Development of an Intelligent and Robust Chat-bot Application for

Enhancing the Teaching and Learning for Online

1. Introduction:
The COVID-19 pandemic has effected almost every aspects of life and teaching and learning is no
exception. Although there is no better option to face-to-face in-class room teaching and learning,
but online teaching has evolved as an alternative teaching and learning mechanism. There is a lot
of mental and physical stress involved in this mode of teaching. The problem becomes more
serious with intermittent and unreliable Internet connectivity in many parts of the country. This
unreliable internet connectivity restricts the students to get their doubts clarified during the online
class and when the students are ready, the teacher may not be always available. Online education
has witnessed significant growth in recent years, driven by advancements in technology and the
increasing demand for flexible learning options. While it offers numerous advantages, such as
accessibility and convenience, it also presents a set of challenges that impact both educators and
learners.

1.1 challenges in online teaching and learning:

1. Access to Technology: One of the primary challenges is the unequal access to technology.
Not all students have the same level of access to computers, high-speed internet, or other
essential devices. This digital divide can create disparities in the quality of education
received by different student groups.
2. Engagement and Motivation: Maintaining student engagement in an online environment
can be challenging. The absence of face-to-face interactions and the potential for
distractions in a home setting can lead to decreased motivation and participation. Educators
face the task of creating interactive and compelling content to keep students actively
involved.
3. Personalised Learning Needs: Students have diverse learning styles and preferences.
Adapting to these individual needs in an online setting can be complex. Providing
personalised attention and feedback becomes crucial for effective teaching, requiring
innovative solutions to address the unique requirements of each learner.
4. Technical Issues and Connectivity: Online learning is susceptible to technical issues,
such as platform glitches, software compatibility problems, and internet connectivity
issues. These disruptions can hinder the learning experience and frustrate both educators
and students, emphasising the need for robust technical support and infrastructure.
5. Assessment and Evaluation: Designing fair and effective assessment methods in an
online environment poses a challenge. Educators must find ways to prevent cheating while
ensuring that assessments accurately measure students' understanding and skills. The
 transition from traditional exams to alternative assessment methods requires careful
consideration.
6. Social Isolation and Collaboration: The absence of physical classrooms can lead to social
isolation among students. Collaborative activities and group projects, which are integral to
holistic learning, may face obstacles in the online realm. Creating a sense of community
and fostering collaboration becomes essential for a well-rounded educational experience.
7. Professional Development for Educators: Educators may face challenges in adapting to
the rapidly evolving technological landscape and implementing effective online teaching
strategies. Continuous professional development is necessary to equip teachers with the
skills and knowledge needed to navigate virtual classrooms successfully.
8. Accessibility and Inclusivity: Ensuring that online content is accessible to students with
diverse abilities is a critical consideration. The design of materials and platforms must
adhere to accessibility standards to accommodate learners with disabilities, promoting
inclusivity in the virtual learning environment.

Chat bots have emerged as a powerful tool for online real-time interactions between the users and
the systems and are able to cater to the requirements of customers in business environment to
support sales, marketing and customer relationship management. However, there are not many
such chat bots in the education sector. This is partly because there was no urgent requirement for
this as the face-to-face class room teaching is still the best alternative.

The pandemic taught us many things and also opened up many alternate practices in different
sectors including education sectors. Some of these alternatives are probably going to be there even
long after this pandemic is over. Universities and institutes are now planning to expand their reach
and fulfil the mandate by reaching out to many students. With new education policy in place, India
is looking forward to extend the reach of quality education to as many people as possible and
online remote teaching mode will be helpful for this.

This scenario requires 24 X 7 availability of teachers for the students to help them in their pursuit
of effective learning which is also not possible on the part of the teachers. An intelligent and robust
chat bot can help the students and teachers for executing the effective teaching and learning
process. There are a few chat bots which are there for education sector but they are not typically
designed for education purpose and just a little bit modification of the chat bot design for business
applications.
Thus, it is high time that we design and deploy an intelligent and robust chat bot application
involving the students and teachers in the development process. Thus the chat bot will be for the
students, by the students and of the students and it will also be for the teacher, by the teachers and
of the teachers.

In educational settings, the role of research has greatly increased in modern times (Kothari, 2004)
because research is studied in some subjects and sometimes required by educational institutions as
graduation criteria. However, the lack of basic research knowledge on research skills may cause
students to feel inadequate or result in serious academic difficulties and not success in study
(Sutasuwan, Sumalee, & Supsombat, 2016).

Therefore, it is important to understand basic knowledge of research so that the translation of that
research knowledge into research skills will be easily facilitated. There are many possible means
with technology support that can be integrated as a digital learning tool to help enhance student’s
research knowledge through personalized learning support due to the fact that technology for
education nowadays is changing how students learn (Singh, 2018) and it can help students learn
faster with a wider perspective (Havenstein, 2008), increase teaching’s effectiveness (Ellison,
Steinfield, & Lampe, 2007), offer guidance and use as information retrieval tool to give a positive
and sometimes fun digital learning experience to students who have good adoption of technology-
based learning.

