PROJECT REPORT

Submitted for the Degree of B.com honours in Accounting & Finance under

(THE UNIVERSITY OF CALCUTTA)

TITLE OF THE PROJECT

IMPACT OF CHAT GPT ON THE EDUCATION

SYSTEM.

SUBMITTED BY:

NAME OF THE CANDIDATE: R O H I T S H A W

REGISTRATION NUMBER: 235-1111-0558-20

CU ROLL NUMBER: 201235-21-0201

NAME OF THE COLLEGE: TARADEVI HARAKHCHAND KANKARIA JAIN COLLEGE

COLLEGE UID: 2020-745

SUPERVISED BY

NAME OF THE SUPERVISOR: MR. SURANJIT BASAK

NAME OF THE COLLEGE: TARADEVI HARAKHCHAND KANKARIA JAIN COLLEGE

MONTH & YEAR OF SUBMISSION: MAY 2023

 SUPERVISOR’S CERTIFICATE

This is to certify that Mr. Rohit Shaw a student of B.Com Honours in Accounting & Finance

(Tara Devi Harakhchand Kankaria Jain college) under the University of Calcutta has worked

under my supervision and guidance for his project work and prepared a Project Report with the

title “IMPACT OF CHAT GPT ON THE EDUCATION SYSTEM’’ the Project Report, which

he is submitting, is his genuine and original work to the best of my knowledge.

PLACE: KOLKATA

DATE:

Signature:

Name: M r . S u r a n j i t B a s a k

Designation: Professor (Guest lecturer)

Name of the college: Tara Devi Harakhchand

Kankaria Jain College
 STUDENT’S DECLARATION

I Hereby declare that the Project Work with the title “ IMPACT OF CHAT GPT ON THE

EDUCATION SYSTEM ” submitted by me for the partial fulfilment of the degree of B.Com

Honours in Accounting & Finance under the University of Calcutta is my original work and

has not been submitted earlier to any other University / Institution for the fulfilment of the

requirement for any course of study.

I also declare that no chapter of this manuscript in whole or in part has been incorporated in

this report for any earlier work done by others or by me . However extracts of any literature

which has been used for this report has been duly acknowledged providing details of such

literature in the reference.

Signature:

Name: ROHIT SHAW

Address: 297 GLT ROD BARANAGAR, KOLKATA -700036

CU Registration Number: 235-1111-0558-20

 ACKNOWLEDGEMENT

I would like to express my sincere gratitude to all the people without whose support this

project cannot be completed .

At the onset, I would like to thank “TARADEVI HARAKHCHAND KANKARIA JAIN

COLLEGE’’ for having provided me a great opportunity to pursue my Bachelor Degree in the

Institution.

I would further like to acknowledge the constant help and support of my project guide Mr.

SURANJIT BASAK who has given necessary suggestion, expert guidance and support in the

completion of this project.

I would also like to acknowledge the constant help and encouragement of my parents, who has

given their valuable suggestions, guidance and support.

THANKING YOU,

ROHIT SHAW.
 TABLE OF CONTENTS

Chapter No. Particulars Page No.

1 Introduction
1.1 Background of the study

1.2 Rationale of the study

1.3 Literature review

1.4 Objective of the study

1.5 Methodology

1.6 Limitations of the study

2 Conceptual Framework
2.1 National Scenario

2.2 International Scenario

3 Presentation of Data,
Analysis and Findings
3.1 Primary Survey

3.2 Secondary Survey

4 Conclusion and
Recommendations
4.1 Conclusion

4.2 Recommendation

Bibliography

Questionnaire
 CHAPTER - 1

INTRODUCTION
 1. INTRODUCTION

ChatGPT is an artificial intelligence (AI) Chabot developed by OpenAI and released in

November 2022. It is built on top of OpenAI's GPT-3.5 and GPT-4 foundational large

language models (LLMs) and has been fine-tuned (an approach to transfer learning) using

both supervised and reinforcement learning techniques. ChatGPT launched as a prototype

on November 30, 2022, and garnered attention for its detailed responses and articulate

answers across many domains of knowledge. Its propensity to confidently provide factually

incorrect responses has been identified as a significant drawback. In 2023, following the

release of ChatGPT, OpenAI's valuation was estimated at US$29 billion. The advent of the

Chabot has increased competition within the space, motivating the creation of Google's Bard

and Meta's LLaMA.

