A SEMINAR REPORT ON

Chat Boat-In Future Communication

SUBMITTED BY,

Mr.Akash Ramchandra Shinge

UNDER THE GUIDANCE OF

Prof. S.N Uke

SINHGAD TECHNICAL EDUCATION SOCIETY

SKN SINHGAD INSTITUTE OF TECHNOLOGY
& SCIENCE, LONAVALA

DEPARTMENT OF INFORMATION TECHNOLOGY

GAT NO. 309, KUSGAON (BK.) OFF MUMBAI-PUNE EXPRESSWAY,

LONAVALA, TAL - MAVAL, DIST - PUNE - 410401.

ACADEMIC YEAR: 2021-2022

This is to certify that the project based seminar report entitled Chat Boat-In Fu-
ture Communication being submitted by Akash Ramchandra Shinge(Exam
Seat No.22) is a record of bonafide work carried out by her under the supervision
and guidance of Prof. S.N.Uke in partial fulfillment of the requirement for TE
(Information Technology Engineering) 2019 course of Savitribai Phule Pune
University, Pune in the academic year 2021-2022.

Date:
Place:

Prof. S.N.Uke Prof. S. B. Kothari

Seminar Guide Head of Department

This seminar report has been examined by us as per the Savirtibai Phule Pune
University, Pune, requirements at SKN Sinhgad Institute of Technology & Science,
Lonavala.

(Prof. A. T. Sonawane) (Name & Signature)

Seminar Coordinator External Examiner
 Acknowledgement

I express my sense of gratitude towards my seminar guide Prof.S.N.Uke for his valu-
able guidance at every step of study of this seminar, also his contribution for the
solution of every problem at each stage.
I am thankful to Prof. S. B. Kothari Head of the Department of Information Tech-
nology, all the staff members and PBS Coordinator Prof. A. T. Sonawane who
extended the preparatory steps of this seminar. I am very much thankful to Principal
Dr. M. S. Rohokale for his support and providing all facilities for seminar.
Finally I want to thank to all of my friends for their support & suggestions. Last
but not the least I want to express thanks to my family for giving me support and
confidence at each and every stage of this seminar.

Mr.Akash R. Shinge

I
 Abstract

ChatBot can be described as software that can chat with people using artificial in-
telligence. These software are used to perform tasks such as quickly responding to
users, informing them, helping to purchase products and providing better service to
customers. In this paper, we present the general working principle and the basic
concepts of artificial intelligence based chatbots and related concepts as well as their
applications in various sectors such as telecommunication, banking, health, customer
call centers and e-commerce. Additionally, the results of an example chabbot for dona-
tion service developed for telecommunication service provider are presented using the
proposed architecture. We are using it for educational purpose to solve the quires of
users. Chatbots are programs that mimic human conversation using Artificial Intelli-
gence (AI). It is designed to be the ultimate virtual assistant, entertainment purpose,
helping one to complete tasks ranging from answering questions, getting driving direc-
tions, turning up the thermostat in smart home, to playing one’s favorite tunes etc.
Chatbot has become more popular in business groups right now as they can reduce
customer service cost and handles multiple users at a time. But yet to accomplish
many tasks there is need to make chatbots as efficient as possible. in this system we
provide the design of a chatbot, which provides an efficient and accurate answer for
any query based on the dataset of FAQs using Artificial Intelligence Markup Language
(AIML) and Latent Semantic Analysis (LSA). Template based and general questions
like welcome/ greetings and general questions will be responded using AIML and other
service based questions uses LSA to provide responses at any time that will serve user
satisfaction[1].
Keywords:Chatbot, Text to Speech, AI.

II
Contents

Acknowledgement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . I
Abstract . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . II
Contents . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . III
List of Figures . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . IV
List of Tables . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . V

1 Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1

2 Motivation, Purpose and Scope . . . . . . . . . . . . . . . . . . . . . . 4

2.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
2.2 Purpose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
2.3 Scope . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