Chatbots are considered as one of the latest and trendy learning technologies with artificial
intelligence. A chatbot is programmed with text messages or speeches to simulate human
conversation in a scripted way (Rouse, 2017; Hettige & Karunananda, 2015; Imran, 2015; Heller
& Procter, 2010; Dryden, 2008; Wang, 2008; Bayan & Atwell, 2007; Heller, Procter, Mah, Jewell,
& Cheung, 2005; Weizenbaum, 1975), engages with a computer, often, over the internet through
text messages or speeches (Xu, Liu, Guo, Sinha, & Akkiraju, 2017), and can be trained with any
language or some jokes to create fun learning. Only typing questions or keywords are needed to
receive answers or [Link] International Education Studies Vol. 14, No. 2; 2021 45
explanation instantly (Shawar, 2005).

Two types of chatbots are popular. Firstly, it is a rule-based or retrieval-based chatbot that uses
preprogrammed responses to match with the text messages or speeches inputted. Secondly, it is a
generative chatbot that generates as suitable a response as possible from the input through Natural
Language Processing (NLP) and deep machine learning (Liu et al., 2016; Nieves, 2018). With
integrated artificial intelligence, chatbots can be used as a digital learning tool to ask questions,
give answers to questions, retrieve information (Shawar & Atwell, 2007), visualize the contents
(Bayan, 2005), explore online content (James, 2016), provide useful information (Brandtzaeg &
Følstad, 2017), establish the knowledge that the students has to learn (Wenger, 1987), and propose
possible solutions to the students individually (Singh, 2018) because several studies have shown
that poor personalized support can lead to weak student learning outcomes while good
personalized support can improve student learning outcomes (Pane et al., 2017; Hone & El Said,
2016; Brinton et al., 2015; Eom, Wen, & Ashill, 2006).

Therefore, educational institutions should utilize chatbots to provide interactive e-learning

environment for students (Kowalski, Hoffman, Jain, & Mumtaz, 2011; Bii, 2013) and sometimes
fun learning. Responses to frequently asked questions can be programmed and instant responses
can be provided (Cameron et al., 2017) while making it easier and more comfortable for students
to ask questions and obtain immediate answers to questions. As a result, chatbots are able to
support the learning process to be more engaging, interesting and entertaining for the students
while facilitating the teaching process (Singh, 2018) to free up teachers from responding to
repetitive questions and act as a virtual assistant or tutors (Garcia-Brustenga, Fuertes-Alpiste, &
Molas-Castells, 2018) for students.

Using chatbot technology has many potential benefits. The advantages of using chatbots include
low cost, less time in obtaining answers, better interaction, creative learning and improved
efficiency when using in instruction (Llic & Markovic, 2016; Bii, 2013) because users find
chatbots safe and easy to chat online (Cameron et al., 2017) with the ability to operate as a 24/7
support service, provide responses to repetitive or frequently asked questions that can easily
resolved, and give access to learning contents (Garcia-Brustenga et al., 2018; Winkler & Söllner,
2018) when required.

In addition, students can refresh their memory by using chatbots to help recall, revise and
remember the knowledge studied. With chatbots, timely and efficient assistance or information
can be obtained with reported motivation and curiosity in their entertaining, social and relational
factors. Students also view chatbots as a novel phenomenon. Furthermore, chatbots can play the
role of teaching guide (Silvervarg, Kirkegaard, Nirme, Haake, & Gulz, 2014) and assistant
throughout the learning process with wide range of functions of obtaining information for students,
giving knowledge and enhancing its understanding with uninterrupted availability if learning
through chatbot technology is properly designed.

The teachers can also use questions asked to collect data, modify a knowledge base, and expand
more knowledge by using chatbot technology to look for questions and add additional answers to
those questions asked in its knowledge base. Most students prefer using chatbot technology
because chatbots are able to give direct answers instead of links for further searching like using
search and sort-based tools (Shawar & Atwell, 2007; Shawar, 2005).

Nowadays, chatbots can work on Facebook’s instant messaging platform that is installed on most
smart phones (Stalista, 2017) and becomes the main network where students and teachers have
their own account users with no need to download any application and more comfort to use the
application that they are already familiar with (Lachs, 2017; Singh, 2018; Preedasutti, 2010). Apart
from that, it is not necessary to have programming knowledge to use chatbot technology as
chatbots can recognize the language inputted by users, and recognize their intent to provide
relevant responses according to the input (Cameron et al., 2017).

Chatbots have significant educational potential and positive impact on student learning and
satisfaction through their personalized learning support (Winkler & Söllner, 2018). Although there
were numerous studies related to successful implementation of chatbots (Dutta, 2017; Huang, Lee,
Kwon, & Kim, 2017; Kerly, Hall, & Bull, 2007), only few of them have been used for educational
purposes (Kowalski et al., 2011). At present, the use of chatbots in education was scarce as not
much research has been done on the utilization of chatbot technology in classrooms (Baker, 2016;
Goos et al., 1998; Bayan & Atwel, 2007; Gimeno, 2008; Wang, 2008; Torma, 2011; Govindasamy,
2014; Osodo, Indoshi, & Ongati, 2010).

