DAHA INTERNATIONAL

UNIVERSITY

TITLE: FAKE NEWS DETECTION USING ML (IBS

MOGADISHU SOMALIA)

A PROJECT

PRESENTED TO THE FACULTY OF COMPUTER SCIENCE AND

ENGINEERING

DAHA INTERNATIONAL UNIVERSITY

Mogadishu, Somalia

In partial fulfilment of the

requirements for the degree of
bachelor of science in
information technology

BY
ABDIFITAH MOHAMED ABDI ID 5211
AUGUST 2025
 DECLARATION A

We declare this thesis is our original work and has not been presented for a
Degree or any other academic award in any university or Institution of learning”
Signature 1: _____________________________________ Date: ___/ ____

Signature 2: _____________________________________ Date: ___/ ____

Signature 3: _____________________________________ Date: ___/ ____

I.

i
 DECLARATION B

“We confirm that the work reported in this thesis was carried out by the
candidate(s) under my supervision”.

Name and signature of Supervisor: __________________________________________ Date:

_______/______/_______________

ii
 APPROVAL SHEET

This thesis entitled “ IOT BASED HEALTHCARE MONITORING SYSTEM

USING ARDUINO Prepared and submitted by Abdirahman Ali Omar and
Mohamed Hassan Ahmed in partial fulfillment of requirements for the degree of
Bachelor of Science in information Technology has been examined and

approved by the panel on oral examination with a grade of:

Name and Sig. of Chairman of the Panel

Name and Sig. of Panelist

____Name and Sig. of Panelist

Name and Sig. of Panelist

 ACKNOWLEDGEMENT

Before we get into thick of things, we would like to thank our Allah who
enabled us to accomplish this successful project and then add a few heart-
felt words for people who are the part of this project report in numerous
ways, people who gave their un-ending support from starting stages to the
completion of this project.

Other great acknowledgements are for our project Supervisor Eng.

Mohamed Mohamud Yusuf, who gave us the opportunity to take up the
project on “IOT BASED HEALTHCARE MONITORING SYSTEM System” as
a part of our study environment and also helped us this project.

It gives us extreme pleasure to acknowledge our heart-felt, thanks to him

who through the study has been a continuous source of encouragement and
instructions, his enthusiastic and unstinted co-operation and support
inspired us largely.

We would like to thank also to Dean of faculty of computer science and

technology

Eng. Bashir Sheikh Mohamed Hussein who helped and gave us the
most important information that we based on our project.
 Dedication

To our parents, whose love and unerring guidance leaves us with

no one to blame but ourselves for our faults and failings We
dedicated this project and documentation works to our beloved
parents who for a long time struggled and forfeited all their luxury
to build our knowledge where availability of education was rarely
feasible, and without them no actions could have been taken. Also
we would like to dedicate this project to our brothers, sisters and
relatives who have been prominent facilitators to many of our
project tasks, and our teachers who have contributed directly or
indirectly to our education up to where we are now and classmates
at DAHA INTERNATIONAL UNIVERSITY who have been
supplementary support to our study.
 Abstract

Nowadays, with the advancement of technology, the use of news sources has also undergone a great
evolution. News sources have constantly evolved from past to present, ranging from magazines to
radios, from newspapers to televisions. The fact that it has become so easy to access news has caused
society to pay more attention to fake news. Fake news has the ability to influence society through
news sources such as social media, which can reach wider audiences with the development of
technology. The difficulties of users in accessing accurate and reliable sources in this information flow
that shapes their daily lives increases the potential for the spread of fake news, and it becomes
increasingly difficult to distinguish between real and fake news. In this study, classification models for
fake news detection were designed using machine learning algorithms. The dataset, which includes
fake and real news examples, contains 42,000 examples. Each class, including fake and real samples,
contains 22,000 sample data. In order to increase data quality, accuracy and usability, preprocessing
methods were applied to the data set. The removal of numbers, stop words, and html tags was done in
the pre-processing step to remove unnecessary information from the text. Models were created for
fake news detection with singular and ensemble classification algorithms. Performance evaluation of
the models was performed using 5-fold cross-validation. In the performance comparisons of the
models, values such as accuracy, sensitivity, specificity, tp rate and fp rate were calculated. The
highest performance results were observed in the random forest classification algorithm with an
accuracy rate of 76%.