The original release of ChatGPT was based on GPT-3.5. A version based on GPT-4, the

newest OpenAI model, was released on March 14, 2023, and is available for paid

subscribers on a limited basis.ChatGPT was launched on November 30, 2022, by San

Francisco–based OpenAI, also the creator of DALL·E 2 and Whisper AI. The service was

initially free to the public and the company had plans to monetize the service later. By
December 4, 2022, ChatGPT had over one million users. In January 2023, ChatGPT reached

over 100 million users, making it the fastest growing consumer application to date.

1.1 BACKGROUND OF THE STUDY:

ChatGPT is a large language model developed by OpenAI, a research organization

founded by Elon Musk, Sam Altman, Greg Brockman, Ilya Sutskever, John Schulman,

and Wojciech Zaremba. The development of ChatGPT is part of a larger effort by

OpenAI to develop artificial intelligence technologies that can benefit humanity.

The first version of ChatGPT, GPT-1, was introduced in 2018. It was a language model

that used a neural network architecture to generate human-like text. GPT-1 was trained

on a large corpus of text data, including books, articles, and web pages, and was able to

generate coherent and contextually relevant responses to prompts.

In 2019, OpenAI released GPT-2, a more advanced version of the model that was

trained on a larger corpus of text data and had significantly more parameters. GPT-2

was able to generate even more coherent and contextually relevant responses and was

capable of tasks such as summarization, translation, and question-answering.

In 2020, OpenAI released GPT-3, the latest and most advanced version of the model to

date. GPT-3 has 175 billion parameters, making it the largest language model ever

created. It has the ability to perform a wide range of tasks, including language

translation, summarization, and question-answering, and can generate text that is

virtually indistinguishable from text written by humans.

ChatGPT is a variant of the GPT models that is specifically designed for use in Chatbot
 applications. It has been fine-tuned on a large corpus of conversational data and is able

to generate human-like responses to a wide range of prompts. ChatGPT has the

potential to revolutionize the field of chatbots by providing more engaging, responsive,

and personalized experiences for users.

1.2 RATIONALE OF YOUR STUDY:

The development of AI-powered language models like ChatGPT has revolutionized the

way we interact with technology and has the potential to transform many aspects of

society, including the education system. As such, studying the impact of ChatGPT on

the education system can provide valuable insights into the potential benefits and

drawbacks of this technology.

One potential benefit of using ChatGPT in education is its ability to provide

personalized learning experiences to students. By analyzing a student's learning history,

ChatGPT can generate tailored content and resources that address their individual needs

and learning styles. This could lead to improved student engagement and academic

performance, as well as a more efficient use of teachers' time.

Another potential benefit is the ability of ChatGPT to facilitate asynchronous learning.

With traditional classroom-based learning, students are often constrained by the pace of

the teacher and the class as a whole. However, with ChatGPT, students can learn at their

own pace and access educational content and resources at any time. This could be

particularly beneficial for students who are unable to attend traditional classes due to

geographic, social, or economic reasons.

Additionally, ChatGPT could help to overcome language barriers in education. With its

ability to understand and generate text in multiple languages, ChatGPT could facilitate

the learning of non-native speakers of a particular language. This could be particularly

relevant in multilingual contexts, where students may have different language

 backgrounds.

In conclusion, studying the impact of ChatGPT in the education system is important to

understand both the potential benefits and drawbacks of this technology. While it has

the potential to provide personalized and asynchronous learning experiences, facilitate

language learning, and improve efficiency, there are also concerns around the

replacement of human teachers, data privacy and security, and accuracy and reliability.

By understanding these issues, we can better harness the potential of ChatGPT in

education while addressing these challenges.

1.3 LITERATURE REVIEW:

Stephen Marche, (Atlantic Magazine 2023), found that there is no clear understanding

yet of the application essays that ChatGPT essays.

Daniel Herman (Nature Journal 2023) found that Catgut can usher the English language

of high schools will come to end.

Chris Stoke-walker (2023) found that the education provider needs to update and

enhance their critical thinking or reasoning.

Emma Bowman (NPR2023) found that the danger of student plagiarism will be on the

high and forever and that the output may be nonsensical text or authoritative toned one.

Joanna Stern (The Wall Street Journal 2023) found that cheating in high schools in

America in English using the tool to generate an essay is on.