3 Literature Survey . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 9

4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11

5 System Architecture . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13

6 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15

III
List of Figures

1.0.1 Chatbot developed by NLP . . . . . . . . . . . . . . . . . . . . . . . . . 2

5.0.1 Architecture of the proposed Chatbot . . . . . . . . . . . . . . . . . . . 13

IV
List of Tables

3.0.1 Literature Survey . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10

V
Chapter 1

Introduction

Advancements in artificial intelligence (AI), speech recognition sys-

tems (ASR), and machine learning have enabled the development of intelligent com-
puter programs called chatbots. Many chatbots have been proposed to provide different
services in many areas such as customer service, sales and marketing. However, the use
of chatbot as advisers in the field of information security is not yet considered. Further-
more, people, especially normal users who have no technical background, are unaware
about many of aspects in information security. Therefore, in this paper we proposed
a chatbot that acts as an adviser in information security. The proposed adviser uses a
knowledge base with json file. Having such chatbot provides many features including
raising the awareness in field of information security by offering accurate advice, based
on different opinions from information security expertise, for many users on different.
Furthermore, this chatbot is currently deployed through Telegram platform, which is
one of widely used social network platforms. The deployment of the proposed chatbot
over different platforms is considered as the future work[1].
A chatbot can conduct smart conversation—either via text or voice. They are armed
with machine learning which can interact with humans and become increasingly agile
with each interaction. It recognizes using pattern matching, user input as well to access
information to provide a predefined acknowledgment. In dialog systems they are used
for numerous practical intends comprising information acquisition or customer service.
Keywords are scanned with the input in simple chatbot and then respond with the

1
 Chat Boat-In Future Communication

most similar matching keywords or patterns from a database while some chatbots use
sophisticated. Their applications make the communication between people and ser-
vices, intensify the experience of customer. To have better customer engagement and
operational efficiency they provide companies new opportunities by lowering the cost
of customer service. [2].

Figure 1.0.1: Chatbot developed by NLP

The study objective was to develop a solution called “Smart

Wireless Interactive Healthcare System” (SWITCHes) to facilitate data recep-
tion and transmission in a real-time manner to web server protected by encryption for
further analysis of data extraction. SWITCHes is made up of two main components:
an interactive web-based dashboard and a smartphone app. An artificial intelligence
(AI)-powered health chatbot lives inside SWITCHes app. The SWITCHes-based clin-
ical trial is set to be carried out after obtaining Institutional Review Board (IRB)
approval. This paper presents an overview of development and implementation of
SWITCHes. which is set to attain the goals of reducing the health care spending,
allow the early detection, diagnosis as well as treatment, and improve clinical outcome.
mHealth app can be viewed as a wide reaching approach, which can reach out to many

SKNSITS, Lonavala. 2020-2021 2 Department of Information Technology

 Chat Boat-In Future Communication

more users who need the medical consultation or treatment throughout the rural or
remote areas, if appropriately designed[3].

Banks play an important role in every country’s economic devel-

opment. In day-to-day life, everybody needs banks. But most of the people, especially
the first-timers, struggle to know various procedures and processes required to get
their work done at the bank and avail of its different products and services. Currently
banks have their own web-sites, mobile applications and facilities like internet banking,
mobile bank-ing but sometimes, these sources can be a bit overwhelming for most of
the users who are either not well versed with technology or in some cases where the
information is too scattered to search for easily. There are different types of platforms
provided by different banks but people are facing problems accessing them (different
GUIs, too much navigation). Although Customer Care centers are available, there are
lot of wait times and redirection in some cases, leaving the customer with no choice
but to experience considerable delays getting a simple informational query resolved.
People have queries about various bank policies, loans, fixed deposits. This results in
unnecessary crowd in banks for inquiry. Banks also face problems solving repeated
queries of customers. This is time consuming and banking staff gets frustrated. Man-
power and money gets wasted for separate inquiry counter. [4]

SKNSITS, Lonavala. 2020-2021 3 Department of Information Technology

Chapter 2

Motivation, Purpose and Scope

2.1 Motivation

2.1.1.Active Communication Method

One would say that telephoning is an active communication method.

The prospect phones you to talk about buying a product or service or getting more
information. It’s happening right now. Well, the same goes with the chatbots. You
are opening up an other communication channel to engage more prospects. It can lead
to better results for those “hot” ones that are ready and hungry for more information.
This is not to say email doesn’t work, but email is more passive communication. You
don’t want to necessarily have a hot prospect start email unless they have been in-
formed and believe they are taken care of.[1]

2.1.2.Flexible and Efficient Lead Generation

The chatbot can continue your brand’s story. It can achieve this
objective depending upon how configuration. If setup in such way, then it can achieve
two goals. The first goal is purely answering questions to give information. The second
goal is telling the story through answering questions in a conversational way. That

4
 Chat Boat-In Future Communication

story is infinitely scaleable. This means, you can continue to expand out your story
as time goes on. This storytelling is also about how you brand the chatbot. When we
will discuss setup and implementation, I will also talk about branding[2].