In Thailand context, there were some researches done on the use of chatbots to provide customer
service (Santirattanaphakdi, 2018), to guide a system (Bungodchai, 2017), to act as performer
agents (Lerdsahapan, 2015) and to diagnose a disease (Mokarat, Unchai, & Marpae, 2016) but
there is little research being done in education although chatbot technology has high potentials as
a digital learning tool for providing personalized learning support.

Therefore, more researches are necessary to widen findings related to chatbot technology.
[Link] International Education Studies Vol. 14, No. 2; 2021 46 Due to the possible and
potential of chatbot technology as a digital learning tool with many functions to use for education
and the limited research on chatbot technology in educational settings, especially in Thailand, the
current study tended to use chatbot technology as a digital learning tool on Facebook’s instant
messaging platform to increase research knowledge of Thai students. It is anticipated that the
chatbot developed can be used as a digital learning tool in class to increase students’ research
knowledge and create positive personalized learning support through this digital platform.

2. Literature Review :

Research on existing chat-bot applications in the education sector reveals a growing trend in
leveraging artificial intelligence to enhance teaching and learning experiences. Chat -bot
applications have emerged as transformative tools in the realm of education, aiming to enhance
the teaching and learning experience. Notable examples such as Duolingo, Squirrel AI, and
Woebot showcase the versatility of chat-bots in catering to various educational needs. Duolingo
utilizes a chat-bot interface for language learning, engaging users in dynamic conversations to
improve language skills. Squirrel AI employs adaptive learning, offering personalized tutoring
through chat-bots to enhance individual learning outcomes. Woebot, focused on mental health,
provides emotional support, contributing to overall well-being for students. Additionally,
integrated solutions like Coursera's ChatGPT integration and Edmodo Buddy streamline
communication and administrative tasks, demonstrating the potential of chat-bots in administrative
efficiency. The common impacts observed include 24/7 support, personalized learning
experiences, and cost-effectiveness, signaling a promising future for the integration of chat-bots
in education. As technology continues to advance, the role of chat-bots in education is poised to
expand, offering innovative solutions to address the evolving challenges in teaching and learning.

Initially chatbots were developed to be entertaining and to mimic human conversation. This is still
a popular reason when developing chatbots, but since the popularity with the technology has gone
up, so has the different uses. The chatbot technology has then been used for many things, like for
retrieving information, answering questions, helping make fact-based decision, as a shopping
assistant, as a museum guide, language partner, or in education, among other things. The chatbot
can be used as a tool to learn and practice a language. There are many perks of having a chatbot as
a conversational partner when learning language, for example a it could allow a student to practice
their language skills anytime, it would not mind repeating the same material several times, it can
incorporate both text, speech which might help a student with both their reading, writing and
listening skills. However, the chatbot as a language tool also has a few disadvantages. The
responses of a chatbot are often predictable, redundant or retain no memory of previous responses.
(Roos, 2018).

As mentioned, a chatbot can be used as an information retrieval tool, in order to answer a user’s
questions on a specific topic. This kind of chatbot has a wide range of applications, from interactive
FAQ to helping a customer make decisions. An example of a bot like this is the YPA, a chatbot
used to provide users with information from the British Telecom’s Yellow pages. The user might
ask for a plumber with an emergency service, and the chatbot will search its knowledge base and
retrieve an address, or if none was found, ask for additional details. When it comes to chatbots in
education, states that it is important to remember that the teacher is the backbone of the teaching
process and the learning technology may act as an amplifier but not a replacement. One example
is that the when a chatbot is used to answer student questions, the teacher can use generated log
files of the conversations to see what the students are having issues with and what their weaknesses
are. (Shawar and Atwell, 2007 cited by Roos, 2018). Thus, the teacher can use a chatbot to look
for problems as the students use it to solve them.

The potential of Chatbots in education:

In particular, the use of chatbots to enhance student interaction is becoming mote popular in a
world where tech-savvy students rely heavily on social media and instant messaging platforms,
such as slack and Facebook Messenger. Chatbots have the potential to provide standardized
information to students instantaneously. Using chatbots is possible to adapt the speed at which a
student can learn without being too pushy. (Palasundram, et al, 2018) Chatbot can also be used as
a source of social learning, in fact students from different backgrounds can share their views and
perspectives on a specific matter while the bot can still adapt to each one of them individually.
This technology can improve engagement among students and encourage interaction with the rest
of the class by assigning group works and projects like teachers usually do. (Roos, 2018).
Chatbot can help teachers in their homework. Often are used as online assessments: if a class
there are many students, give attention to each one of them becomes very demanding for
teachers, while chatbots can work with multiple students and groups at the same time. They also
can work as
a support to teachers by identifying spelling and grammatical mistakes, checking homework,
assigning projects and especially keeping track of progress and achievements of each student.
(Colace, et al, 2018) Chatbot aims to be an e-Tutor for Students

Considering the advantages, the review of a handful of research done by scholars in

the use of Chabot for tutoring is summarized below:

