Bimonthly    Since 1986
ISSN 1004-9037
Publication Details
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
 
   
      09 May 2023, Volume 38 Issue 3
    Article

    TWITTER BOT DETECTION USING MACHINE LEARNING ALGORITHMS
    P. Sai Karthik Reddy and P. Sai Nath and Dr. J. Vijayashree*
    Journal of Data Acquisition and Processing, 2023, 38 (3): 138-146 . 

    Abstract

    A staggering number of individuals use social media platforms nowadays, which encompass a wide range of media. It is estimated that Twitter has 330 million monthly active users. Twitter is a social networking site where users may express their ideas and opinions on a variety of situations happening around the world, it may share information about the economy, stocks, important information about business, politics etc. With millions of users actively using it, it is one of the most widely used social networking sites worldwide. It is one of the fastest methods of information transfer. Can be said as one of the quickest ways to deliver information. A Twitter account that has been programmed to carry out social media tasks automatically by scheduling tweets is known as a Twitter bot. This found that a growing number of problematic bot accounts are disinformation, comedy, and promote unverified material, which can negatively affect several concerns. It may alter user confidence, public perceptions of a problem, or even the social order. Thus, it is mandatory to know that tweets are made by real humans or bots. For the implementation of our project, we have used different machine learning algorithms like KNN, Gaussian Naïve Bayes, Decision Tree Classifier, Random Forest. We will be training the dataset with these algorithms. As a result, we concluded Random Forest is the best algorithm which has highest accuracy among all the others. Random Forest machine learning technique is ultimately chosen because it can avoid most overfitting and produce a generalized model that can be used accurately right after training. The flask server was utilized to connect our model to the web content. Our analysis of our framework's results shows that we can reasonably determine if a user is a person or a bot.

    Keyword

    Bot detection, Decision Tree Classifier, Gaussian Naïve Baye, KNN, Random Forest, Twitter Bot.


    PDF Download (click here)

SCImago Journal & Country Rank

ISSN 1004-9037

         

Home
Editorial Board
Author Guidelines
Subscription
Journal of Data Acquisition and Processing
Institute of Computing Technology, Chinese Academy of Sciences
P.O. Box 2704, Beijing 100190 P.R. China
E-mail: info@sjcjycl.cn
 
  Copyright ©2015 JCST, All Rights Reserved