Research Journal of Engineering and Technology

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6092
A survey on Different Algorithms used in Chatbot
Siddhi Pardeshi1, Suyasha Ovhal2, Pranali Shinde3, Manasi Bansode4, Anandkumar Birajdar5
1Siddhi Pardeshi, Student, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune
Maharashtra, India
2Suyasha Ovhal, Student, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune
Maharashtra, India
3Pranali Shinde, Student, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune
Maharashtra, India
4Manasi Bansode, Student, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune
Maharashtra, India
5Professor, Dept. of Computer Engineering, Pimpri Chinchwad College of Engineering, Pune, Maharashtra, India
Abstract – Machines are working similar to humans
because of advanced technological concepts. Best example is
chatbot which depends on advanced concepts in computer
science. Chatbots serve as a medium for the communication
between human and machine. There are a number of chatbots
and design techniques available in market that perform
different function and can be implemented in sectors like
business sector, medical sector, farming etc. The technology
used for the advancement of conversational agent is natural
language processing (NLP). Due to these advancements in
artificial intelligence concepts, the precision and perfection
has been greatly improved, chatbots have become a good and
optimal option for many organizations. There is also a chatbot
system in the travel sector which collects user searches and
provides appropriate search results, but still the research is
going on to improve customer satisfaction. We introduce the
background of chatbots so as to get an idea of how chatbots
have been developed. This paper also gives a brief look on
recent design techniques used and thus one can get to know
what advancements can still be done in the chatbotsystemfor
various sectors.
Key Words: Artificial Intelligence, Chatbot, Natural
Language Processing, LSTM, HEIM, Sequence to Sequence,
RNN, Pattern Matching, Naïve Bayes.
A bot is a software application that accomplishes
computerized, robotic tasks and hence is used for work
automation. A chatbot is a software that can converse with
the users in natural language. For that purpose it makes the
use of artificial intelligence. The main aim of chatbot is to
converse with humans and with the help of that it makes
many redundant task easy for humans. Nowadays, chatbots
are used in number of sectors. Some of the popular sectors
are used, educational, e-commerce, gaming and are also
becoming competitors for various cab booking systems.
Basically chatbots have two types:
Rule-based/Command based: In these types of chatbots,
predefined rules are stored which includes questions and
answers. Based on what question has requested by the user
chatbot searches for an answer. But this gives limitations on
the type of questions and answers to be stored.
Intelligent Chatbots/AI Chatbots: To overcome the issue
faced by rule based chatbots intelligent chatbots are
developed. As these are based on advanced machine learning
concepts, they have the ability to learn on their own
depending on questions requested by the user.
Mostly it depends on for what purpose it’s being used.
Command-based or rule-based chatbots have a number of
disadvantages but still they have advantages too.Number of
companies depends on these chatbots as they provide
guidance to focus on improving the experience of customers.
Intelligent or AI chatbots are more convenient to use as they
can handle simple as well as complex questions.
Chatbots which can reply through voice are becoming more
popular due to the technologies like AI, ML etc. Chatbot
provides an artificial service through which it can handle
very difficult user queries of humans. Thus chatbots which
interact via voice are equipt with advance features to
respond to humans. Natural Language Processing (NLP)
technology can understand all kinds of user requests along
with their sentiments, and this widens the use chatbot.
Chatbots are not time bounded and hence can service the
user anytime. Chatbots provides efficient customer service
and thus benefits to businesses and companies. Businesses
also don’t have to pay much if they use chatbots instead of
employees to sell their products. Thus chatbots thereby
improves efficiency. Chatbots are also used in the real estate
sector, education system, entertainment sector Apple Siri,
Amazon Alexa, Facebook Messenger, WeChat are the
examples of some famous chatbots.