1. Customized learning:

Personalized attention to students advances their results as the tutors get to knowledge of the
domain where the learners are fragile in. The availability of personal educators to individual
students of different capacities can conceive larger number of professionals. Students can acquire
deeper knowledge of their interests. Technology Mediated Learning (TML) is defined as “an
environment in which the learner’s interactions with learning materials (readings, assignments,
exercises, etc.), peers, and/or instructors are mediated through advanced information technologies”.
Chatbot mediated learning is also considered as a branch of TML where the study
is personalized and students can dynamically use these bots for their learning. (Thomas, 2020).
The chatbots assess the discernment of the students and provides the subsequent lecture. For
instance, the Summit Learning Project uses chatbots to identify the weak areas of students and
adapt to their leaning style and help them manage the modules. The chatbots further conducts
quizzes and submits the results to the tutors, who provide immediate feedback to the students. This
is accomplished through digital Forums.

2. Spaced Interval Learning:

Spaced Interval learning helps students polish up what they have studied until then. The students
can recall what they have memorized. Super Memo is an application that reminds students when
they are about to forget. It uses an algorithm to monitor the frequency mode in which the learning
happens and repeats subjects already covered.

3. Assessment of composition skills:

Currently, educators tend to assess the students through Multiple-choice questionnaires easing their
tasks. A student can be assessed better based on their writing and composition skills which can be
acquired through essay writing. This has been explored through an automated evaluating system
where the researchers have executed unsupervised machine learning on performing robotic
assessment and have also done an analysis on the performance of the robot which was analysed
using an amalgam of combination of term frequency inverse-document function (tfidf) with cosine
Euclidean distance. A real time study was conducted on a set of medical students, where the web
tutoring program increased their test scores and cognitive efficacy to three-fold the size which was
measured in Cohen’s D effect size (95%) and confidence interval (CI)

4. Easing tasks of tutors:

Kerfoot BP,. Baker H, Jackson TL, et al. A multi-institutional randomized controlled trial of
adjuvant web-based teaching to medical student. Acad Med It is a false assumption for teachers
who think the chatbots may take up their job and they will be laid off. It only simplifies tasks for
them by helping students with frequent queries and assessing them personally. Teachers can equip
themselves with the latest research during the supplementary time they get. Ashok Goel, is one
among the initial educators who used this method and developed his own chatbot and named it Jill
Watson. Jill attempted to answer the students through an online forum dispensing all available
information including technical doubts.

5. Integration of chatbots to classrooms:

Apart from standalone chatbots, there has been an increase in the integration of these
chatbots in social platforms such as Facebook, Google classroom and so on. Based
on the category, language and development platform chatbots used for education in
Facebook has been studied in and the efficacy has been evaluated. Quality allocation
was tabulated using Analytic Hierarchy Process (AHP).

6. Appealing methods of online education:

How effective can chatbots be in education, also relies on its attractive design.
Reeves, B. & Nass, C. (1996) exemplified in their investigation that most of the humans
consider social platforms such as televisions, computers and internet as their fellow
beings and treat them with more respect. This finding led few researchers to think with
ingenuity to impart knowledge as a dignitary or an influential person from the past. To
elaborate, in the research conducted in 2014, a talkbot labelled Freudbot was built
using non-proprietary software called AIML (Artificial Intelligence Markup Language)
and ELIZA kind of control features. The highlighting feature of Freudbot was that it
communed with the learners as a famous personality from history. Though it provided
neutral results, it was assumed to be more promising for the future online education.

2.1 Common Impacts and Trends:

1. 24/7 Support: Chat-bots provide continuous support outside regular office hours, catering
to diverse schedules and time zones.
2. Personalization: Personalized learning experiences tailored to individual needs enhance
engagement and comprehension.
3. Cost-Efficiency: Chat-bots contribute to cost-effective education solutions by automating
routine tasks and support services.
2.2 Impact of Technology on online Education:

Technology has undeniably revolutionized the landscape of online education, ushering in a myriad
of transformative changes. The integration of advanced technologies has not only democratized
access to education but has also redefined the dynamics of teaching and learning. Virtual
classrooms, interactive learning management systems, and the proliferation of educational apps
have made learning more accessible and flexible. Additionally, technologies like artificial
intelligence and machine learning have paved the way for intelligent tutoring systems and adaptive
learning platforms, offering personalized educational experiences. The use of video conferencing
tools facilitates real-time interaction and collaboration among students and educators, bridging
geographical gaps. However, challenges such as the digital divide and the need for up-to-date
infrastructure remain. In essence, the impact of technology on online education is profound,
reshaping traditional models and presenting new opportunities for inclusive, dynamic, and learner-
centric approaches to learning. As technology continues to evolve, its influence on online
education is expected to deepen, providing innovative solutions and expanding the boundaries of
accessible and effective learning experiences.

Drawing from extensive systematic literature reviews, as summarized in Table 1, AI chatbots

possess the potential to profoundly influence diverse aspects of education. They contribute to
advancements in both teaching and learning processes. However, it is essential to address concerns
regarding the irrational use of technology and the challenges that education systems encounter
while striving to harness its capacity and make the best use of it.