Check Point (Research2023) found that Catgut was capable of writing phishing emails.
James Vincent (The Verge 2023) found the viral success of ChatGPT as the mainstream

AI. Economist Tyler Cowen found and expressed concerns about the effects of

democracy that ChatGPT would bring in.

Samantha Lock (The Guardian 2023) found that ChatGPT produces impressively

detailed human-like tests as an outcome. Derek Thompson found that Chat GPT is "the

generative AI eruption as it may change our mind with the way how we work.

Kelsey Piper (Vox2023) found Chat GPT as the general public’s first hand-on ―smart

enough assistant despite the flaws it has.

Derek Thompson (The Atlantic Magazine 2023) found that the ChatGPT as the

generative-AI eruption may change our minds, our work and the way we think about

what creativity is.

The information website (The New York Times 2023), Microsoft Bing, plans of

making optional ChatGPT functionality public as a search engine in the coming

times.

Stuart Cobbe, (England and Wales) tested the ChatGPT by questions to found that the

ChatGPT scored 42 per cent pass mark, though 55 was the pass percentage, fears the

advanced version will be too good to score out the limitation in passing exams.

Steven Minz (Inside Higher Ed (2023) found that ChatGPT is an ally as well as

advantageous support rather than an adversary since the AI could assist educational

goals like making reference lists, generating first drafts as well as solving equations. He
 found that the AI could even do the debugging to tutoring simultaneously assists to

evaluate, the answers with specific answers to questions asked.

Sam Altman (The New York Times2023) found that AIs support for humankind could

be so high that it is hard to believe the extent of intellectual support that AI could

deliver, which we cannot fathom explain in clear terms.

Cai GoGwilt CTO of Ironclad found that ChatGPT could summarize the changes

to legal documents. He found that ChatGPT betters in more creative responses

compared to similar language AIs.

LexisNexis and Min Chen (Legal research and Data Company), found ChatGPT to be

more useful for using Microsoft's Azure Cloud.

Abeba Birhane (Mozilla) found that ChatGPT produces song lyrics. Krishna Gade

CEO of Fiddler found that ChatGPT creates ―disruptions in web search‖ that are

long dominated by Google.

1.4 OBJECTIVE OF THE STUDY:

1. Determine the extent to which ChatGPT is perceived as a comprehensive conversational

technology capable of analyzing written and spoken.

2. To examine the relationship between ChatGPT and student engagement and participation

in class.

3. To investigate whether ChatGPT will play an important role in the education system in

the future.

1.5 METHODOLOGY:

Quantitative research is a research methodology that involves the collection and analysis

of numerical data to test hypotheses or answer research questions. It is used to study and

understand phenomena that can be measured objectively, such as physical or biological

processes, attitudes, behaviors, or social trends.

Quantitative research typically involves collecting data through methods such as

surveys, experiments, or statistical analysis of existing data. The data collected is

usually in the form of numerical values or statistics, such as percentages, means, or

correlations.

Once the data is collected, it is analyzed using various statistical methods to test

hypotheses or answer research questions. The analysis involves identifying patterns,

relationships, or differences in the data and using statistical tests to determine the

probability that these patterns or relationships are significant.

Quantitative research has several advantages over qualitative research. It allows

researchers to generalize findings to larger populations and to test hypotheses in a

 rigorous and objective manner. It is also less subject to bias and interpretation, as the

analysis is based on numerical data and statistical tests.

However, there are also some limitations to quantitative research. It may not provide a

comprehensive understanding of complex phenomena or the experiences and

perspectives of individuals. It can also be difficult to capture all the relevant variables or

to control for extraneous factors that may affect the outcomes.

Overall, quantitative research is a valuable methodology for testing hypotheses or

answering research questions in a rigorous and objective manner. It can provide valuable

insights into the relationships and patterns that exist in the data and can inform decision-

making in a wide range of fields, including science, social sciences, and business.

1.6 LIMITATIONS OF THE STUDY:

Some potential limitations of a study on the impact of ChatGPT on the education system:

Limited sample size: The study may have a small sample size, which can affect the

generalizability of the findings.

Selection bias: The sample used in the study may not be representative of the entire

population, leading to selection bias.

Lack of control group: Without a control group, it may be challenging to determine

whether any observed effects are due to the ChatGPT or other factors.

Short study duration: The study may be conducted over a short period, making it difficult

to assess the long-term impact of ChatGPT on the education system.