In this paper, we are introducing a number of design
techniques widely used by the chatbbot These techniques
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6093
identified by us are , Sequence to Sequence model, pattern
matching, LSTM, HEIM, Naive Bayes, and NLP.
The fascinating history of bots started way back in 1950’s
whenAlan Turing (a British computer scientist)publishedan
article ‘Computing Machinery and Intelligence’ followed by
the Turing Test . This lead to further research and emphasis
on the thought that ‘Can machine think and converse like
humans’. ELIZA and ALICE were two prominent research
results which are explained below.
ELIZA: The concept of chatbot was first coined by MIT
professor Joseph Weizenbaum in the year 1966.Carrying
forward Turing thoughtWeizenbaumdevelopedfirst chatbot
called ELIZA which seemedtomakeuserbelieve thatthey are
actually conversing with a real human. ELIZA was basically
developed to bridge the conversation gap between machine
and humans. ELIZA simulates a psychotherapist and it does
so byusingpatternmatching andsubstitutionmethodologies.
‘Scripts’ which were originallywritteninMAD-slipwereused
to direct ELIZA on how to interactwith user.Elizawas alsoan
early test case for Turing test, which is an Artificial
Intelligence(AI) method which determines does computer
has ability to think like human. However, ELIZA lacked to
maintain conversation with humans or answer complicated
ALICE: ALICE chatbot system which is an acronym for
Artificial Linguistic Internet Computer Entity and was
developed by Dr. Richard S. Wallace in the year 1995 [13].
ALICE is a chatbot which mainly focuses on the areas such as
knowledge representation and algorithm like pattern
matching algorithm. ALICE has won prizes such as Leobner
thrice, thus it is an award winning chatbot with open source
Natural Language Artificial Intelligence. ALICE is also called
as a modified version of ELIZA chatbot system. To take the
user inputs ALICE uses techniques like depth-first search
AIML which is an acronym for Artificial Intelligent Mark-up
Language. They are the files where the knowledge about the
English conversation patter of ALICE is gathered. It is
basically derived from XML which is an acronym for
Extensible Mark-up language. [11] AIML also has its own
templates which are used toproduce response giventouser’s
utterance and also dialogue history. The user sentence are
taken as input by AIML first and then stored which is called
as category. [11] Here, each category comprises of response
template and a set of conditionswhichprovide significance to
the template and called as content.Themodeltheninfluences
it and compared to the decision tree nodes. Thus, the
response is generated by the chatbot whenever user input
gets matched. By using Recursive technique, the template in
AIML repeats the input utterance generated by the user.
However, the response generated is not meaningful every
How is ALICE better than Eliza?
1) Both ALICE and Eliza uses techniques like pattern
matching and knowledge representation but ALICE uses
simple pattern matching algorithm and also easy template
pattern for representation of input and output. Also for
simplifying the input ALICE uses recursive techniques.
2) The pattern matching algorithm used by ALICE is easy to
implement and it depends on depth-first search.
Drawbacks of ALICE chatbot :-
ALICE lacks behind in providing the relevant response and
has no reasoning functionalities also it is not capable of
generating human-like responses. Since for generating such
response it requires huge number of categories for creating a
robust bot but this may cause unfeasibility and difficulties to
maintain and may lead to a time consuming application.
ALICE does not possess features such as grammatical and
sentiment analysis also intelligent features like NLU, for
structuring a particular sentence. During conversation
whenever ALICE is provided with the same repetitive inputs
most of the time it produces same response.
In upcoming years Artificial Intelligence AI came into
existence. AI is a computer science area that affirm the
development of intelligent machine which can response and
work like humans. It can perform task like speech
recognition, translation between language, decision making
and visual perception. AI can provide human like response
from every conversational chatbot. The chatbot can
understand users query and can give accurate response.
3.1 Natural language processing (NLP) :-
Chatbot can answer users queries in natural language which
is made possible by using an artificial intelligence term