Keywords: Fake News Detection, News on Social Media, Classification.(Patel et al., 2020)
 Table Of Contents

DECLARATION A.......................................................................................................i

DECLARATION B.......................................................................................................ii

APPROVAL SHEET.....................................................................................................iii

ACKNOWLEDGEMENT...............................................................................................iv

Dedication................................................................................................................v

Abstract....................................................................................................................vi

LIST OF TABLES........................................................................................................x

LIST OF FIGURES.......................................................................................................xi

CHAPTER ONE...........................................................................................................1

INRODUCTION...........................................................................................................1

1.0: INTRODUCTION..................................................................................................1

1.1: BACKGROUND OF THE PROJECT-----------------------------------------------------------------------1

1.2 : STATEMENT OF THE PROBLEM.........................................................................5

1.3 RESEARCH QUESTIONS.....................................................................................6

1.3 : PROJECT OBJECTIVES.......................................................................................6

1.4 : THE SCOPE OF THE SYSTEM............................................................................7

1.5 : SIGNIFICANCE OF THE PROJECT.......................................................................7

1.6 : PROJECT ORGANIZATION.................................................................................9

1.7 : CHAPTER SUMMARY........................................................................................10

CHAPTER TWO..........................................................................................................11

LITERATURE REVIEW................................................................................................11

2.0 : INTRODUCTION................................................................................................11

2.1 : HISTORY OF IOT...............................................................................................11

2.2 : THEORITICAL FRAMEWORK..............................................................................12

2.3 : MACHINE LEARNING........................................................................................15

2.3.1 : MACHINE LEARNING CLASSIFICATION...........................................................16

2.3.2 Applications Of Machine Learning...................................................................17

2.4 : CASE STUDY------------------------------------------------------------------------------------------18

2.5 : EXISTING SYSTEM-----------------------------------------------------------------------------------19

A) IOT based fire alarm system temperature and smoke sensor with android
connectivity using
Arduino.---------------------------------------------------------------------------------------------20
B) IOT fire detection system using sensor with Arduino_____________________________21

2.6 : GAP ANALYSIS...................................................................................................23

2.7 : PREVIEW OF THE SYSTEM.................................................................................23

2.8 : CHAPTER SUMMARY.........................................................................................24

CHAPTER THREE.....................................................................................................25

REQUIREMENT ANALYSIS.......................................................................................25

3.0 : INTRODUCTION................................................................................................25

3.1 : USER REQUIREMENT ANALYSIS........................................................................25

3.1.1 : ORGANIZATION PROFILE................................................................................25

3.1.2 : CURRENT SYSTEM..........................................................................................26

3.2 : DATA GATHERING............................................................................................26

3.2.1 : Interview........................................................................................................27

Advantages of interview........................................................................................27

Disadvantages of interview....................................................................................28

3.2.2 : Observation...................................................................................................28

3.3 : PROCESS MODELING........................................................................................29

3.3.1 UML.................................................................................................................29

3.3.2 USE CASE DIAGRAM........................................................................................30

3.4 DATA MODELING...............................................................................................31

3.4.2 TYPES OF RELATIONSHIP...............................................................................31

3.5 : USER REQUIREMENT SPECIFICATION...............................................................31

3.5.1 : NEW PROPOSED SYSTEM...............................................................................32

3.5.2 : SOLUTION STRATEGY.....................................................................................33

3.6 : SYSTEM REQUIREMENT SPECIFICATION...........................................................33

3.6.1 : SOFTWARE REQUIREMENTS...........................................................................34

3.6.2 : HARDWARE REQUIREMENTS..........................................................................34

3.6.3 : SYSTEM REQUIREMENT DEFINITION...............................................................34

3.7 : FEASIBILITY STUDY...........................................................................................36

3.8 : CHAPTER SUMMARY.........................................................................................39

CHAPTER FOUR......................................................................................................40

SYSTEM DESIGN.....................................................................................................40

4.0 INTRODUCTION..................................................................................................40

4.1 DESIGN GOALS..................................................................................................40

4.2 SYSTEM DESIGN................................................................................................40

4.2.1 SYSTEM ARCHITECTURE..................................................................................41

4.2.2 DATASET DESCRIPTION...................................................................................41

4.3 Table Design.....................................................................................................42

4.4 REQUIREMENTS.................................................................................................42

4.4.1Functional Requirements.................................................................................43