Dependency on user input: ChatGPT's performance and quality of responses depend on

the input provided by users, which may affect the results.

Ethical considerations: There may be ethical concerns regarding the use of AI in

education, such as bias, privacy, and data protection, which must be addressed in the study.

Technical limitations: The study may not account for technical limitations such as internet

connectivity, hardware specifications, or accessibility of technology, which can impact the

efficacy of ChatGPT in education.

 CHAPTER – 2
CONCEPTUAL FRAMEWORK
2.1 NATIONAL SCENARIO:
The impact of AI and machine learning on education in India is a complex and multifaceted
topic that requires a comprehensive understanding of the country's education system and the
role of technology in it. In this essay, we will explore the various ways in which AI and
machine learning are being used in education in India and the potential impact they could
have on the education system.

Firstly, AI and machine learning have the potential to provide personalized learning
experiences for students in India. With the help of intelligent tutoring systems and adaptive
learning platforms, students can receive tailored learning paths and recommendations based
on their individual needs and learning styles. This personalized approach to learning can help
students achieve better learning outcomes and improve their academic performance.

Furthermore, AI-powered Chabot’s and virtual assistants can provide students with instant
help and support. These Chabot’s can answer students' queries and doubts, provide feedback
on assignments, and offer suggestions for additional resources. This reduces the workload on
teachers and can help students learn more efficiently and effectively.

AI can also help in automating administrative tasks such as grading, attendance tracking, and
scheduling. This frees up teachers' time and enables them to focus on teaching and student
interaction. Automation can also improve the accuracy and reliability of administrative tasks,
reducing errors and delays in the education system.

Another significant impact of AI on education in India is the ability to improve the quality of
assessments. AI algorithms can analyse large volumes of data to identify patterns and insights
that humans may miss. This can lead to more accurate and objective assessments, reducing
the potential for biases and subjectivity in the grading process.

In addition to the benefits of AI in education, there are also concerns about its impact on jobs
in the education sector. Automation of administrative tasks could potentially lead to job
losses for support staff, while AI-powered Chabot’s and virtual assistants could reduce the
demand for human teachers. However, it is essential to note that AI and machine learning are
not intended to replace human teachers. Instead, they are meant to complement and enhance
their teaching capabilities.

Another concern about the impact of AI on education is the potential for bias and
discrimination in AI algorithms. If AI algorithms are not designed to account for cultural and
social differences, they could perpetuate existing inequalities in the education system.
Therefore, it is crucial to ensure that AI algorithms are designed and trained in a way that is
fair, transparent, and accountable.

Overall, the impact of AI on education in India is still being studied and evaluated. While AI
has the potential to transform education in India by providing personalized learning
experiences, automating administrative tasks, and improving the quality of assessments, it is
essential to consider the potential risks and challenges as well. It is crucial to ensure that AI is
developed and deployed in a way that aligns with India's unique social and cultural context
and does not perpetuate existing inequalities. Additionally, it is essential to invest in the
training and development of teachers and educators to ensure that they can effectively
integrate AI and machine learning into their teaching practices
2.2 INTERNATIONAL SCENARIO:
As an AI language model, CHATGPT has the potential to significantly impact the education
system in various ways on an international scale. Here are some potential impacts:

Enhanced Learning Experience: CHATGPT can improve the learning experience for students
by providing them with personalized and interactive learning experiences. It can help
students with their homework, answer their questions, and provide feedback on their
progress.

Accessibility and Inclusion: CHATGPT can help bridge the gap between students who have
access to quality education and those who don't. For instance, students who live in remote
areas or who have disabilities that limit their ability to access education can use CHATGPT
to access learning resources.

Language Learning: CHATGPT can help students learn new languages by providing them
with real-time translation and language practice. It can also help educators translate and
interpret teaching materials for students who speak different languages.

Teacher Support: CHATGPT can support teachers by providing them with resources and
information that can help them create effective lesson plans and assessments. It can also help
teachers with administrative tasks such as grading and record-keeping.

Distance Learning: CHATGPT can help facilitate distance learning by providing students
with virtual classrooms, online tutoring, and interactive educational materials.