Systematic literature reviews on AI Chatbots in Education:

It is evident that chatbot technology has a significant impact on overall learning outcomes.
Specifically, chatbots have demonstrated significant enhancements in learning achievement,
explicit reasoning, and knowledge retention. The integration of chatbots in education offers
benefits such as immediate assistance, quick access to information, enhanced learning outcomes,
and improved educational experiences. However, there have been contradictory findings related
to critical thinking, learning engagement, and motivation. Deng and Yu (2023) found that chatbots
had a significant and positive influence on numerous learning-related aspects but they do not
significantly improve motivation among students. Contrary, Okonkwo and Ade-Ibijola (Okonkwo
& Ade-Ibijola, 2021), as well as (Wollny et al., 2021) find that using chatbots increases students’
motivation.

In terms of application, chatbots are primarily used in education to teach various subjects,
including but not limited to mathematics, computer science, foreign languages, and engineering.
While many chatbots follow predetermined conversational paths, some employ personalized
learning approaches tailored to individual student needs, incorporating experiential and
collaborative learning principles. Challenges in chatbot development include insufficient training
datasets, a lack of emphasis on usability heuristics, ethical concerns, evaluation methods, user
attitudes, programming complexities, and data integration issues.
Although existing systematic reviews have provided valuable insights into the impact of chatbot
technology in education, it's essential to acknowledge that the field of chatbot development is
continually emerging and requires timely, and updated analysis to ensure that the information and
assessments reflect the most recent advancements, trends, or developments in chatbot technology.
The latest chatbot models have showcased remarkable capabilities in natural language processing
and generation. Additional research is required to investigate the role and potential of these newer
chatbots in the field of education. Therefore, our paper focuses on reviewing and discussing the
findings of these new-generation chatbots' use in education, including their benefits and challenges
from the perspectives of both educators and students.
There are a few aspects that appear to be missing from the existing literature reviews: (a) The
existing findings focus on the immediate impact of chatbot usage on learning outcomes. Further
research may delve into the enduring impacts of integrating chatbots in education, aiming to assess
their sustainability and the persistence of the observed advantages over the long term. (b) The
studies primarily discuss the impact of chatbots on learning outcomes as a whole, without delving
into the potential variations based on student characteristics. Investigating how different student
groups, such as age, prior knowledge, and learning styles, interact with chatbot technology could
provide valuable insights. (c) Although the studies highlight the enhancements in certain learning
components, further investigation could explore the specific pedagogical strategies employed by
chatbots to achieve these outcomes. Understanding the underlying mechanisms and instructional
approaches utilized by chatbots can guide the development of more effective and targeted
educational interventions. (d) While some studies touch upon user attitudes and acceptance, further
research can delve deeper into the user experience of interacting with chatbots in educational
settings. This includes exploring factors such as usability, perceived usefulness, satisfaction, and
preferences of students and teachers when using chatbot technology.
Addressing these gaps in the existing literature would significantly benefit the field of education.
Firstly, further research on the impacts of integrating chatbots can shed light on their long-term
sustainability and how their advantages persist over time. This knowledge is crucial for educators
and policymakers to make informed decisions about the continued integration of chatbots into
educational systems. Secondly, understanding how different student characteristics interact with
chatbot technology can help tailor educational interventions to individual needs, potentially
optimizing the learning experience. Thirdly, exploring the specific pedagogical strategies
employed by chatbots to enhance learning components can inform the development of more
effective educational tools and methods. Lastly, a deeper exploration of the user experience with
chatbots, encompassing usability, satisfaction, and preferences, can provide valuable insights into
enhancing user engagement and overall satisfaction, thus guiding the future design and
implementation of chatbot technology in education.
3. Aim and Objective:
To develop an intelligent, adaptive and robust chat bot application for assisting in the teaching-
learning process and also help both the teachers and students. which interacts with the user
(student) and answers their queries regarding subjects taught through online courses.

To involve the users both students and teachers in the development process using a crowd sourcing
model for obtaining frequently asked questions and also validating and approving the answers by
the concerned course teacher. This will help to make the chat bot adaptive to the style of the teacher
and also the local students.

To build a large bank of frequently asked questions from different students and also teachers who
taught that course using a crowd sourcing approach. The question bank is validated and approved
by the teachers again in the crowd sourcing model.

“A chat bot by the students, for the students and of the teachers” is the uniqueness of this
proposed model.

3.1 Objective:

1. Provide Instant Assistance: Enable students to receive instant and accurate assistance for their
queries, creating a responsive support system available 24/7.