4.4.2 Non-Functional Requirements.........................................................................44

4.4.3 Domain requirements.....................................................................................44

4.5 CHAPTER SUMMARY.......................................................................................44

CHAPTER FIVE........................................................................................................45
SYSTEM DEVELOPMENT.........................................................................................45

5.0 CODING PHASE..................................................................................................45

5.1 TYPES OF TESTING............................................................................................53

5.2 System implementation....................................................................................53

5.2.1 CORE CONSTRUCTION....................................................................................54

5.2.2 POWER-CONSTRUCTION.................................................................................54

5.3 User documentation _____________________________________________________54

CHAPTER SIX..........................................................................................................55

RECOMMENDATION & CONCLUSION......................................................................55

6.1 CONCLUSION.....................................................................................................55

6.1.1 Achievements.................................................................................................55

6.1.2 limitation.........................................................................................................56

6.2 Future Enhancement.........................................................................................57

6.3 Concluding........................................................................................................58

References_________________________________________________________________59

Appendix: A............................................................................................................63

Appendix: B............................................................................................................62

Appendix: C............................................................................................................63
 LIST OF TABLES

Table 1.1 Project organization......................................................................................9

Table 2.1 shows the comparison between the existing system.................................22

Table 3: 1 Hardware Interface....................................................................................35

Table 3: 2 Software Interface.....................................................................................36

Table 3: 3 Technical feasibility....................................................................................37

Table 3: 4 Operational Feasibility...............................................................................37

Table 3: 5 Economic feasibility...................................................................................38

Table 3: 6 schedule feasibility....................................................................................38

Table 4.1 Table Design--------------------------------------------------------------------------------------

42
 LIST OF FIGURES

Figure 2.1 Healthcare Monitoring System using

Arduino-----------------------------------20
Figure 2.2 patient health monitoring
system-------------------------------------------------21
Figure 2.3 Smart Health Monitoring System for Efficient
Service--------------------------22
Figure 3.1 use case diagram--------------------------------------------------------------------
30
Figure: 3.2 Entity- relationship
diagram-------------------------------------------------------31
Figure 4.1 System
Architecture------------------------------------------------------------------41
Figure 4.2: Software
requirements--------------------------------------------------------------43

Xi
 INTRODUCTION
1.0 INTRODUCTION
Fake news has become a pervasive problem in the modern world, with the potential to mislead individuals
and even sway public opinion. The spread of fake news is facilitated by the rapid growth of social media
platforms, which provide a means for false information to be disseminated quickly and widely. This has
led to growing concerns about the impact of fake news on everything from public health to political
elections, and has spurred the development of new approaches to detecting and preventing its spread. One
of the most promising approaches to fake news detection is the use of machine learning algorithms, which
can analyze and classify news articles based on their content. Machine learning has emerged as a
powerful tool for identifying subtle differences in language, syntax, and other features that may indicate
the presence of fake news. By training on large datasets of real and fake news articles, machine learning
algorithms can learn to distinguish between the two and make predictions about the authenticity of new
articles. There are several challenges associated with fake news detection using machine learning,
however. One of the main challenges is the difficulty of distinguishing fake news articles from real news
articles, especially when the fake news is designed to mimic real news in terms of style, tone, and
formatting. Another challenge is the need for large and diverse datasets of news articles, in order to train
machine learning algorithms effectively. Additionally, machine learning algorithms must be constantly
updated to adapt to new types of fake news and to maintain their accuracy over time. Despite these
challenges, there has been growing interest in using machine learning for fake news detection, with
researchers and practitioners developing a wide range of algorithms and models for this purpose. Some of
the most popular machine learning algorithms used for fake news detection include Naive Bayes, Logistic
Regression, and Support Vector Machines, among others. Each of these algorithms has its own strengths
and weaknesses, and may be better suited to different types of fake news detection tasks. One of the key
advantages of machine learning for fake news detection is its ability to learn patterns and make
predictions based on large amounts of data. This allows machine learning algorithms to identify even
subtle differences in language and other features that may indicate the presence of fake news. For
example, some machine learning algorithms can analyze the presence of certain words or phrases that are
commonly associated with fake news, while others can assess the overall sentiment of an article and
compare it to other articles in order to determine whether it is likely to be fake or real. To train machine

