Cyber bullying detection

1. 1
CYBERBULLYING DETECTION
Submitted to the Mahatma Gandhi University in partial
Fullfillment of the requirement for the Degree of
BCA
CBCS BCA Degree Programme
Submitted by
ARJUN K VINOD
Reg No: 200021094304
Under the guidance of
Mr. AZHAR BIN SAGAR
Assistant Professor
Department of ComputerApplication Musaliar
College of Arts and Science,Pathanamthitta
(Affiliated to MG University, Kottayam)

2. 2
MUSALIAR COLLEGE OFARTS AND SCIENCE
PATHANAMTHITTA
(Affiliated to MG University, Kottayam)
CERTIFICATE
This is to certify that the seminar entitled “CYBERBULLYING DETECTION” is a
bonafide record of work done by ARJUN K VINOD (Reg.No:200021094304) for the
partial fulfillment of the requirements for the award of the Degree of Bachelor of
Computer Application of Mahatma Gandhi University, Kottayam.
Prof. Dr. Vilzon Koshy Asst.Prof. Anju ElizabethCherian
(Principal) (Vice Principal)
Asst. Prof. Leena Natarajan Asst.Prof. Azhar Bin Sagar
(Head of the Department) (Faculty Guide)
Internal Examiner External Examiner

3. 3
DECLARATION
I hereby declare that this seminar report “CYBERBULLYING DETECTION” is a
bonafide work done at Musaliar College of Arts & Science, Pathanamthitta,
towards the partial fulfillment of the requirements for the award of Degree of Bachelor
of Computer Application from Mahatma Gandhi University, Kottayam during the
academic year 2018-2021.
Place: Pathanamthitta ARJUN K VINOD
Date: Reg No: 200021094304

4. 4
ACKNOWLEDGEMENT
During the course of the present study, I received help and inspiration from
many individuals and sources. I wish to express my deep sense of gratitude to all those
who contributed directly or indirectly to complete my seminar work.
I am greatly indebted to our Principal Prof. Dr.Vilzon Koshy for providing all
the required facilities for completing the seminar work.
I take this opportunity to express my heartfelt thanks and gratitude to our Vice
Principal Mrs. Anju Elizabeth Cherian for the valuable support and guidance.
My sincere thanks to Asst. Prof. Leena Natarajan Head of the Department
whose remarkable ideas and supervision made me to do Completing This Seminar
successful1.
I am thankful to my guide Asst. Prof Azhar Bin Sagar for the keen interest
and continuous encouragement, which had inspired us throughout the study.
I express my sincere thanks to all faculty members, friends, library facilities
provided and well-wishers for their cooperation in completing this seminar.
Above all I thank God “the almighty” for the benevolence he has shown to us
for the successful completion of this project.
Place: Pathanamthitta ARJUN K VINOD

5. 5
ABSTRACT
As a side effect of increasingly popular social media, cyberbullying has
emerged as a serious problem afflicting children, adolescents and young
adults. Machine learning techniques make automatic detection of bullying
messages in social media possible and this could help to construct a healthy
and safe social media environment. In this meaningful research area, one
critical issue is robust and discriminative numerical representation learning
of text messages.
Our method named Semantic-Enhanced Marginalized Denoising Auto
Encoder (smSDA) is developed via semantic extension of the popular deep
learning model stacked denoising auto encoder. The semantic extension
consists of semantic dropout noise and sparsity constraints, where the
semantic dropout noise is designed based on domain knowledge and the
word embedding technique . Our proposed method can exploit the hidden
feature structure of bullying information and learn a robust and
discriminative representation of text.