2.1.3.Enhance Your Facebook Marketing

Now, if you don’t use Facebook, let me provide you a couple of

reasons why you should start: Nearly 2.07 billion user 1.15 billion mobile users 307
million users are in Europe Assuming that you are using Facebook, the platform allows
you to install bot applications. You could install it on your business page, or your
personal page. Either way, you enhance your Facebook marketing strategy by engaging
potential prospects and leading them somewhere. You can choose either to lead them
to your website or engage with them to proceed via Facebook[3].

2.2 Purpose

2.2.1.Available 24*7, cost saving, Quick to reply

Today, businesses’ need for a robust customer service department

is consistently rising. Implementing powerful chatbots allows companies to manage a
massive amount of customer queries in relatively short periods and saves time as well.[1]

2.2.2.Provision of personalized experience

AI Chatbot uses the data to provide a personalized experience for

the users. These chatbots go much beyond just answering pre-programmed questions
that every customer will experience in a precisely similar way.[4]

2.2.3. Detailed Analysis Insight of Customer Data

SKNSITS, Lonavala. 2020-2021 5 Department of Information Technology

 Chat Boat-In Future Communication

Businesses can analyze how well the bot performs in terms of suc-
cessful business outcomes and sales generated and detailed insights on how people
engage with the business.[5]

2.2.4 Increased lead generation, conversion, sales and rev-

enue
Chatbots’ flexible structure makes them super easy to integrate
with other systems, increasing customer engagement in return. They equip chatbot to
ask necessary and relevant questions, persuading the customers, and generating leads
quickly. It ensures that the conversation flow is in the right direction to get higher
conversion rates.
Not only in marketing retail sector but chatbots are now used in healthcare, bank-
ing, Media, HR sectors as well.
One example is of healthcare sector. Where in Casper’s amazingly named Insom-
nobot 3000 conversational agent that aims to give insomniacs someone to talk to while
the rest of the world rests easy. Outstanding initiative right.[8]

2.3 Scope

3.3.1.Exploring Different Use Cases Of Chatbots In The Work-

place

With the increase in adoption of messaging and video-based tech-

nologies, the potential of conversational chatbots is also realized. Chatbots are powered

by a set of rules and instructions that help learners to communicate via an easy to ac-

cess chat interface. Users can ask questions and the chatbots carry out specific actions

in their response. They are mainly considered as automated systems that run within

SKNSITS, Lonavala. 2020-2021 6 Department of Information Technology

 Chat Boat-In Future Communication

messaging apps such as SMS, Messenger, or any other mobile app. As per Gartner,

around 85 percent of customer interactions will be managed without humans by 2020.[2]

3.3.2.HR Chatbots For Employee Onboarding

Today, organizations use HR chatbots to effectively streamline the

onboarding process using modern LMSs. Bots are used to introduce new employees
to the company’s policies, work culture, and other significant aspects through team
communication app. Other benefits of using bots for HR purposes include:

For any onboarding program, it is essential for employees to know their company’s
history, its achievements, ongoing projects, and future goals. New hires can ask
the HR bot about their team, their role within the team, and how that role is
changing. To ensure the onboarding process is smooth, HR bots can reach out to
new hires and take their individual feedback. If there are some challenges, then
bots can also impart potential solutions to address the same. HR bots can also
provide refreshers on different pieces of training including Safety, Compliance,
Human Resources, Operations, and more to ensure high workforce engagement
and satisfaction.[4]
3.3.3.Chatbots In Everyday Life Today
Imagine walking into a museum and having no human tour
guides to show you around. Instead, your companion for the museum tour would
be a chatbot application on your phone. This is already a reality in some muse-
ums around the world. As you walk through the museum, you can ask the bot to
provide more information on the exhibit you are looking at. Museums are using
chatbots to increase engagement with their visitors. Compared to guided tours
by a human agent, chatbots can personalise the learning experience for each in-
dividual and tailor it based on their preferences. This is particularly useful for
tourists when they are in a foreign country and when English may not be their
first language, chatbots could converse with them in their native language and
retain their attention in learning about local culture. Chatbots allow visitors to
tour the premises at their own pace and answer questions about items on display

SKNSITS, Lonavala. 2020-2021 7 Department of Information Technology

 Chat Boat-In Future Communication

with instantaneous replies.[5]