1
learning algorithms for fake news detection, researchers typically use large datasets of news articles that
have been manually labeled as fake or real. These datasets may be obtained from a variety of sources,
including social media platforms, news websites, and other online sources. Once a dataset has been
obtained, it must be preprocessed in order to extract relevant features and prepare it for use in machine
learning algorithms. There are several preprocessing techniques that may be used for fake news detection
using machine learning, including text cleaning, tokenization, stemming, and stop word removal. Text
cleaning involves removing any extraneous characters or symbols from the text, while tokenization
involves breaking the text up into individual words or phrases. Stemming involves reducing each word to
its base form, while stop word removal involves removing common words that do not carry significant
meaning, such as "the" and "and". Once a dataset has been preprocessed, it may be used to train and test
machine learning algorithms for fake news detection. Researchers typically use a range of metrics, such
as accuracy, precision, and recall, to evaluate the performance of these algorithms. In general, machine
learning algorithms have shown promising results for fake news detection, with some studies reporting
accuracy rates of up to 95%. Overall, fake news detection using machine learning is a rapidly evolving
field, with new algorithms and models. Recently, more websites are being created that are trying to help
assess the accuracy of the information, the so called fact-checkers. Unfortunately, it is not possible to
check them manually with such a massive amount of new messages. Hence, more and more hope is
placed in automatic fake news. The main reason for the rapid increase in the use of disinformation is the
ability to use not only traditional mainstream media but also social media, like Twitter or Facebook. It is
worth noting that its popularity can rapidly grow according to the rule that false news spreads faster and
more comprehensive. Its extensive spread has a severe negative impact on media users and society. The
main goal of publishing such information with malicious content is to attract readers, which could
increase publisher rank and popularity, which consequently increases revenues form adds. The main
contributions of this paper are as follows: Formulating the problem of fake news detection as a data
stream classification task. Proposing a novel pattern classification methods based on feature extraction
techniques, which address the detection of fake news in streaming data from social media .An extensive
experimental analysis backed-up by the statistical tests.(Lohitha et al., 2023)

European In recent years, the dissemination of fake news has been brought more and more into
the spotlight as it has been massively used to disseminate political propaganda, influence the
outcome of elections or harm a person or a group of people.

Highly sophisticated applications (bots) are organization in networks and massively spread to
amplify fake news over social media in the form of text, images, audio or video files. Often, these

2
bot nets happened to be organization by foreign state actors, trying to obscure the originator.

Fighting fake news is extremely challenging, as:

 in a democracy, freedom of speech is a fundamental right fostering media independence and

pluralism; however, sometimes there is a very subtle line between separating unconventional
personal views and claims of truth from fake news;

 fake news can be detected by checking consistency of the news with different domains

1.1 BACKGROUND OF THE PROJECT

From an NLP perspective, researchers have studied numerous aspects of the credibility of
online information. For example applied the time-sensitive supervised approach by relying on
tweet content to address the credibility of a tweet in different situations. used LSTM in a
similar problem of early rumour detection. In another work, aimed at detecting the stance of
tweets and determining the veracity of the given rumour with convolution neural networks. A
submission to the SemEval 2016 Twitter Stance Detection task focuses on creating a bag-of-
words autoencoder and training it over the tokenized tweets. Another team, combined multiple
models in an ensemble providing a 50/50 weighted average between a deep convolutional
neural network and a gradient-boosted decision tree. Though this work seems to be similar to
our work, the difference lies in the construction of an ensemble of classifiers. In a similar
attempt, a team concatenated various features vectors and passed them through an NLP model.
Passive Aggressive algorithm is a margin-based online learning algorithm for binary
classification. It is also an algorithm of a soft margin-based method and robust to noise. It can
be used in fake news detection Term Frequency-Inverse Document Frequency is also a method
used to represent text in.(Singhal, 2017)

1.2 STATEMENT OF THE PROBLEM

In this day and age, it is extremely difficult to decide whether the news we come across is real
or not. There are very few options to check the authenticity and all of them are sophisticated
and not accessible to the average person. There is an acute need for a web-based fact-checking
platform that harnesses the power of Machine Learning to provide us with that opportunity.