However, it's worth noting that the implementation of AI in education must be done with care
and consideration. There are concerns about the ethical use of AI and the potential for bias
and discrimination. Therefore, it's essential to have clear policies and guidelines in place to
ensure that the use of AI in education is ethical and equitable for all students.
 CHAPTER – 3
PRESENTATION OF DATA, ANALYSIS
AND FINDINGS
3.1 PRIMARY SURVEY

According to the survey we can say that majority i.e. 60.8% of the people are from age group
19-23 and 21.6% of the people are from age group 24-28.

According to the survey, we can say that 41.3% are strongly aware of ChatGPT, which is less
than the half of the people from whom the survey were collected.
3.2 SECONDARY SURVEY

Artificial Intelligence (AI) has gained steam in recent years and is playing an increasingly
prominent role in almost every industry – including education. Whether its personalized
learning, automated grading, intelligent tutoring systems, or virtual learning assistants, AI
tools have become essential for educational institutions. They provide invaluable help leading
to cost savings and improved learning outcomes.

This blog will cover ChatGPT, an artificial intelligence (AI) assistant bot that has been on the
radar of educators, students, regulators, and education specialists since its release in
November 2022. Many are debating whether AI technology is suitable for the education
industry with optimism and caution. Learners and instructors are optimistic because they
believe the tool will improve their learning and teaching. However, on a cautionary note,
some experts believe that ChatGPT is a double-edged sword because it poses cheating
possibilities and exacerbates educational inequity. We will investigate these arguments by
evaluating both sides of the issue. We will focus on various sections of the education sector
(K-12 and Higher Education, testing & assessment, and Edtech/online learning) and their
functional applications. We will offer some solutions or best practices and evaluate
ChatGPT's overall disruptive capacity. We will utilize the Technological Trend Analysis and
Assessment framework from Evalueserve.
So, what are the primary use cases for ChatGPT, and how can it disrupt the traditional
learning process or threaten different incumbents in the Education and EdTech space?

First of all, ChatGPT can enhance personalized learning. The tool allows teachers to create
lesson plans and personalized materials in minutes instead of hours. Teachers can create a
more engaging and effective learning experience for their students. Because of its potential to
offer one-to-one instruction for learners and answer questions in real-time, ChatGPT can
challenge online tutoring solutions providers, such as Chegg, Think Academy, or Tutor.com.
Students will benefit as they can study at their own pace and focus on areas of improvement.

ChatGPT can provide targeted and tailored feedback as it evaluates learners' output. That
allows students to close educational gaps by identifying strengths and weaknesses that were
difficult to spot and address. Some online providers, like Coursera, already use AI to identify
frequently made mistakes learners make in their homework. Teachers can also create
customized tests and assessments using ChatGPT to generate content. The quasi-free nature
of the tool and its versatility might endanger the business model for some companies, such as
Chegg or Course Hero, which charge a fee for homework aid.

The AI chatbot helps students practice their reading comprehension skills by providing
tailored questions and feedback on their answers. The tool can improve critical thinking and
analytical skills if applied correctly. Assisting students in language learning is yet another
essential feature of ChatGPT. Learners can use the tool to understand grammar, undertake
vocabulary and pronunciation exercises, translate phrases, or provide real-time translations.
By using it extensively and leveraging it in more complex ways, learners can replace
established language learning apps such as Duo lingo, Babbel, or Mondly.

ChatGPT's most important use is its potential as a writing assistant. It allows students and
teachers to generate content ideas that inspire them to write essays on any topic. Moreover,
they can help create different drafts of the same essay and suggest improvement areas
regarding grammar, clarity, or conciseness. Thus, the tool allows users to overcome writer's
block and generate new perspectives on their chosen topic. The implications are enormous in
business and ethics. Using ChatGPT, content writers might rethink paying huge subscriptions
for AI copywriting tools such as Jasper or Copy.ai. AI. Writing assistants such as Grammarly
or Quill box might also face competition. The most significant implication is ethics.
According to Stephen Marche from the Atlantic, "The College Essay is dead" as ChatGPT
endangers the existence of the most essential tool in educational assessment: writing essays
and its learning implications for skills attainment. Study.com research shows 89% of students
aged 18+ admitted using ChatGPT for their homework assignments. The AI Chabot can
completely or partially write the essay for them, raising an alarm about cheating. Already
26% of educators in K-12 have identified at least one student cheating using ChatGPT.

