2019, Mlm, 4171–4186. https://aclanthology.org/N19-1423.pdf

Dhyani, M., & Kumar, R. (2019). An intelligent Chatbot using deep learning with
Bidirectional RNN and attention model. Materials Today: Proceedings, 34(June 2020),
817–824. https://doi.org/10.1016/j.matpr.2020.05.450
10
Fernandes, A. (2018). NLP, NLU, NLG and how Chatbots work. Medium.
https://chatbotslife.com/nlp-nlu-nlg-and-how-chatbots-work-dd7861dfc9df

H V, S., & S, D. S. (2022). Implementation of an Educational Chatbot using Rasa

Framework. International Journal of Innovative Technology and Exploring
Engineering, 11(9), 29–35. https://doi.org/10.35940/ijitee.g9189.0811922

hassan, walaa, & elsayed, ahmed. (2023). An Interactive Chatbot for College Enquiry.
Journal of Computing and Communication, 2(1), 20–28.
https://doi.org/10.21608/jocc.2023.282081

Hien, H. T., Cuong, P. N., Nam, L. N. H., Nhung, H. L. T. K., & Thang, L. D. (2018).
Intelligent assistants in higher-education environments: The FIT-EBOt, a chatbot for
administrative and learning support. ACM International Conference Proceeding Series,
December, 69–76. https://doi.org/10.1145/3287921.3287937

Hill, J., Randolph Ford, W., & Farreras, I. G. (2015). Real conversations with artificial
intelligence: A comparison between human-human online conversations and human-
chatbot conversations. Computers in Human Behavior, 49, 245–250.
https://doi.org/10.1016/j.chb.2015.02.026

Jehangir, B., Radhakrishnan, S., & Agarwal, R. (2023). A survey on Named Entity
Recognition — datasets, tools, and methodologies. Natural Language Processing
Journal, 3(10), 100017. https://doi.org/10.1016/j.nlp.2023.100017

Khanna, A., Pandey, B., Vashishta, K., Kalia, K., Pradeepkumar, B., & Das, T. (2015). A
Study of Today’s A.I. through Chatbots and Rediscovery of Machine Intelligence.
International Journal of U- and e-Service, Science and Technology, 8(7), 277–284.
https://doi.org/10.14257/ijunesst.2015.8.7.28

Khin, N. N., & Soe, K. M. (2020). Question Answering based University Chatbot using
Sequence to Sequence Model. Proceedings of 2020 23rd Conference of the Oriental
COCOSDA International Committee for the Co-Ordination and Standardisation of
Speech Databases and Assessment Techniques, O-COCOSDA 2020, 55–59.
https://doi.org/10.1109/O-COCOSDA50338.2020.9295021

11
Kim, J., Lee, H. G., Kim, H., Lee, Y., & Kim, Y. G. (2018). Two-step training and mixed
encoding-decoding for implementing a generative chatbot with a small dialogue corpus.
2IS and NLG 2018 - Workshop on Intelligent Interactive Systems and Language
Generation, Proceedings of the Workshop, 31–35. https://doi.org/10.18653/v1/w18-
6707

Mahesh, B. (2020). Machine Learning Algorithms - A Review. International Journal of

Science and Research, 9(1), 381–386. https://doi.org/10.21275/ART20203995

Milani Fitria, K. (2023). Information Retrieval Performance in Text Generation using

Knowledge from Generative Pre-trained Transformer (GPT-3). Jambura Journal of
Mathematics, 5(2), 327–338. https://doi.org/10.34312/jjom.v5i2.20574

Nguyen, T. T., Le, A. D., Hoang, H. T., & Nguyen, T. (2021). NEU-chatbot: Chatbot for
admission of National Economics University. Computers and Education: Artificial
Intelligence, 2(December), 100036. https://doi.org/10.1016/j.caeai.2021.100036

Okonkwo, C. W., & Ade-Ibijola, A. (2021). Chatbots applications in education: A systematic

review. Computers and Education: Artificial Intelligence, 2, 100033.
https://doi.org/10.1016/j.caeai.2021.100033

