A Survey on Various Types of Chatbots

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 09 Issue: 07 | July 2022 www.irjet.net p-ISSN: 2395-0072
© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 688
A Survey on Various Types of Chatbots
Supreetha H V1
1M. Tech Student, Dept. Of CS&E, RVCE Bengaluru, Karnataka, India
---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Chatbots are software applications which are
mainly used to perform tasks asked by the users. Thesearejust
like virtual assistants. With the increase in conversational
medias, chatbot’s application increased drastically. Many
social media, e-commerce, banking sectors also use these
chatbots for easy access to the customers. These chabtots can
communicate with users anytime and they won’trequiremore
cost for maintenance. Thus many websites andconversational
platforms are choosing chatbots as face of their products. The
aim of this paper is to get to know in-details about various
kinds of chatbots available in market and their applications in
real life scenarios.
Key Words: chatbots, conversational media, ML, NLP,
virtual assistants
1.INTRODUCTION
Machine learning and artificial intelligence are hot topics in
recent times. The growth in these domains have made huge
impact in many ares. One of the major applications of these
domains can be seen in chatbots. The chatbots just try to
imitate human behaviour and tries to help users. The
increase in chatbot can decrease work load of many
industries. Say in an e-commerce website, the chatbot can
interact with user and learn user’s personal interests and
suggest some of the product. This will make customerhappy
and will also help sellers to increase their profit. Some of the
chatbots can also be used in health field also to boost the
confidence of the users. Say if a person is in depression and
is not ready to share his difficulties with family and friends,
he can converse with chatbot to come out from the state of
mind. Similarly chatbot’s application can be seen in many
areas.
1.1 Natural Language Processing
NLP is the reason which caused the developmentofchatbots.
With natural language understanding, thechatbotswilltryto
understand the context of the user given input and provide
suitable responses forthe users. The NLU can be dividedinto
further stages namely, lexical analysis, syntax analysis,
semantic analysis, disclosureintegration,pragmaticanalysis.
Lexical analysis include splitting of user given inputs to
paragraphs, sentencesandwords.Thesyntaxanalysischecks
for logical meaning of the user given inputs. Checks if all
words are correctly placed in order or not. “The good is
flower” is rejected by English syntactic analyzer. The
sentence is not placed in meaningful way hence it will be
rejected. It will take care of grammatical part. The semantic
analysis will try to understand context and tries to
understand if there is any meaning for users sentence. Say if
a user asks if the milk is black? The bot should reject such
logic-less questions as it don’t have any meaning. Disclosure
integration stage makeschatbotmoreconversationalenough
for users. This will track the progress of chat and tries to link
current and previousstates to providemeaningfulresponses
for users. The pragmatic analysis do real time analysis for
understanding queriesaskedby theusers.Thediagrammatic
representation of stages in NLU is given in Figure 1.
Figure 1. Stages in NLU
The organization of the report is as follows the section 2 will
discuss about the various kinds of chatbots and its
applications and section 3 will give conclusion followed by
reference section.
2. TYPES OF CHATBOTS
Chatbots can be broadly classified into two types, they are:
AI chatbots and Rule based chatbots. AI chatbots are recent
developments which are using intelligent systems for giving
outputs to uses. It requires more training for these chatbots
to behave like humans. Some times these bots are trained in
such away that it would become much difficult even for
users to understand whether a other end if it is user or a bot
they are conversing with. Rule based bots don’t require
much training, they will be having set of questions and
answers they can interact only for those set of queries.