natural language processing or NLP. Natural language
processing gives machine the ability toingestthe giveninput,
break it down, extractit’s meaning , determining appropriate
action and answering user in there natural language.
Natural language processing (NLP) has two subsets Natural
language understanding (NLU) and natural language
generation (NLG).
NLU takes unstructured data as input and convert it into
structured data so machine can understand and act upon it.
NLU focuses on extracting the meaning from user input
Natural language generation (NLG) simply converts the
answer generated by chatbot in structured data to human
understandable natural language.
Natural language processing (NLP) does processing in 5
steps. The unstructured data is first passed for lexical
analysis. The structure of words is analyzed and identified.
The whole input text is divided into tokens. Then the tokens
are passed to syntax analysis where tokens are analyzed for
grammar and arranged in a way inwhichrelationshipamong
the word is easy to understood. Then the input is passed to
semantic analysis. The meaning of words or tokens is
extracted in this step. Object in task domain and mapping
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6094
syntactic structure are responsible for meaning extraction
from input. Next step is discourse integration where the
meaning of sentence is tried to extracted using the previous
sentence meaning. Final step is pragmatic analysis. In this
analysis, the main emphasis is on what was said is
reinterpreted on what does it actually meant. After all this
steps the meaning of sentence is known to machine and it
finds answer to user query and passes it to Natural language
generation (NLG) for generation of final output. Natural
language processing (NLP) is used in many chatbot for
effective communicationwith humans. Below figure1shows
Basic working of chatbot using Natural language processing
Figure 1: Understanding Language
3.2 Pattern Matching Algorithm:-
Pattern matching was one of the most used algorithms in
chatbots Pattern Matching Algorithm containsquestions and
answers stored into a database. Questions are named as
patterns whereas answers are named as templates. The
answer for the particular question consists of Artificial
Intelligent Mark-up Language (AIML) tags. Patterns and
templates are stored in the form of a tree. Questions are on
the branches and answers are at the nodes so whenever the
question is asked by the user first that question is searched
for an answer word by word, then it fetches the particular
answer from the node. This type of structure is used in the
ALICE chatbots. The advantage of this algorithm is that user
can easily get answer to the questionas it’s already store.And
thus it is widely used because of it’s incomplexity . This
algorithm stores only particular types ofquestions andthus if
any question other than the stored is asked by the user it
would not be able to give an answer. And thus, it lacks self
learning capability.
Figure 2: AIML Structure
Figure 2 shows example explaining the working of pattern
matching algorithm. In figure 2, the question ‘Who is
Narendra Modi’ is stored into database on the branches of a
hierarchical structure as each word on each branch.Thenthe
answer for this question is stored into node. So,when the
questionlike ‘do you know whoNarendra Modi is’is askedto
the bot ,it will first search the ‘who’ and ‘is’ word then will
search for ‘Narendra’ and then ‘Modi’. Then it will fetch the
answer stored into database and according to what type of
bot itis, whether a chatbot or voice botit will give an answer
to the user accordingly.
The machine then produces:
Human: Who is Narendra Modi?
Robot: Narendra Modi is an Indian politician serving as the
14th and current(2020) Prime MinisterofIndia since
3.3 Naive Bayes Algorithm:-
NaiveBayes is another efficient algorithmusedfor chatbot.In
this algorithm the first step is tokenization and then
stemming.In tokenization,thewhole sentence isdividedinto
words called tokens. Then each token is stemmed. For
example ‘have a great day’ is tokenized and stemmed as
‘have’, ’a’, ’great’, ’day’. Next step is to give training data. This
data is stored in the form of list or dictionaries where
dictionary has class and sentence as attributes. For example,
for the above sentence class will be ‘greeting’. Then the data
is organized by making the list of words of each class. When
we give the input sentence it checks for each word and
compares with all the tokens then it predicts which class has
possibility of having the input sentence. There can be 2 or