Moreover, besides cheating, plagiarism is a major problem in academia. Another issue is

ChatGPT's ability to pass exams in different domains: the AI bot has passed a Wharton
Business School Exam, the United States Medical Licensing Exam, and four law school
courses at the University of Minnesota. AI tools can pass the history, art, microbiology,
physics, or mathematics exams. Academic dishonesty is also an issue because of ChatGPT's
ability to write scientific articles that could qualify for a first academic review. This worries
experts about its negative impact on research.

Considering this, it is no wonder some school districts (e.g., New York, Los Angeles, Seattle)
or universities worldwide (e.g., Sciences Po, Washington University) chose to ban the AI tool
from their networks and devices.
Plagiarism and cheating aside, ChatGPT is an excellent research assistant with powerful
"research skills" and the potential to summarize long texts or articles. Integrations with Bing
or Office 365 Co-pilot will make the AI tool more powerful and increase its overall usage.
Students and educators can reduce time spent reading, analysing, and understanding complex
academic materials. Even more, this is helpful for students and educators with ADHD or
other disorders that affect concentration. Still, overreliance on the tool might backfire; experts
caution that using AI in research should not replace critical thinking and research skills, and
students should still learn to evaluate and analyse information independently.

Another caveat with using ChatGPT as a research assistant is its limitations regarding data
accuracy, citation of sources, or even providing biased search results based on previous user
interactions. Despite generating academic texts, it only sometimes offers reliable and up-to-
date information: papers written using ChatGPT were proven factually incorrect. Being used
extensively on campus by students, education experts see the potential of lowering academic
standards, as professors need to identify and highlight in real-time what is human and what is
not in student assignments.

Similar to Google, Wikipedia, and the calculator, ChatGPT will continue to influence how
educators and students interact with knowledge and technology. This will impact the
education ecosystem. According to a recent Ipsos survey, education and learning will be the
industry most affected by AI in the next three to five years. Moreover, 77% of respondents
feel AI will enhance Education and learning. This is also supported by research conducted by
Global Market Insights, which determined that the current worldwide AI in Education market
size is $4Bn, but is expected to grow to $30Bn by 2032 due to rising usage in higher
education and corporate training.

ChatGPT is currently in the Trough of Disillusionment stage of the Gartner Hype Cycle. Still,
OpenAI, in partnership with Microsoft, aims to enhance its capabilities, improve
performance, and monetize future developments. ChatGPT4’s release in March 2023 has
already stirred controversy as the tool seems more accurate, reliable, and responds faster.
These improvements and increased integration with different productivity tools (Slack,
Zoom, and Salesforce) will increase adoption. So embracing the trend is better than fighting
it.
 CHAPTER - 4
CONCLUSION AND RECOMMENDATION
 4.1 CONCLUSION

As an AI language model, ChatGPT has the potential to significantly impact the education
system in a number of ways. One of the most notable ways in which ChatGPT can contribute
to education is through its ability to provide personalized and adaptive learning experiences
to students. By analysing the data on a student's learning habits and patterns, ChatGPT can
create customized learning plans that cater to their individual needs and learning styles.

Moreover, ChatGPT can serve as an excellent resource for students who need additional help
with their coursework. It can provide quick answers to queries and assist with understanding
complex concepts through clear and concise explanations.

Additionally, ChatGPT can be an effective tool for teachers, allowing them to automate
mundane tasks and focus on more important aspects of their role, such as lesson planning and
creative teaching strategies.

However, it is also important to note that ChatGPT should not replace human teachers
entirely. It is still essential for students to have face-to-face interaction with their educators
and peers to fully develop their social and emotional skills. Furthermore, the use of ChatGPT
should be carefully monitored to ensure that it does not perpetuate biases or reinforce
incorrect information.

Overall, the impact of ChatGPT on the education system has the potential to be significant,
but it is important to approach its use with caution and ensure that it is used in a way that
benefits students and teachers alike.
 4.2 RECOMMENDATION

As an AI language model, CHATGPT is constantly learning and improving, but there are
several recommendations that could help it provide better responses and interactions:

1. Improve accuracy:

One of the main challenges for CHATGPT is to improve its accuracy in responding to
questions and providing helpful information. While the model is already quite accurate, there
is always room for improvement. One way to achieve this is by continuing to train the model
on large and diverse datasets, especially in niche areas or domains where the model may not
have much experience.

In addition to training on more data, it is important to continuously monitor and evaluate

CHATGPT's responses to identify areas where it can be improved. This can be done by
analysing user feedback, conducting automated evaluations, and comparing its responses to
those of other language models or human experts.