This section gives indetaileddescriptionaboutvariouskinds
of chatbots with its applications. Menu based chatbots,
Linguistic chatbots, ML chatbots, Hybrid chatbots, keyword
recognition chatbots and Voice bots. Thediagrammaticview
of this is shown in Figure 2.
2.1 Menu Based Chatbots
These chatbots are initially trained with yes or no option
menus. The next question asked by the bot will be linked
with the answer given in the present stage. These bots will
be pre-fed with list of questionnaires with its answer path
for two options also. The answer chosen by user will
determine next set of questions. Mainlydecisiontreemodels
are used to train this type of chatbots.
Figure 2. Types of chatbots
2.2 Linguistic Chatbots
Many linguistic chatbots can be seen now-a-days. A wide
range of applications are based on this type of chatbots.
Many social media platforms like facebook, messenger will
be having a number of linguistic chatbots. These bots will
attract large audience because many users will not beaware
of English language. Adding linguistic chatbots will attract
more customers for a given website and finally increasing
the profit of the organizations. Many times these bots are
created for language learning and language translation
purpose also. These will help to learn new languages by
giving translations in user asked languages. In a placewhere
we don’t know native language, I would be beneficiary
2.3 ML chatbots
The ML chatbots will be properly trained bots. These will be
trained for intent entity selection and response giving
methodologies. Many platforms will provide open source
tools to develop these chatbots. Some of the very famous
platforms where one can develop these kindsofchatbotsare
DiaglogFlow, RASA, gupshup interface, BotKit etc.These will
be having template for chatbot development where one can
create bots according to their needs. They also provide
integration with other messaging platforms like whatsapp,
facebook, telegram etc to deploy build chatbots. One can
select any ML models of their interest to develop chatbots
here. Some of the models that can be used are RNN, Neural
network modes, DIET classifiers, CNN models etc.According
to users comfort they can choose any model to train the
chatbots.
2.4 Voice Bots
The main advantage and growth of chatbot was seen once
voice based chatbot were developed. Because large number
of audience don’t wish to type or some people don’t know
how to type. With the voice bots, all these challenges are
solved. This chatbot will be having an additional feature of
text-to speech or speech-to-textconversions.ManyAPI’swill
help to enable this feature. The main usecase of this
chatbots can be found for specially visualized persons also.
They can give input to the bots by voice and the chatbot will
respond back with voice outputs. Thus they can b used even
as assistants by specially visualized persons. Some of the
additional functionalitieslikesending e-mail,voicemessages
can also be possible using these bots.
2.5 Keyword Recognition based Chatbots
These are requirement specific chatbots. Say if a user asks
“book a movie ticket”, the chatbot will try to retrieve
keywords such as book and movie ticket. It will first collect
the keywords from the queries and then process it. If a bot
can’t understand the keyword then proper output can’t be
given and sudden stop or no response from the bot could be
observed. Hence in these cases proper training of chatbots
are very much essential. More the training lesser will be non
reorganization of keywords.
2.6 Hybrid Model Chatbots
These bots will be having both features of menu drive
chatbots and AI enabled chatbots. These are growing
chatbots now-a-days. In real time scenarios may people will
be lazy enough to type and answer all the queries asked by
the users, So if in another flow, a set of questions with list of
options are provided, users can switch the wayofanswering
according to their convenience. Many of the well developed
e-commerce websites will use this hybrid bots for their
websites. They will provide set of products as menu driven
and sometimes they will also converse contextually with
users to engage them more with their products. Hence this
bot is a milestone in chatbot history.
Table 1 will give comparison of types of chatbots.

Table 1 Comparison of types of chatbots
Chatbot AI/ Rule
Based?
Time for Response
giving and Training
Advantages Limitations
Menu Based
Chatbots
Rule Based  Less Training.
 Less Response
time.
 Quickly response will
be obtained.
 Less ambiguity as
paths are pre defined.
 Limited usage.
 Only used for
Yes/No type of
questions.
Linguistic Chatbots AI Based  More Training.
 More Response
time.
 Helpful for language
learning.
 Can be integrated
with multiple
messaging platforms
 More training is
required.
 Sometimes more
training may
lead to
overfitting.
ML Chatbots AI Based  More Training
 More Response
Time
 Conversational bots
just like humans.
 Context preserved.
 More training is
needed to get
accurate results.
 As it needs
processing
response time is
also more user
needs to wait to
get response.
Voice Bots AI Based  More Training
 More Response
Time
 Helpful for specially
visualized group.
 No typing is required.
 Extra step of
text-to-speech
or speech-to-
text.
 Difficult to
understand the
accent of users
correctly.
Keyword
Recognition Based
Chatbots
Rule Based  More Training
 More Response
Time
 Easy for pre-trained
data
 Fast response.
 More training.
 Limited set of
queries can be
answered.
Hybrid Chatbots AI & Rule Based  More Training
 More Response
Time
 Interactive
 Gives personalized
outputs
 Much time for
training.
 Complex
architecture.
3. APPLICATIONS OF CHATBOTS
The applications of chatbots can be seen in manyareas.Some
of the area of applications of chatbots are discussed in this
section. The diagrammatic representation of chatbot’s
application is shown in Figure 3.
3.1 CUSTOMER SUPPORT
Whenever a user is having any issues or doubts he usually
calls to toll free numbers of customer care. They need to wait
for long period to get their turn. It would be tedious even for
users and also forth person who needs to answer these calls.