6. 6
TABLE OF CONTENTS PAGE NO:
1.INTRODUCTION 7
2.BACKGROUND 8
3.FLOW DIAGRAM OF APPLICATION 9
4.CONCLUSION 11
5.REFERENCES 12

7. 7
1. INTRODUCTION
Social media may have some side effects such as cyberbullying, which may
have negative impacts on the life of people, especially children and teenagers.
The objective of this project is to develop a social media network like Facebook
with some functionalities and demonstrate how cyberbullying can be prevented
on social media.
Most of us would agree that any form of bullying is unacceptable. However,
the same ‘us’ again, at some point in our lives, may have been a victim of
bullying or may have bullied others. For the victims, some are able to move on
and live normal lives whilst others are less fortunate. Some of them carry life-
long scars from the trauma, damaging their self-worth, confidence and
happiness, and, in the worst cases, some of them would resort to suicide due to
the weight of the bullying and the foreboding pain. The perpetrators I assume
would carry on with their lives regardless
Due to its anonymous nature also, it is hard to detect this form of bullying
and policing it is almost impossible. Cyberbullying victims are usually told to
simply turn off the computer and ignore the bullies but this rarely works
unless one shuts down all communication in social media. On the part of the
perpetrator, the act of cyberbullying, due to its detached nature, pretty much
encourages a lack of empathy towards the victim. In contrast to traditional
bullying, the cyber bully would not be there in person as the victim is hurt or
damaged by the cyberbullying, leaving less room for feeling sorry for the
victim or acknowledgement that it could have gone too far. Additionally, the
anonymous nature of cyberbullying also encourages the cyberbully to be
brazen and ruthless in their acts as it can be tremendously difficult to identify
the cyberbully, making it very easy for them to cyberbully someone time and
time again while also not seeing any true consequence to their actions.

8. 8
2.BACKGROUND
Using various social media applications, people can experience
convenient communication and enjoy enormous information. However,
social media may have some side effects such as cyberbullying, which may
have negative impacts on the life of people, especially children and
teenagers. Cyberbullying is the use of technology like the internet, email, cell
phones, social media or pictures to harass, threaten, embarrass, or target a
person. Usually, it occurs among young people. But when an adult is
involved, it may mean cyber harassment or cyber stalking, a crime that can
have legal consequences and include imprisonment.
It includes
• Sending inappropriate text messages.
• Posting statements online that are vulgar or unacceptable.
• Sending or posting pictures that are not permitted by you.
• Making negative comments.
• Blackmailing with certain demands.
• Stalking and use of intimidation.
• Threats of violence or death.
• Sexually explicit photos or descriptions, which is considered
pornography.
• Secretly-recorded photos or videos that were taken without the subject’s
knowledge.

9. 9
3.FLOW DIAGRAM OF APPLICATION
1.For a general user
The details of the workflows are as explained above.
1) The user logs on to the web portal.
2) The user selects the menu to view a profile and sends a friend request
3) After friend request is approved, photos and messages can be shared.
4) When sharing private and public message and posting on the wall, check
for bullying words.

10. 10
2.For an admin
The details of the workflows are as explained below.
1) The admin logs on to the web portal.
2) The admin selects the menu and finds abnormal user
3) The admin can block bullying post

11. 11
4.CONCLUSION
The proposed OSN Cyberbullying system is designed to prevent Cyberbullying in
Social media space. By designing semantic dropout noise and enforcing sparsity,
we have developed semantic-enhanced marginalized denoising autoencoder as a
specialized representation learning model for cyberbullying detection. Also, the
design is verified for the functional correctness, code and functional coverage
numbers are used for measuring the verification activity

12. 12
5.REFERENCES
[1] Y. Bengio, A. Courville, and P. Vincent, “Representation
learning: A review and new perspectives,” Pattern Analysis and
Machine Intelligence, IEEE Transactions on, vol. 35, no. 8, pp.
1798–1828, 2013.
[2] A. M. Kaplan and M. Haenlein, “Users of the world, unite!
The challenges and opportunities of social media,” Business
horizons, vol. 53, no. 1, pp. 59–68, 2010.
[3] R. M. Kowalski, G. W. Giumetti, A. N. Schroeder, and M.
R.Lattanner, “Bullying in the digital age: A critical review and
metaanalysis of cyberbullying research among youth.” 2014.
[4] B. K. Biggs, J. M. Nelson, and M. L. Sampilo, “Peer relations
in the anxiety–depression link: Test of a mediation model,”
Anxiety, Stress, & Coping, vol. 23, no. 4, pp. 431–447, 2010.

13. 13