Threat Detector for Social Media Using Text Analysis

Sadi, Saidul Haq and Hossain Pk, Md Rubel and Zeki, Akram M. (2021) Threat Detector for Social Media Using Text Analysis. International Journal on Perceptive and Cognitive Computing (IJPCC), 7 (1). pp. 113-117. E-ISSN 2462-229X

PDF - Published Version Restricted to Registered users only Download (482kB) | Request a copy

Abstract

The scam is one of the most important security threats among social media users. It is required to detect scams not only to protect social user's data that is stored online but also to secure the social network. Besides, machine learning techniques are becoming more popular in the text analysis sector. To fraud detection, the most used supervised machine learning techniques are Naïve Bayes (NB) and Support vector machine (SVM). In this project, a machine learning model is developed for detecting threats from Twitter tweets. Accordingly, the Naïve Bayes classifier and flask micro web framework were used to build the model by using the python programming language. The model provided 91% accuracy in detecting tweet scam threats. This finding will benefit the social network users to be aware of threats as well as social media network providers to enhance their security system.

Item Type:	Article (Journal)
Uncontrolled Keywords:	threat detector social media Twitter supervised machine learning Naïve Bayes classifier
Subjects:	Q Science > QA Mathematics > QA76 Computer software
Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button):	Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System
Depositing User:	Akram M Zeki
Date Deposited:	04 Mar 2022 08:04
Last Modified:	04 Mar 2022 08:04
URI:	http://irep.iium.edu.my/id/eprint/97026

Actions (login required)

View Item