If a chatbot is given training for answering these questions it
would be easier. Much of time is not wasted on repetitive
tasks. Moreover chatbots wont get tired and they can be
made available 24/7 with less maintenance cost.
3.2 SOCIAL MEDIA
These bots will be incorporated in social media for engaging
people. Sometimes the chatbots can be harmful also in some
social media platforms. Say in Instagram people may create
fake bots to increase popularity of a person. They may fake
like and comment usingchatbots.Similarcaseswerefoundin
Twitter also where people will buy bots to change the
mindset of people. Some chatbots are also used in creating
fake profiles just to give fake follower numbers for users in
many social media platforms.
Figure 3. Applications of chatbots
3.3 TRAVEL AENCIES
Many travel agencies use chatbots in their websites. These
bots will help in finding customized hotels, restaurants also.
The bots will take care of finding the tickets in different
modes like planes, trains andalso help to get bookingingood
hotels and restaurants. This will make bookings easy for
users and increase the profits of the agencies.
3.4 ASSITANT TO PERSONS
The bots can also be used as personal assistants. Some of the
famous personal assistants are Siri, Alexa, google’s assistant.
These can be used forentertainment purpose also. Theyhelp
to engage users by giving some activities or recommending
some personalized music, comedies, news etc. They can also
be used to track the day-to-dayactivitiesofusersandcanalso
be used to get alert reminders.
3.5 SKILL ENHANCEMENT
Many chatbots will help in skill enhancements by giving
personalized recommendation systems for users’ interest.
They will collect users interests and give more training
regarding skills such as poster making, digital drawings and
video editing and makings.
3.6 BANKING SECTORS
In recent days all banking sectors have moved to online
platforms. With this advancement they have also included
chatbots in their website to guide users of all the benefits
they offer. The bots willalso suggestthetypeofaccountusers
can open, the interests in different accounts,interestsoffered
by the bank and loan facilities. It will help users as they need
not wait in long queues inside bank to get all the details. In
online only users can understand all the facilities of banking
sectors. It will reduce time of users also and reduce burden
on bank employees.
4. CHALLENGES OF CHATBOTS
There are some challenges wile implementing of the
chatbots. Some of them are:
4.1 SECURITY
AI chatbots needs to collect information and data which
are needed to transmit over Internet. The bots must make
sure that the confidential information about the users are
not shared with anyone and help to maintain privacy of
users.
4.2 UNDERSTANDING EMOTIONS
There may be cases where user my give abbreviations as
inputs, and sometimes bot needs to consider redundant
words, and negative words to understand exact context of
the request asked by the users. Proper training of chatbot
is needed to overcome these challenges.
5. CONCLUSIONS
With growth in technology many of the platforms have
included chatbots insidetheirapplications.Alargenumberof
chatbots are already developed in health, e-commerce,social
media, customer service and educational sectors. The main
aim of this paper is to understand various types of chatbots
and the areas in which theycanbeusedfor.Fromtheanalysis
it could be seen that almost every field is incorporating
chatbots based on their requirements. Thus in coming days
once can see major increase in number of chatbots and its
applications, One need to understandbothitsdrawbacksand
applications and try to use this chatbot as in favour to help
others.