Another way to improve accuracy is to incorporate external knowledge sources into

CHATGPT's responses. For example, CHATGPT could be trained to recognize and
incorporate information from structured databases, knowledge graphs, or other external
sources. This would allow it to provide more accurate and comprehensive answers to user
questions.

2. Enhance context awareness:

Providing context is critical to improving the accuracy of CHATGPT's responses. To enhance

context awareness, CHATGPT should be trained to identify and understand contextual
information in text, such as pronouns, named entities, and time references. It should also be
able to recognize and respond appropriately to changes in context during a conversation or
interaction.
One way to achieve this is by training the model on conversational datasets, where context is
constantly changing and evolving. This would allow CHATGPT to learn how to track context
and respond appropriately based on the current context of the conversation.

Another approach is to use contextual embedding’s or other contextual models that can
encode the context of a conversation or text passage into a fixed-length vector. This would
allow CHATGPT to better capture the nuances of context and provide more accurate and
personalized responses.

3. Develop emotional intelligence:

Another area where CHATGPT can be improved is in emotional intelligence. This involves
understanding and responding appropriately to emotional cues such as tone, sentiment, and
humour. Developing emotional intelligence would allow CHATGPT to provide more
personalized and engaging responses to users.

One way to achieve this is by training the model on datasets that contain emotional or
sentiment information, such as sentiment analysis datasets or datasets of online conversations
that include emotional content. This would allow CHATGPT to learn how to recognize and
respond appropriately to emotional cues in text.

Another approach is to incorporate sentiment analysis or emotion detection models into

CHATGPT's response generation process. This would allow the model to generate responses
that are tailored to the emotional state of the user, which could help to improve engagement
and user satisfaction.
 5. BIBLIOGRAPHY

1. Alavi, H., & Leidner, D. E. (2001). Review: Knowledge management and knowledge
management systems: Conceptual foundations and research issues. MIS Quarterly,
107-136.

2. Chen, G., & Liu, Y. (2020). Artificial intelligence in education: A review. Journal of
Educational Technology Development and Exchange (JETDE), 13(1), 1-18.

3. Dhawan, S. (2020). Online learning: A panacea in the time of COVID-19 crisis.

Journal of Educational Technology Systems, 49(1), 5-22.

4. Hodges, C., Moore, S., Lockee, B., Trust, T., & Bond, A. (2020). The difference
between emergency remote teaching and online learning. EDUCAUSE Review, 1-12.

5. Khatun, M., Paul, P., & Rahman, M. S. (2021). Artificial intelligence-based Chabot:
A promising tool for online education during the COVID-19 pandemic. Journal of
Educational Technology Development and Exchange (JETDE), 14(1), 1-13.
 QUESTIONARE

1. Have you heard of ChatGPT before this survey?

-strongly agree

-agree

-neither agree nor disagree

-disagree

-strongly disagree

2. Have you ever use ChatGPT for conversational or language analysis?

-Yes

-No

3. ChatGPT provides a more comprehensive conversation than other technologies due to

its ability to analyze written and spoken language?

-Strongly agree

-agree

-neutral

-disagree

-strongly disagree

4. Do you think ChatGPT has impacted our education system?

-Yes

-No
5. ChatGPT is providing students with personalized and real time support and making
information more accessible?

-Strongly agree

-agree

-neutral

-disagree

-strongly disagree

6. Can ChatGPT be used to enhance student’s academic experience?

-Strongly agree

-agree

-neutral

-disagree

-strongly disagree

7. ChatGPT has helped students develop critical thinking and problem solving skills?

-Strongly agree

-agree

-neutral

-disagree

-strongly disagree
8. ChatGPT has improved student engagement and participation in class?

-Strongly agree

-Agree

-Neutral

-Disagree

-Strongly disagree

9. Has ChatGPT caused a decline in the quality of education by replacing human

teachers?

-Yes

-No

10. ChatGPT has increased accessibility and flexibility in learning by providing 24/7
support to students?

-Strongly agree

-agree

-neutral

-disagree

-strongly disagree

11. Can ChatGPT Bes used to support students with learning disabilities?

-Yes

-No
12. In your opinion what role will ChatGPT play in the education system in future?

-Very important

-Somewhat important

-neutral

-somewhat unimportant

-very important