more predicted classes for each sentence we give as input so
score is also calculated for each class. Then from those 2 or
more classes 1 with highest score is selected. In this way this
algorithm works.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6095
Let’s see in the above example, suppose we give more
training data as-’Have a great day’, ‘Good morning’, ’Hello
there’,’is theweather rainy?’,’itis too cold today’. Supposewe
give the input as ‘Hii, good morning’.
Training data set:-
‘Have a great day’
‘Good morning’
‘Hello there’
‘is the weather rainy?’
‘it is too cold today’
Input:-’Hii, good morning’
term:-Hii(no match)
term:-morning(1 match, class : greeting).
Hence, output will be classifier :Greeting and score:2
The advantage ofthis algorithm is thatifthere arepredefined
classes it becomes easy to predict.Butincase ifthedata given
as input does not belong to any predefined class it becomes
impossible to predict the output sentence. Hence because of
this disadvantage it has limited usage.
3.4 The Sequence to Sequence
In Sequence to Sequence Model(seq2seq ) model the model
takes input as sequence of words or sentences and then
generates an output which is sequence ofwords.This is done
with the help of recurrent neural network (RNN).Hence
input to this model is token of words and the output of this
model is the translated token of words. The seq2seq model
takes the current word or input along with the neighbouring
words while translating it into output.
The seq2seq model has an encoder and a decoder. This task
is sequence based. The encoder and decoder uses RNNs,
LSTMs to process. The hidden state vector in this model can
be of any size but in most of the cases it is taken as a power
of 2 and a large number like 256, 512, 1024 which may
represent the complexity ofthe complete sequence aswell as
the domain.
The recurrent neural networks (RNNs)takes inputs from the
current example they are fed and also some inputs from the
representation of the previous input. Thus, the output of
seq2seq model at time T is dependent on the current input
as well as the previous input that is at time T-1. This serves
as the reason for the better performance of seq2seq model in
sequence related tasks. The sequential information which is
collected is stored in a hidden state vector of the network
and then it is used in the next instance of the sequence.
As seq2seq model mainly has two components namely
Encoder and Decoder so this model is also called as the
Encoder-Decoder Network.
Role of Encoder:
The main motive of the encoder is to capture the context of
the input sequence in the form of a hidden state vector and
then the encoder feeds it to the decoder which at the last
produces the output sequence. The encoder converts the
input words to corresponding hidden vectors by using deep
neural network layers. The current word and the context of
the word is represented by each vector. The Encoder takes
the sequence of words as an input and generates a final
embedding words atthe end ofthe sequencewith the help of
RNNs. This final embedding sequence of words is then sent
to the Decoder. The Decoder uses it to predict a sequence,
and after every successful predictions, it uses the previous
hidden state vector to predict the next instance of the
Role of Decoder:
The input to decoder is the hidden vector which is generated
and fed by Encoder. The decoder reverses the process of
Encoder. It turns the hidden state vector fed by the encoder
into an output sequence of words. It uses the previous
output as the input context for doing this. It also uses its own
hidden states and current word to predict the next word.
This model’s different applications can be seen in
conversational models, image captioning, text
summarization etc.
Drawback of seq2seq model:
The output sequence of words in seq2seq model depends
entirely on the context defined by the hidden state vector in
the terminating output ofthe encoder. This brings difficulties
for the seq2seq model to process long sentences which
consist of long sequence of words. In such cases there is a
strong possibility that the beginning context gets vanished
by the end of the sequence.
Figure 3: Seq2seq Model
3.5 Hybrid Emotion Interference Model
Tone of voice, expression and even other information are
factors that help humans to understand others emotions.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6096
Humans can understand emotions through the tone of
voices, expressions, body language along with some other
information. In case of chatbot this can be made possible