2. Personalized Learning Support: Develop a chat-bot that can adapt to individual learning
styles, providing personalized recommendations, resources, and guidance tailored to each student's
needs and preferences.
3. Enhance Engagement and Motivation: Implement interactive and engaging features within
the chat-bot to enhance student motivation and participation, making the learning process more
enjoyable and dynamic.
4. Address Accessibility Challenges: Ensure the chat-bot is designed with accessibility features
to accommodate diverse learning needs, making educational content accessible to students with
different abilities.
5. Facilitate Automated Assessment and Feedback: Integrate features for automated assessment
and instant feedback, allowing students to receive timely evaluations on their performance in
quizzes, assignments, and other learning activities.
6. Support Language Learning: Incorporate language learning functionalities within the chat-
bot, offering conversational practice, vocabulary building, and grammar assistance to enhance
language acquisition.
7. Track Student Progress and Provide Analytics: Implement mechanisms for tracking and
analyzing students' progress, providing educators with valuable insights to tailor teaching
strategies and offer targeted support.
8. Support Educators in Administrative Tasks: Develop features that assist educators in
managing administrative tasks, such as answering frequently asked questions, providing resources,
and automating certain aspects of grading.
9. Integrate Emerging Technologies: Ensure the chat-bot is adaptable to emerging technologies,
such as virtual reality (VR) or augmented reality (AR), to enhance the overall learning experience
with immersive and interactive elements.
10. Promote Cost-Effectiveness: Create a cost-effective solution that reduces the need for
additional human resources in support services, making the educational support system efficient
and sustainable.
11. Foster a Collaborative Learning Environment: Implement features that encourage
collaboration among students, facilitating group discussions, project work, and other collaborative
activities within the online learning platform.
12. Improve User Experience for Both Educators and Learners: Prioritize the development of
a user-friendly interface and experience for both educators and learners, ensuring that the chat -bot
seamlessly integrates into the online teaching and learning environment.

4. Methodology:
4.1 Data Collection and creation of knowledge based in crowd sourcing mode:

We aim to build and maintain a website which will collect frequently asked question that will be
useful for the development of intelligent chat bot. There will be authentication for the user, i.e.,
they need to login. This authentication is being done to identify users and credentials who posted
the questions. The users are required to choose the subject and post the question along with
answer (optional).

The scenario:

First the user will select the subject (example OS) . The users can provide any number of questions
and answers (or only questions, if they don’t have the answer) regarding topics of that subject.
These questions as well as answers will be stored in a transaction database which will be then
verified by the teacher (who will have administrative privilege). While verifying the question and
answers, it should be activated in edit mode. In case where only questions are given, the teacher
shall add the answers and approve the question. Once the Q/A is verified the teacher/ administrator
will ‘freeze’ it and then it is transferred to the course/ subject wise master database. There will be
databases corresponding to every subject. The naming convention should be done such that the
required database is used depending on the subject chosen. This will build up our required
database, which will act as the knowledge base for the chat bot. We can have a special option to
edit the master database also.

The database obtained from this will act as the input to the RASA Framework or similar, which
will then be used to build the chat-bot application.

4.2 Technology Required:

The website will be built using NodeJS. We will use a NOSQL database for this purpose, i.e.,
MongoDB and use Express to set up the server. We will use HTML and CSS for the User Interface
and JavaScript for the client side. The website will be deployed using cloud server (Heroku/ Azure/
AWS or similar).

RASA frame work along with Python will be used to develop the chat bot along with its NLU
(Natural Language Understanding) interface which is an open-source natural language processing
tool for intent classification (decides what the user is asking), extraction of the entity from the bot
in the form of structured data and helps the chat bot understand what user is giving as input i.e.
questions.

There are also other frameworks like Dialogflow along with cloud services like [Link] (a Facebook
initiative), Microsoft Bot framework, Bottr framework and a few other similar things. It is
proposed to explore the different options for better user experience and efficiency of the chat bot.
The core engine will be AI based with state of the art machine learning techniques for providing a
natural-like interface.

4.3 Reinforcement Learning:

As the bot collects user satisfaction and based on the satisfaction level, the question is discarded
or sent to the professor with logs. We can turn this feature into a reinforcement learning system
where the bot is awarded for a good review and fined for a bad review. So the bot tries to
maximize the reward by answering correctly.

4.4 Setting-up the engine:

The engine is proposed to be a mother chat bot engine which will create chat bots for different
subjects/ courses. The mother chat bot engine will create a subject/ course wise chat bot to be
deployed by different teacher/ educators in their course page.

4.5 Chat bot (Subject-wise):

1. The chat bot greets

2. The user will have an authentication code to interact with the chat bot.
3. The user can type a question
4. The chat bot will give an answer using the database and machine learning algorithm
5. If the answer is not found in the master database, the chat bot should be able to search the
Internet (google) and give an answer
a. We can develop a crawler which periodically collects data from different sites and builds
a database
b. The chat bot instantaneously can search the internet for an answer and display to the use/
sutdent
6. The answer is followed with a Satisfied/ not satisfied prompt
a. We can think of putting 1-5 scale for satisfaction level
 b. If the answer is unsatisfactory, the administrator is immediately alerted
7. If the chat bot could not give an answer, should log it and the administrator should be
immediately alerted
8. All the interaction with the chat bot are logged in a database (with format (Date, Time, User,
Question, Answer, Chatbot_Status, User_Response, Administrator_Note [to be added by the
Admin after checking if required])
9. There should be a separate option to display the Log and to be seen by the Teacher/ Admin only.
10. We should also design to query the Log based on some attributes like number of questions
asked by a user, number of questions responded by the chat bot upto satisfaction etc.