3.3.3.Chatbots In Education Today
With students taking to technology very quickly these days, in-
teracting with chatbots can enhance their learning experience too. There are
already various education chatbots that communicate with students on a wide
range of topics such as language, science, mathematics, etc. Research suggests
that digital learning retention rates are up to 60 percent higher compared to face-
to-face retention rates. This implies that technology should supplement tradi-
tional teaching methods to enrich the learning journey for students. For instance,
chatbots in language learning can facilitate student engagement. When learning
any language, deliberate practice is necessary and valuable for the learner. Chat-
bots can help you practice your language skills without the intimidation and
awkwardness of conversing with a real human being. It is also convenient and al-
lows learners to get conversation practice anytime and anywhere. Further more,
chatbots allow for personalised learning as it can create a tailored learning path
for learners of different proficiencies in the language. Advanced learners can prac-
tise conversations in real-life situations while learners at lower levels of proficiency
can benefit from practising and reviewing vocabulary and grammar structures.
Unlike humans, chatbots will never get bored of repeating or lose their patience
with slower learners. This boosts students’ confidence and helps them cope with
learning based on their needs.[7]

SKNSITS, Lonavala. 2020-2021 8 Department of Information Technology

Chapter 3

Literature Survey

9
 Chat Boat-In Future Communication

Sr. Title of Paper Description Technique Merits/Demerits

No. With Seed Used
Idea

1 Intelligent Chatbot for Easy It contain To avoid Manpower dur-

Web-Analytics Insights”. analytics’ the time ing online com-
IEEE Author: Ravi, R raw data taking munication
task.

2 “Recruitment Chat- Comprehend Recruiters Unsaved query

bots”,Authors:Akash Bal- a conclusive can use is introduced to
achandar,Anusha D Kulkarni human them
response

3 “Task-based Interaction NLU is used An ap- Companies can

Chatbot”Authors: Dr. Kevin to under- propriate reach out to
Curran, Dr. Daniel Kelly stand the response them later as
context and and asks they trace their
intent of the the chat- activities during
user input bots to non working
perform hours
the re-
quired
action.

Table 3.0.1: Literature Survey

SKNSITS, Lonavala. 2020-2021 10 Department of Information Technology

Chapter 4

Discussion

A chatbot, which is known as interactive agent, conversational

interface, Conversational AI, or artificial conversational entity, is a computer
program using technology of an artificial intelligence, that makes a conversation
through different ways such as text-based ways. These computer programs be-
have similar to humans when then involved in a conversation.[2]

Provision of consultancy services in a vital field such as infor-

mation security is an important and plays main role in the raise of awareness
about information security for many users. Raising the awareness of users in
information alleviate security threats that face them, help them to take the right
action to protect themselves, and their society. Having a good level of security
in many parts can be achieved through the utilization of chatbot. Therefore, the
researchers sought to provide intelligent virtual information security adviser with
efficient and accurate replies to the customer.[5]

The programming challenging of the chatbot has been discussed

in [15], authors reviewed the problems that occur when designing chatbot using
the techniques and concepts of machine learning and natural processing. In [16]
the authors proposed a Chatbot for tourism purpose, in which the tourist have

11
 Chat Boat-In Future Communication

limited time. Their methodology divided to three phases. Data preparing was
the first phase, which include collecting the famous places and their location in
the city[6]

NLU (natural language understanding) is used to understand

the context and intent of the user input. An appropriate response is generated
from user. The knowledge base determines the chatbots knowledge, which is done
with the NLU and supported at the back-end. The back-end produces the knowl-
edge base by making use of the domains corpus. Input is given to the chatbot in
the form of speech or text. The input is given to the dialog management system
which defines an appropriate response and asks the chatbots to perform the re-
quired action. The responses are produced in the form of text and speech both.[7]

SKNSITS, Lonavala. 2020-2021 12 Department of Information Technology

Chapter 5

System Architecture

Figure 5.0.1: Architecture of the proposed Chatbot

As we know the use of automated machines is increasing day by

day i.e., the machine-human interaction is also increasing day by day. The case
might as well come true where one day humans would be replaced by automated

13
 Chat Boat-In Future Communication

bots for performing specific functioning of the system. Where, a central system
will be a chatbot which will receive the input from the user which will be in
the form of an audio/ voice. The input can be received using a mic and then
this voice input will be converted to the corresponding textual input using pre-
existing python libraries. Then this textual input will be provided to the system
which consists of the chatterbot which will perform Natural Language Processing
on the provided input and search within its database for the query. Two cases
will be generated: (1) When the input entered is an identifiable query, to which
already an answer is known to the system. This corresponding answer will be
directly provided to the user in this case. (2) When the input entered is not rec-
ognized, this is where the intelligence of the bot comes into play and the system
will understand the input and answer it using its intelligence. This is termed as
“Artificial Intelligence”.[1]
There are situations where chat bot cannot give right answer or
cannot have answer to asked question because the question is out of database.
For such circumstances, we have developed feedback mechanism for our chat bot.
Web application will have Dislike button along with submit button. If in case
user is not satisfied with the answer provided by system, he can press this Dislike
button. Then log file will be generated for this query or the query will be inserted
into already created log file. Developer comes into picture now for handling such
situations. He will check classes for these queries, enter right answers and will re-
train the classification model. So that whenever user enters the same query next
time he will get correct answer. In this way chat bot will improve its accuracy
and dataset.[3]
To best of our knowledge and after a wide read on the previous published re-
searches work, we found many of the chatbots that provide service in many
domains such as medical consultant, airline help, tourism and so many other ap-
plication, but unfortunately we couldn’t find any Chatbot that help users to get
advices in information security.[7]