using model called Hybrid Emotion Interference Model
(HEIM). HEIM model entails two different models, First
model is Latent Dirichlet Allocation (LDA) and second is
Long Short-Term Memory (LSTM) model.
Analogous to humans , machine can develop the proficiency
to read, comprehend and derive meaning from human
languages with an Artificial intelligence field called Natural
language processing (NLP). LDA is a generative statistic
model of NLP. LDA is used to extract text features of input
text. LDA generates topics based on word frequency. LDA
uses bag of words feature representation. LDA works by
computing the probability that a word belongs to a topic.
Table 1 shows an example of text processing done by LDA.
Table 1: Processing example texts
LSTM is used to model the acoustic features of input text.
LSTM does modeling of word-level audio features. LSTM is
convenient to deal with time sequences like voices as it is
capable of acquiring contextual dependencies.
The text information, the acoustic data of users’ queries and
query attributes are incorporated by HEIM in a joint
framework. HEIM combines together LSTM generated high
level delegation of acoustic features andthe textfeatures that
are generated by LDA .To compute the probability of every
emotion categoryHEIM feeds the combinedoutput generated
by LDA and LSTM to a softmax classifier. Softmax classifiers
give probability for each class labelwhilehinge loss gives you
the margin. In some chatbot to improve efficiency a
RecurrentAutoencoderGuidedbyQueryAttributes (RAGQA)
which incorporates other emotion-relatedquery attributes is
used to pre-train LSTM.
HEIM is used in Sogou Voice Assistant (Chinese Siri).
3.6 Long Short Term memory(LSTM):-
LSTM an acronym for Long Short Term memory is an
Artificial RNN that is Recurrent Neural Network. LSTM
provide great advantage not only in processing the single
data input like images but also the entire sequence of data
like speech or video. Handwriting recognition and Speech
recognition are the major task done by LSTM algorithm.
LSTM in chatbotis mainly used for speech recognition.LSTM
algorithm is best-suited in classifying techniques,processing,
making prediction’s based on time series data. They were
specially developed for solving vanishing gradientproblems.
LSTM takes vector data as input . So before actually using
LSTM algorithm the text input is first converted into vector
form. The process of converting text data into vector is called
as word embedding and it can bedone using skip-gram.Later
when the text is converted into vector form, it is passed to
LSTM algorithm as an input for further processing. LSTM
algorithm comprises of three gates such as input gate, forget
gate, and output gate. It also consists of cell memory, tanh
activation function and sigmoid activation function. [17]
There are various stacked blocks of LSTM where each block
takes three inputs et , ct-1 and ht-1, here ct-1 and ht-1 are input
from earlier step. Thus, finally the output is computed thatis
ht..BelowFigure 4 shows the computation of ht..
Figure 4: Computation of ht based on the formulae
How is LSTM better than Simple RNN?
Simple RNN is nothing but the product of input xtand earlier
output ht-1which further passed to activation function tanh.
Here there no gates present as like LSTM algorithm.Whereas
LSTM is the updated version of RNN which actually solve the
problem of vanishing data by maintaining in addition the
three gates input gate it, output gate ot, and forget gate ft also
the cell vector ct.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6097
The following table 1 shows the time (in second) required to
compute the output for one phrase question by Simple RNN
and LSTM [15]. In Table 2 we can see slight difference in
computing time between Simple RNN and LSTM. The time
difference in random but it is relatively small.
Question Simple RNN
(time in second)
(time in second)
Hello 0.09 0.83
Morning 1.12 1.10
Noon 1.10 0.90
Table 2: One Phrase Question Test
The following table 3 shows the time (in second) required to
compute the output for more than one phrase question by
Simple RNN and LSTM [15]. In table 2 we can see LSTM
works better than Simple RNN for more than one Phrase.
This is because LSTM is created to recognize the word order
while Simple RNN algorithm treats every word
independently. Also, there is possibility thatifless amount of
training data is used then Simple RNNalgorithm is incapable
of reading the phrase pairswhich usually occur.Thus, Simple
RNN requires more time duration to respond to the question
.So, LSTM algorithm provides more controllability and better