3
 (Singhal, 2017)

1.3 RESEARCH QUESTIONS

A SLR has to answer some RQs. In this literature review, three research questions will be answered
on the basis of valid arguments. These two research questions are given below.

RQ1: Why machine learning is required to detect the fake news?

RQ2: Which machine learning supervised classifiers can be used for detecting fake news?

RQ3: How classifiers of machine learning are trained to detect fake news?

These research questions will be answered in the result and discussion section of this literature
review(Et al., 2021)

1.4 PROJECTIVE OBJECTIVE

The objective of this project is to examine the problems and possible significances
related with the spread of fake news. We will be working on different fake news data set
in which we will apply different machine learning algorithms to train the data and test it
to find which news is the real news or which one is the fake news. As the fake news is a
problem that is heavily affecting society and our perception of not only the media but
also facts and opinions themselves. By using the artificial intelligence and the machine
learning, the problem can be solved as we will be able to mine the patterns from the
data to maximize well defined objectives. So, our focus is to find which machine
learning algorithm is best suitable for what kind of text dataset. Also, which dataset is
better for finding the accuracies as the accuracies directly depends on the type of data
and the amount of data. The more the data, more are your chances of getting correct
accuracy as you can test and train more data to find out your results.

With the advancement of technology, digital news is more widely exposed to users globally and
contributes to the increment of spreading and disinformation online. Fake news can be found
through popular platforms such as social media and the Internet. There have been multiple

4
 solutions and efforts in the detection of fake news where it even works with tools. However,
fake news intends to convince the reader to believe false information which deems these
articles difficult to perceive. The rate of producing digital news is large and quick, running
daily at every second, thus it is challenging for machine learning to effectively detect fake
news.(Lohitha et al., 2023)

1.5 THE SCOPE OF THE SYSTEM

The main goal of this project is to build a machine learning-based system that can
automatically detect whether a given news article is fake or real. The system will focus only
on text-based news data, and will use a combination of data preprocessing, feature
extraction, and classification techniques to make accurate predictions.

The scope of the system includes the following:

 Collecting a dataset of both real and fake news articles.

 Preprocessing the news text to remove irrelevant elements.

 Converting text into numerical features using techniques such as TF-IDF or word
embeddings.

 Training machine learning models such as Naive Bayes, Logistic Regression, or Random
Forest.

 Evaluating the model using performance metrics like accuracy, precision, recall, and F1-
score.

 Providing a simple user interface where users can input a news article and receive a
prediction.

1.6 SIGNIFICANCE OF THE PROJECT

However, on the other hand, social media provides the ideal place for the creation and
spread of fake news. Fake news can become extremely influential and has the ability to spread
exceedingly fast. With the increase of people using social media, they are being exposed to

5
 new information and stories every day. Misinformation can be difficult to correct and may
have lasting implications. There for we need to make sure the news we read are correct and
real so, there should be be fake news detection in our applications so that we don‟t fall for
those fake news spreading around us .(37110401 ) 37110431 ), n.d.)

1.7 PROJECT ORGANISATION

Chapter one The system of the scope
Projective objective

1.8 CHAPTER SUMMER

This chapter outlines the boundaries and extent of the proposed system, "Fake News Detection
using Machine Learning." It defines what the system will do, what features will be included, and
what limitations are present.

CHAPTER TWO
LITERATURE REVIEW

The available literature has described many automatic detection techniques of fake news and
deception posts. Since there are multidimensional aspects of fake news detection ranging from
using chatbots for spread of misinformation to use of clickbaits for the rumor spreading .There
are many click baits available in social media networks including facebook which enhance
sharing and liking Proceedings of posts which in turn spreads falsified information. Lot of
work has been done to detect falsified information.(Lohitha et al., 2023)

6
2.0 INTRODUCTION
HISTORY OF IOT

THEORITICAL FRAMEWORK

MACHINE LEARNING

MACHINE LEARNING CLASSIFICATION

Applications Of Machine Learning

CASE STUDY