SKNSITS, Lonavala. 2020-2021 14 Department of Information Technology

Chapter 6

Conclusion

The main objectives of the project were to develop an algorithm

that will be used to identify answers related to user submitted questions. To de-
velop a database were all the related data will be stored and to develop a web
interface. The web interface developed had two parts, one for simple users and
one for the administrator.[1]

A background research took place, which included an overview

of the conversation procedure and any relevant chat bots available. A database
was developed, which stores information about questions, answers, keywords, logs
and feedback messages. A usable system was designed, developed and deployed
to the web server on two occasions. An evaluation took place from data collected
by potential students of the University. Also after received feedback from the
first deployment, extra requirements were introduced and implemented [3]

We have developed a chatbot that extracts keywords during a chat with users,
then uses the keywords to search a knowledge base (in a json file) and sends
matching replies for users. Having such chatbot, many advantages have been
achieved. These advantages include raising the awareness in a vital field, which
reduces security threats normal users face. In addition, provision of an accu-

15
 Chat Boat-In Future Communication

rate and fast response. This chatbot is intended to be deployed over platform of
telegram at the beginning. The future work will focus on deployment on more
platforms using Json[5]

Chatbots have been on the rise since a couple of years and have already faced
a wide adoption. They are bringing a new way for businesses to communicate
with the world and most importantly with their customers and with the rise of
emerging technologies and Artificial Intelligence (AI). Proving their usability in
the field of customer support, the chatbots can also be extended to help users
mentally like a companion. Our chatbot, HappySoul, is one such approach. It
helps the adolescent users to talk freely about their mental conditions without
being hesitant about it. It proves to be a great help towards society as men-
tal health is a topic of grave concern especially in the youngsters. The future
scope of this project would involve analyzing the different kinds of emotional
disturbances faced by the teenagers and their causes. This would help to evolve
happier generations. The concept of RNN can be used for implementation of a
conversational chat bot[7]

SKNSITS, Lonavala. 2020-2021 16 Department of Information Technology

References

[1]• Dr. Kevin Curran, Dr. Daniel Kelly. Task-based Interaction Chatbot.
IEEE521 final year project Report school of computing, Engineering In-
telligent System

[2] Deshpande, A., Shahane, A., Gadre, D., Deshpande, M., Joshi, P. M, 2017. A
Survey of various chatbot implementation techniques. International Journal
of Computer Engineering and Applications, Volume XI, Special Issue, ISSN
2321-3469

[3] Sarosa, M., Junus, M., Hoesny, M. U., Sari, Z., Fatnuriyah, M 2018. Clas-
sification Technique of Interviewer-Bot Result using Naı̈ve Bayes and Phrase
Reinforcement Algorithms. International Journal of Emerging Technologies
in Learning (iJET), 13(02), 33-47.

[4] Akash Balachandar, Anusha D Kulkarni 2018. Recruitment Chatbot. Inter-

national Research Journal of Engineering and Technology (IRJET), Volume:
05,Issue: 08.

[5] Gentsch P. (2019) Conversational AI: How (Chat)Bots Will Reshape the Dig-
ital Experience. In: AI in Marketing, Sales and Service. Palgrave Macmillan,
Cham.

[6] Yuan, Michael (2018-02-19). Chatbots: Building Intelligent, Cross-Platform,

Messaging Bots. Pearson Education. ISBN 9780134650616.

[7] V. Elupula,”How do chatbots work? An overview of the architecture of chat-

17
 Chat Boat-In Future Communication

bots” August 2018, In https://bigdatamadesimple.com/how-do-chatbots-

work-an-overview-ofthe-architecture-of-a-chatbot/

[8] Rahman, A. M., Abdullah Al Mamun, and Alma Islam. ”Programming chal-
lenges of Chatbot: Current and Future

SKNSITS, Lonavala. 2020-2021 18 Department of Information Technology