Question Simple RNN
(time in
(time in
Thank you for your
0.92 1.00
I want to order a ticket 1.66 1.09
Is the ticket to
Bangalore still
2.05 1.19
Table 3: More than One Phrase Question Test
Chatbots are widely in use now-a-days for various business
or personal purpose. They brought a newway for businesses
to communicate with their customers with the help of
emerging technologies likeArtificialIntelligence (AI).Not only
chatbots can be used for customer support but also it can
help users to act as their companion.
In this survey we studied several Deep learning techniques
and algorithms likeNatural LanguageProcessing (NLP),Long
Short-Term Memory(LSTM) and Hybrid Emotion Inference
Model (HEIM) to make the system with self-learning
capabilities, user emotionanalysis andalsoprovide flexibility
for chatinterface. We completed the survey on how chatbots
can produce more personalized and accurate predictions for
a user while having an intelligent conversation in natural
we studied can show great results on large real-world data
While texting, we use tons of abbreviations and also lot of
slang words. Sometimes autocorrect feature almost jumbles
messages once during a while. The input to conversational
agent can also be in form of sentence fragments. As we
communicate so differently in various messaging apps from
the way we do in spoken conversation, it is important that
the chatbot should understand a message despite of
containing errors in grammar or spelling in the conversation.
Thus, in future it would be possible to implement chatbot
using slang language along with NLP concepts. Voice
Dialogue Applications like chatbots recognize users
emotions and generate responses which would be more
humanized and would be capable of understanding users
intention clearly and thus help in optimizing the bot-human
We express immense gratitude to our Seminar Guide Prof.
Anandkumar Birajdar for his support and encouragement.
We also especially thank him for his useful suggestions and
having laid down the foundation for the success ofthiswork.
We would also like to thank our Research & Innovation
coordinator Prof. Dr. Swati Shinde and Seminar Coordinator
Prof. Pallavi Dhade for their genuine support , guidance , and
assistance from early stages of the seminar. We would also
like to express our gratitude to Prof Dr. K. Rajeswari,Head of
Computer Engineering Department for her unwavering
succour during the whole seminar activity. We would also
like to thank all the web communities for enriching us with
their enormous information.
[1] Nahdatul Akma Ahmad, Mohamad Hafiz Che
Hamid,Azaliza Zainal,Muhammad Fairuz Abd Rauf,
Zuraidy Adnan ,”Review of Chatbots Design
Techniques”,August 2018.
[2] J. Masche and N. Le, “A Review of Technologies for
Conversational Systems”, 2018.
International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 05 | May 2020 p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page 6098
[9] Building Chatbot with Emotions [Honghao WEI, Yiwei
Zhao, JunjieKe(2018)]
[10] Inferring User’s Emotions for Human-Mobile Voice
Dialogue Applications [Boyawu, JiaJia, Tao He, Juan
Du, Xiaoyuan Yi, YishuangNing (2016)]
[11] Mohammad Nuruzzaman, Omar Khadeer Hussain, “A
Survey on Chatbot Implementation in Customer
Service Industry through Deep Neural
[12] Weizenbaum, J., ELIZA: a computer program for the
study of natural language communication between
man and machine. Commun. ACM, 1966. 9(1): p. 36-
[13] Wallace, R.S., The Anatomy of A.L.I.C.E, in Parsing the
Turing Test: Philosophical and MethodologicalIssues
in the Quest for the Thinking Computer, R. Epstein, G.
Roberts, and G. Beber, Editors. 2009, Springer
Netherlands: Dordrecht. p. 181-210.
[14] Vibhor Sharma, Monika Goyal , Drishti Malik, “An
Intelligent Behaviour Shown by Chatbot System”,
ISSN:2454-4116, Volume-3, Issue-4, April 2017.
[15] Yulius Denny Prabowo, Harco Leslie Hendric Spits
Warnars, Widodo Budiharto, Achmad Imam
Kistijantoro, Yaya Heryadi, Lukas, “Lstm And Simple
Rnn Comparison In The Problem Of Sequence To
Sequence On Conversation Data Using Bahasa
Indonesia”, The 1st 2018 INAPR International
Conference, 7 Sept 2018, Jakarta, Indonesia.
[16] Milla T Mutiwokuziva, Melody W Chanda, Prudence
Kadebu, Addlight Mukwazvure, Tatenda T Gotora, “A
Neural-network based Chat Bot”,2017.
[17] Keng-hao Chang, Ruofei Zhang , Zi Yin, “DeepProbe:
Information Directed Sequence Understanding and
Chatbot Design via Recurrent Neural Networks”, 1
Mar 2018.
[18] Vishal Aggarwal, Anjali Jain, Harsh Khatter, Kanika
Gupta , “Evolution of Chatbots for Smart Assistance”,
August 2019

