Predicting attackers of online shaming using ant colony optimization / Noor Shafiqa Fazlien Mohamad Fauzi

Mohamad Fauzi, Noor Shafiqa Fazlien (2020) Predicting attackers of online shaming using ant colony optimization / Noor Shafiqa Fazlien Mohamad Fauzi. Degree thesis, Universiti Teknologi Mara Perlis.

Download

[thumbnail of 34831.pdf] Text
34831.pdf

Download (89kB)

Abstract

Online shaming is an act which involves persecution by the internet. It is a vigilante activity which is carried out through social media on the internet. Online shaming involves the action of attackers which publicly embarrasses the victim by sharing some personal information of the victim. Then, the attackers are usually involved in sharing something to embarrass the victim publicly by using social media. This is because the social media platform makes it easier to share something and it is easier to share the photo that can shame others in the real world. The main objective of this study is to develop a class model for predicting the attackers of online shaming. This study implemented Ant Colony Optimization Algorithm to develop classification rules for predicting the attackers of online shaming. In order to predict the attackers of online shaming, Ant Colony Optimization Algorithm will be used and it will be compared with J48 algorithm. The accuracy of model for J48 is 66.88% while accuracy of Ant-Miner is 69.69%. The results have shown that the Ant Colony Optimization Algorithm produced a better predictive accuracy. Therefore, it is submitted that the Ant Colony Optimization Algorithm produces the most accurate result in predicting the attackers of online shaming. This study also shows that Ant Colony Optimization is a suitable technique in developing the classification model. Besides, the Ant-Miner algorithm is suitable in this study because it can train the data for many times to obtain the highest percentage of accuracy for developing the classification model to predict the attackers of online shaming. The Ant Miner system plays an important role in running the Ant Colony Optimization Algorithm and making comparison in this case study.

Metadata

Item Type: Thesis (Degree)
Creators:
Creators
Email
Mohamad Fauzi, Noor Shafiqa Fazlien
2016535243
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science > Algorithms
Divisions: Universiti Teknologi MARA, Perlis > Arau Campus > Faculty of Computer and Mathematical Sciences
Programme: Bachelor of Science (Hons) Management Mathematics
Item ID: 34831
Uncontrolled Keywords: Predicting Attackers ; Online Shaming ; Ant Colony Optimization Algorithm ; Classification Rules
URI: https://ir.uitm.edu.my/id/eprint/34831

Fulltext

Fulltext is available at:
  • Bilik Koleksi Akses Terhad | Kampus Arau, Perlis
  • ID Number

    34831

    Indexing


    View in Google Scholar

    Edit Item
    Edit Item