Open Access Journal

ISSN : 2394-2320 (Online)

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

Open Access Journal

International Journal of Engineering Research in Computer Science and Engineering (IJERCSE)

Monthly Journal for Computer Science and Engineering

ISSN : 2394-2320 (Online)

Malicious tweet detection and disaster reporting using topic and user behavior analysis

Author : Dhanashri R.Deosarkar 1 Sandeep Gore 2

Date of Publication :21st March 2018

Abstract: The social networking sites received much more attention recently in that tweeter is used more than others. In tweeter micro blogging services received more attention. Micro blogging is used to blog the words which are related to that topic, that depend on three behavioral factors which are t user virality, topic virality and user susceptibility. In proposed system Malicious tweets identifies using traffic patterns in that this system uses click traffic analysis method and for the malicious URL uses the URL shortening websites to identifies blacklisted URLs. The URL shorteners are used to sharing URLs on Twitter, because tweeter having 140 character tweet limit per message. Spammers uses the URL shorteners to improve the user quality of their spam URLs. Our proposed system provides integrated approach for the spam detection from different tweets. The integrated approach includes the different machine learning techniques, spam URL detection and NLP. Firstly this system identifies the sensitivity of tweet depend on the topic varality or user virality after that micro blogging is used to calculate the tensor factor which means tensor factor is used to calculate the user impact on that tweet. Last module is disaster event reporting in this if the event like earth quick is occurred then it sends the mail or message to the people witch are present in that area.

Reference :

    1. Sagar Gharge, Manik Chavan “An Integrated approach for Malicious Tweets detection using NLP” 978-1-5090- 5297-4/17 2017 IEEE.
    2. Ee-Peng Lim, Tuan-Anh Hoang “Microblogging Content Propagation Modeling Using Topic-Specific behavioral Factors” in ieee transactions, vol. 28, no. 9, september 2016
    3. Danesh Irani, De Wang, “Click Traffic Analysis of Short URL Spam on Twitter” conference on collaborative computer networking, application and worksharing 2013.
    4. Makoto Okazaki, Takeshi Sakaki, Yutaka Matsuo and Makoto Okazaki, “Tweet Analysis for Real-Time Event Detection and Earthquake Reporting System Development” 1041-4347/13 _ 2013 IEEE Published by the IEEE Computer Society.
    5. Diotra Henriyan, Mochamad Vicky Ghani Aziz , Rifki Wijaya and Ary Setijadi Prihatmanto, “Design and Implementation of Natural Language Processing with Syntax and emantic Analysis for Extract Traffic Conditions from Social Media Data” 978-1-4673-6713- 4/15/$31.00 ©2015 IEEE
    6. Chao Chen, Jun Zhang, Yi Xie, Yang Xiang Wanlei Zhou “A Performance Evaluation of Machine LearningBased Streaming Spam Tweets Detection” 2329- 924X © 2016 IEEE
    7. Kamalanathan Kandasamy and Preethi, “An Integrated Approach to Spam Classification on Twitter Using URL Analysis, Natural Language Processing and Machine Learning Techniques” 978-1-4799-2526- 1/14/$31.00 ©2014 IEEE
    8. Zi Chu, Steven Gianvecchio, Haining Wang, Sushil Jajodia “Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?” 1545-5971/12/$31.00 _ 2012 IEEE Published by the IEEE Computer Society
    9. William Deitrick, Brian Dickinson , Wei Hu, Alex Hai Wang and Zachary Miller, “Twitter spammer detection using data stream clustering” 2013 Published by Elsevier Inc.
    10. Juan Martinez-Romo , Lourdes Araujo “Detecting malicious tweets in trending topics using a statistical analysis of language” 0957-4174/$ - see front matter _ 2012 Elsevier Ltd. All rights reserved.

Recent Article