Get Professional Assignment Help Cheaply

Buy Custom Essay

Are you busy and do not have time to handle your assignment? Are you scared that your paper will not make the grade? Do you have responsibilities that may hinder you from turning in your assignment on time? Are you tired and can barely handle your assignment? Are your grades inconsistent?

Whichever your reason is, it is valid! You can get professional academic help from our service at affordable rates. We have a team of professional academic writers who can handle all your assignments.

Why Choose Our Academic Writing Service?

  • Plagiarism free papers
  • Timely delivery
  • Any deadline
  • Skilled, Experienced Native English Writers
  • Subject-relevant academic writer
  • Adherence to paper instructions
  • Ability to tackle bulk assignments
  • Reasonable prices
  • 24/7 Customer Support
  • Get superb grades consistently

Online Academic Help With Different Subjects


Students barely have time to read. We got you! Have your literature essay or book review written without having the hassle of reading the book. You can get your literature paper custom-written for you by our literature specialists.


Do you struggle with finance? No need to torture yourself if finance is not your cup of tea. You can order your finance paper from our academic writing service and get 100% original work from competent finance experts.

Computer science

Computer science is a tough subject. Fortunately, our computer science experts are up to the match. No need to stress and have sleepless nights. Our academic writers will tackle all your computer science assignments and deliver them on time. Let us handle all your python, java, ruby, JavaScript, php , C+ assignments!


While psychology may be an interesting subject, you may lack sufficient time to handle your assignments. Don’t despair; by using our academic writing service, you can be assured of perfect grades. Moreover, your grades will be consistent.


Engineering is quite a demanding subject. Students face a lot of pressure and barely have enough time to do what they love to do. Our academic writing service got you covered! Our engineering specialists follow the paper instructions and ensure timely delivery of the paper.


In the nursing course, you may have difficulties with literature reviews, annotated bibliographies, critical essays, and other assignments. Our nursing assignment writers will offer you professional nursing paper help at low prices.


Truth be told, sociology papers can be quite exhausting. Our academic writing service relieves you of fatigue, pressure, and stress. You can relax and have peace of mind as our academic writers handle your sociology assignment.


We take pride in having some of the best business writers in the industry. Our business writers have a lot of experience in the field. They are reliable, and you can be assured of a high-grade paper. They are able to handle business papers of any subject, length, deadline, and difficulty!


We boast of having some of the most experienced statistics experts in the industry. Our statistics experts have diverse skills, expertise, and knowledge to handle any kind of assignment. They have access to all kinds of software to get your assignment done.


Writing a law essay may prove to be an insurmountable obstacle, especially when you need to know the peculiarities of the legislative framework. Take advantage of our top-notch law specialists and get superb grades and 100% satisfaction.

What discipline/subjects do you deal in?

We have highlighted some of the most popular subjects we handle above. Those are just a tip of the iceberg. We deal in all academic disciplines since our writers are as diverse. They have been drawn from across all disciplines, and orders are assigned to those writers believed to be the best in the field. In a nutshell, there is no task we cannot handle; all you need to do is place your order with us. As long as your instructions are clear, just trust we shall deliver irrespective of the discipline.