4.6 Deployment:

The chat bot will be deployed in the corresponding course page of each teacher. The users of the
chat bot will be registered students of that course.

The chat bot will have access to the master database to answer the questions but in a priority of
(concerned teachers Q/A, master database Q/A obtained through crowdsourcing mode, Q/A
collected in crawling mode, Internet resources.

The chat bot interactions will be logged in two tier mode; one in the local system of the teacher
which is visible to him/ her and also a copy in the master log for further training and making the
chat bot more robust over a period of time.

5. System Architecture :

In this section, we describe a general architectural design and delve deep into the important parts
of each component. A general chatbot architecture consists of five main components, a User
Interface component, a Natural Language Understanding (NLU) component, a Dialogue
Management (DM) component, a Backend component, and a Response Generation (RG)
Component [6], as illustrated in the figure below.
Figure 1: General chatbot architecture
Figure 2: Flowchart
Figure 3: Flowchart
 Figure 4: ER Diagram
6. Discussion:

Applying the chatbot system proposed in this study to the junior high school biology classes had
a positive impact on students’ learning achievement. The past studies have pointed out that
chatbots are instantly responsive and indicated that real-time feedback is an effective technology
to engage learners [32-33]. Real-time feedback can create an effective learning environment based
on student’s learning status [34]. Thus, chatbots are an effective way to motivate students to learn,
especially in a one-to-one learning environment [35]. In addition, the proposed chatbot system can
effectively collect students’ learning behaviors, which conforms to past studies. The studies
suggested that collecting and presenting information about students’ learning behaviors can
support students to understand individual learning status in an online learning environment, thus
enhancing their learning achievements [36-40].
Furthermore, through informal feedback from the students in the experimental group, several
students reported that they were satisfied with their biology learning experience using the chatbot
system. Moreover, they also indicated that they had a quality leaning experience on using the
chatbot system. A different feedback from few students is that their parents may think they are
chatting with friends while they are learning with the chatbot system. This phenomenon is
consistent with the research findings [41-42]. Therefore, educational practitioners have to be able
to provide appropriate guidance to stakeholders while implementing such learning approaches.

7. Conclusion:

The challenges in online teaching and learning are multifaceted, encompassing technological,
pedagogical, and socio-economic aspects. Addressing these challenges requires a holistic approach
that combines innovative technology solutions, pedagogical strategies, and a commitment to
inclusivity. The development of intelligent chat-bot applications presents an opportunity to
mitigate some of these challenges by providing personalized support, fostering engagement, and
enhancing the overall online learning experience.

Chatbots in online learning can be real game-changers! They provide instant support and guidance,
helping students with queries anytime, anywhere. This not only enhances the learning experience
but also promotes self-directed learning. Chatbots can also assist in personalized learning by
tailoring recommendations based on individual progress and preferences. Plus, they're available
24/7, so there's no waiting around for office hours.
the development of an intelligent and robust chat-bot application for enhancing online teaching
and learning represents a significant stride towards addressing the evolving challenges in modern
education. Through meticulous design and implementation, this project has aimed to revolutionize
the online learning experience by providing instant, personalized, and engaging support to students
and educators alike.

The integration of cutting-edge technologies, including natural language processing, machine

learning, and adaptive algorithms, has empowered the chat-bot to adapt to individual learning
styles, fostering a more personalized and inclusive educational environment. The 24/7 availability
of the chat-bot ensures that learners can access assistance and resources at their convenience,
overcoming the constraints of time zones and differing schedules.

Furthermore, the chat-bot's role in automating administrative tasks, providing real-time feedback
on assessments, and promoting collaborative learning has not only streamlined educational
processes but has also contributed to the overall efficiency of online teaching platforms.
As we reflect on the journey of developing this intelligent chat-bot application, it becomes evident
that the fusion of technology and education holds immense potential for the future. The positive
impacts witnessed in terms of enhanced engagement, accessibility, and cost-effectiveness
underscore the significance of intelligent chat-bots in shaping the next generation of online
education.

However, it is crucial to acknowledge that this project represents a step in an ongoing evolution.
The ever-changing landscape of technology and education calls for continuous improvement,
adaptability, and a commitment to staying abreast of emerging trends. The feedback from users
and educators will play a pivotal role in refining and expanding the capabilities of the chat -bot,
ensuring that it remains a valuable asset in the dynamic realm of online teaching and learning.
In essence, the development of this intelligent chat-bot application is not just a conclusion but a
catalyst for future advancements in the intersection of technology and education. As we navigate
the uncharted territories of online learning, the lessons learned and achievements attained in this
project will undoubtedly contribute to the broader narrative of transforming education through
innovation and intelligent solutions.