REFERENCES
[1] M. M. Khan, "Development of An e-commerce Sales
Chatbot," 2020 IEEE 17th International Conference on
Smart Communities:ImprovingQualityofLifeUsingICT,
IoT and AI (HONET), 2020, pp. 173-176, doi:
10.1109/HONET50430.2020.9322667.
[2] S. Thorpe and H. Scarlett, "Towards a Cyber Aware
Chatbot Service,"2021IEEEInternational Conferenceon
Big Data (Big Data), 2021, pp. 6040-6042, doi:
10.1109/BigData52589.2021.9671775.
[3] W. Mahanan, J. Thanyaphongphat, S. Sawadsitang and S.
Sangamuang, "College Agent: The Machine Learning
Chatbot for College Tasks," 2022 Joint International
Conference on Digital Arts, Media and Technology with
ECTI Northern Section Conference on Electrical,
Electronics, Computer and Telecommunications
Engineering (ECTI DAMT & NCON), 2022, pp. 329-332,
doi: 10.1109/ECTIDAMTNCON53731.2022.9720420.
[4] P. Srivastava and N. Singh, "Automatized Medical
Chatbot (Medibot)," 2020 International Conference on
Power Electronics & IoT Applications in Renewable
Energy and its Control (PARC), 2020, pp. 351-354, doi:
10.1109/PARC49193.2020.236624.
[5] N. Kanodia, K. Ahmed and Y. Miao, "Question Answering
Model Based Conversational Chatbot using BERTModel
and Google Dialogflow," 2021 31st International
Telecommunication Networks and Applications
Conference (ITNAC), 2021, pp. 19-22, doi:
10.1109/ITNAC53136.2021.9652153.
[6] J. Doshi, "Chatbot User Interface for Customer
Relationship Management using NLP models," 2021
International Conference on Artificial Intelligence and
Machine Vision (AIMV), 2021, pp. 1-4, doi:
10.1109/AIMV53313.2021.9670914.
[7] P. Voege and A. Ouda, "A Study on Natural Language
Chatbot-based Authentication Systems," 2021
International Symposium on Networks, Computers and
Communications (ISNCC), 2021, pp. 1-4, doi:
10.1109/ISNCC52172.2021.9615767.
[8] R. Garg et al., "NLP Based Chatbot for Multiple
Restaurants," 2021 10th International Conference on
System Modeling & Advancement in Research Trends
(SMART), 2021, pp. 439-443, doi:
10.1109/SMART52563.2021.9676218.
[9] D. P. P. Villanueva and I. Aguilar-Alonso, "A Chatbot as a
Support SystemforEducational Institutions," 202162nd
International Scientific Conference on Information
Technology and Management Science of Riga Technical
University (ITMS), 2021, pp. 1-6, doi:
10.1109/ITMS52826.2021.9615271.
[10] H. Beattie, L. Watkins, W. H. Robinson, A. Rubin and S.
Watkins, "Measuring and Mitigating Bias in AI-
Chatbots," 2022 IEEE International Conference on
Assured Autonomy (ICAA), 2022, pp. 117-123, doi:
10.1109/ICAA52185.2022.00023.
[11] C. J. Luo and D. E. Gonda, "Code Free Bot: An easy way to
jumpstart your chatbot!," 2019 IEEE International
Conference on Engineering, Technology and Education
(TALE), 2019, pp. 1-3, doi:
10.1109/TALE48000.2019.9226016.
[12] S. Meshram, N. Naik, M. VR, T. More and S. Kharche,
"Conversational AI: Chatbots," 2021 International
Conference on Intelligent Technologies (CONIT), 2021,
pp. 1-6, doi: 10.1109/CONIT51480.2021.9498508.

A Survey on Various Types of Chatbots

More Related Content

Similar to A Survey on Various Types of Chatbots (20)

More from IRJET Journal (20)

Recently uploaded (20)

A Survey on Various Types of Chatbots