Are your writers competent enough to handle my paper?

Our essay writers are graduates with bachelor's, masters, Ph.D., and doctorate degrees in various subjects. The minimum requirement to be an essay writer with our essay writing service is to have a college degree. All our academic writers have a minimum of two years of academic writing. We have a stringent recruitment process to ensure that we get only the most competent essay writers in the industry. We also ensure that the writers are handsomely compensated for their value. The majority of our writers are native English speakers. As such, the fluency of language and grammar is impeccable.

What if I don’t like the paper?

There is a very low likelihood that you won’t like the paper.

Reasons being:

  • When assigning your order, we match the paper’s discipline with the writer’s field/specialization. Since all our writers are graduates, we match the paper’s subject with the field the writer studied. For instance, if it’s a nursing paper, only a nursing graduate and writer will handle it. Furthermore, all our writers have academic writing experience and top-notch research skills.
  • We have a quality assurance that reviews the paper before it gets to you. As such, we ensure that you get a paper that meets the required standard and will most definitely make the grade.

In the event that you don’t like your paper:

  • The writer will revise the paper up to your pleasing. You have unlimited revisions. You simply need to highlight what specifically you don’t like about the paper, and the writer will make the amendments. The paper will be revised until you are satisfied. Revisions are free of charge
  • We will have a different writer write the paper from scratch.
  • Last resort, if the above does not work, we will refund your money.

Will the professor find out I didn’t write the paper myself?

Not at all. All papers are written from scratch. There is no way your tutor or instructor will realize that you did not write the paper yourself. In fact, we recommend using our assignment help services for consistent results.

What if the paper is plagiarized?

We check all papers for plagiarism before we submit them. We use powerful plagiarism checking software such as SafeAssign, LopesWrite, and Turnitin. We also upload the plagiarism report so that you can review it. We understand that plagiarism is academic suicide. We would not take the risk of submitting plagiarized work and jeopardize your academic journey. Furthermore, we do not sell or use prewritten papers, and each paper is written from scratch.

When will I get my paper?

You determine when you get the paper by setting the deadline when placing the order. All papers are delivered within the deadline. We are well aware that we operate in a time-sensitive industry. As such, we have laid out strategies to ensure that the client receives the paper on time and they never miss the deadline. We understand that papers that are submitted late have some points deducted. We do not want you to miss any points due to late submission. We work on beating deadlines by huge margins in order to ensure that you have ample time to review the paper before you submit it.

Will anyone find out that I used your services?

We have a privacy and confidentiality policy that guides our work. We NEVER share any customer information with third parties. Noone will ever know that you used our assignment help services. It’s only between you and us. We are bound by our policies to protect the customer’s identity and information. All your information, such as your names, phone number, email, order information, and so on, are protected. We have robust security systems that ensure that your data is protected. Hacking our systems is close to impossible, and it has never happened.

How our Assignment  Help Service Works

1.      Place an order

You fill all the paper instructions in the order form. Make sure you include all the helpful materials so that our academic writers can deliver the perfect paper. It will also help to eliminate unnecessary revisions.

2.      Pay for the order

Proceed to pay for the paper so that it can be assigned to one of our expert academic writers. The paper subject is matched with the writer’s area of specialization.

3.      Track the progress

You communicate with the writer and know about the progress of the paper. The client can ask the writer for drafts of the paper. The client can upload extra material and include additional instructions from the lecturer. Receive a paper.

4.      Download the paper

The paper is sent to your email and uploaded to your personal account. You also get a plagiarism report attached to your paper.

smile and order essaysmile and order essay PLACE THIS ORDER OR A SIMILAR ORDER WITH US TODAY AND GET A PERFECT SCORE!!!

order custom essay paper