8. Future Work:

1. Advanced Personalization: Explore more advanced machine learning techniques to

enhance the personalization capabilities of the chat-bot. Implement algorithms that can
dynamically adapt to individual learning preferences and styles, ensuring an even more
tailored educational experience.
2. Emotional Intelligence Integration: Integrate emotional intelligence features into the
chat-bot to better understand and respond to the emotional state of learners. This could
involve sentiment analysis and the ability to provide empathetic support, creating a more
holistic learning environment.
3. Multilingual Support: Expand the language capabilities of the chat-bot to support a
broader range of languages. This will enhance accessibility for a more diverse global
audience and cater to the linguistic diversity in online education.
4. Integration with Emerging Technologies: Explore integration with emerging
technologies such as augmented reality (AR) and virtual reality (VR) to create immersive
learning experiences. This could involve virtual classrooms, interactive simulations, and
3D visualizations to augment traditional teaching methods.
5. Enhanced Assessment and Feedback: Improve the chat-bot's capabilities for assessing
student progress and providing feedback. Implement more sophisticated evaluation
methods, including natural language understanding for nuanced responses to open-ended
questions.
 6. Continuous Learning and Adaptation: Implement mechanisms for the chat-bot to
continuously learn and adapt based on user interactions and feedback. Utilize reinforcement
learning or other adaptive algorithms to enhance the chat-bot's ability to improve over time.
7. Collaborative Learning Features: Introduce features that facilitate collaborative learning
among students. This could involve group discussions, collaborative projects, and peer-to-
peer learning experiences facilitated by the chat-bot.
8. Enhanced Security Measures: Implement robust security measures to ensure the privacy
and confidentiality of user data. Explore encryption methods and compliance with data
protection regulations to build trust among users.
9. Integration with Learning Management Systems (LMS): Enhance integration with
existing learning management systems to streamline administrative tasks further. This
could include seamless data exchange, automated grading, and synchronization of course
materials.
10. User Experience Optimization: Continuously optimize the user interface and overall user
experience based on user feedback and usability studies. Prioritize accessibility features to
ensure an inclusive experience for users with diverse needs.
11. Long-Term Educational Impact Assessment: Conduct longitudinal studies to assess the
long-term educational impact of the chat-bot application. Evaluate its effectiveness in
improving learning outcomes, retention rates, and overall student satisfaction over
extended periods.

9. References:

1. Avalverde, D. (2019). A Brief History of Chatbots. Perception, Control, Cognition. Retrieved

March 9, 2019 from: [Link]

2. Chatbot Magazine (2019). A Visual History of Chatbots. Retrieved March 9, 2019 from:
[Link]

3. Egencia (2018). What is a Chatbot and How does it work? Retrieved March 9, 2019 from:
[Link]

4. Hattie, J. (2012). Visible learning for teachers: Maximizing impact on learning: Routledge.
[Link]

5. V Soft Consulting. (2019). 7 of the best Language-learning Chatbot Apps. Retrieved March 9,
2019 from: [Link]
6. [Link]

7. [Link]

8. [Link]

9. F. Zhang, P. Markopoulos, T. Bekker, Children’s Emotions in Design-Based Learning: a

Systematic Review, Journal of Science Education and Technology, Vol. 29, No. 4, pp. 459-481,
August, 2020.

10. S. Ahmad, S. Jamil, Development and Validation of Biology Attitude Scale for Secondary
School Students in Islamabad, Pakistan, Journal of Contemporary Teacher Education, Vol. III, pp.
13-29, 2019.

11. M.-C. Yen, B.-Y. Huang, A Meta-Analysis of the Learning Effects of Flipped Classroom on
Elementary School and Junior High School Students, Bulletin of Educational Psychology, Vol. 51,
No. 1, pp. 23-50, September, 2019.

12. J. M. Lodge, G. Kennedy, L. Lockyer, A. Arguel, M. Pachman, Understanding Difficulties and

Resulting Confusion in Learning: An Integrative Review, Frontiers in Education, Vol. 3, Article
No. 49, June, 2018.

13. T.-H. Wang, H.-C. K. Lin, T.-T. Wu, Y.-M. Huang, A Multimethod Approach for Supporting
Reflection and Creativity in Online Collaborative Courses, Journal of Internet Technology, Vol.
21, No. 4, pp. 1097-1106, July, 2020.

14. S.-C. Chang, G.-J. Hwang, Impacts of an augmented reality-based flipped learning guiding
approach on students’ scientific project performance and perceptions, Computers & Education,
Vol. 125, pp. 226-239, October, 2018.

15. M. Adnan, K. Anwar, Online Learning amid the COVID-19 Pandemic: Students’ Perspectives,
Journal of Pedagogical Sociology and Psychology, Vol. 2, No. 1, pp. 45-51, June, 2020.

16. S. Kim, Incentive mechanism-based influential maximisation scheme for social cloud service
networks, International Journal of Ad Hoc and Ubiquitous Computing, Vol. 33, No. 1, pp. 11-21,
January, 2020.

17. J. Zhang, Y. J. Oh, P. Lange, Z. Yu, Y. Fukuoka, Artificial Intelligence Chatbot Behavior
Change Model for Designing Artificial Intelligence Chatbots to Promote Physical Activity and a
Healthy Diet: Viewpoint, Journal of Medical Internet Research, Vol. 22, No. 9, Article No.
e22845, September, 2020.

18. P. Smutny, P. Schreiberova, Chatbots for learning: A review of educational chatbots for the
Facebook Messenger, Computers & Education, Vol. 151, Article No. 103862, July, 2020.