Prieto, A., Prieto, B., Ortigosa, E. M., Ros, E., Pelayo, F., Ortega, J., & Rojas, I. (2016).
Neural networks: An overview of early research, current frameworks and new
challenges. Neurocomputing, 214, 242–268.
https://doi.org/10.1016/j.neucom.2016.06.014

Pugliese, R., Regondi, S., & Marini, R. (2021). Machine learning-based approach: Global
trends, research directions, and regulatory standpoints. Data Science and Management,
4(November), 19–29. https://doi.org/10.1016/j.dsm.2021.12.002

Rana, M. (2019). EagleBot: A Chatbot Based Multi-Tier Question Answering System for
Retrieving Answers From Heterogeneous Sources Using BERT. 54.
https://digitalcommons.georgiasouthern.edu/etd

Ranoliya, B. R., Raghuwanshi, N., & Singh, S. (2017). Chatbot for university related FAQs.
2017 International Conference on Advances in Computing, Communications and
Informatics, ICACCI 2017, 2017-Janua(September 2017), 1525–1530.
12
 https://doi.org/10.1109/ICACCI.2017.8126057

Reimers, N., & Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using siamese
BERT-networks. EMNLP-IJCNLP 2019 - 2019 Conference on Empirical Methods in
Natural Language Processing and 9th International Joint Conference on Natural
Language Processing, Proceedings of the Conference, 3982–3992.
https://doi.org/10.18653/v1/d19-1410

Shah, H., Warwick, K., Vallverdú, J., & Wu, D. (2016). Can machines talk? Comparison of
Eliza with modern dialogue systems. Computers in Human Behavior, 58, 278–295.
https://doi.org/10.1016/j.chb.2016.01.004

Sharma, R. M. (2015). Chatbot based College Information System. UGC Listed Journal]
RRIJM, 109(03), 109–112. www.rrjournals.com[UGC

Shinde, P., Boraste, P., Datir MVPS, S., & Coe, K. (2021). Chatbot Using Natural Language
Processing. 10(8), 2394–0697. https://www.researchgate.net/publication/354523522

Singh, L. K., & Khanna, M. (2023). Introduction to artificial intelligence and current trends.
In Innovations in Artificial Intelligence and Human-Computer Interaction in the Digital
Era. Elsevier Inc. https://doi.org/10.1016/B978-0-323-99891-8.00001-2

Singh, R., Paste, M., Shinde, N., Patel, H., & Mishra, N. (2018). Chatbot using TensorFlow
for small Businesses. Proceedings of the International Conference on Inventive
Communication and Computational Technologies, ICICCT 2018, 1614–1619.
https://doi.org/10.1109/ICICCT.2018.8472998

Singh, S., Darbari, H., Bhattacharjee, K., & Verma, S. (2016). Open source NLG systems: A
survey with a vision to design a true NLG system. International Journal of Control
Theory and Applications, 9(10), 4409–4421.

Thakkar, J., Raut, P., Doshi, Y., & Parekh, K. (2018). Erasmus AI Chatbot. International
Journal of Computer Sciences and Engineering, 6(10), 498–502.
https://doi.org/10.26438/ijcse/v6i10.498502

Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., &
Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information
Processing Systems, 2017-Decem(Nips), 5999–6009.
13
Wang, P. (2019). On Defining Artificial Intelligence. Journal of Artificial General
Intelligence, 10(2), 1–37. https://doi.org/10.2478/jagi-2019-0002

Wu, T., Wang, M., Xi, Y., & Zhao, Z. (2024). Intent recognition model based on sequential
information and sentence features. Neurocomputing, 566(October 2023), 127054.
https://doi.org/10.1016/j.neucom.2023.127054

Zhang, R., & El-Gohary, N. (2022). Natural language generation and deep learning for
intelligent building codes. Advanced Engineering Informatics, 52(March), 101557.
https://doi.org/10.1016/j.aei.2022.101557

Zheng, S., Yahya, Z., Wang, L., Zhang, R., & Hoshyar, A. N. (2023). Multiheaded deep
learning chatbot for increasing production and marketing. Information Processing and
Management, 60(5), 103446. https://doi.org/10.1016/j.ipm.2023.103446

14