Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?

NANO SCIENTIFIC RESEARCH CENTRE PVT.LTD.,  AMEERPET, HYD

WWW.NSRCNANO.COM, 09640648777, 09652926926

JAVA PROJECTS LIST--2013

JAVA 2013 IEEE PAPERS

Detecting Automation of Twitter Accounts: Are You a Human, Bot, or Cyborg?

Abstract

            Twitter is a new web application playing dual roles of online social networking and microblogging. Users communicate with each other by publishing text-based posts. The popularity and open structure of Twitter have attracted a large number of automated programs, known as bots, which appear to be a double-edged sword to Twitter. Legitimate bots generate a large amount of benign tweets delivering news and updating feeds, while malicious bots spread spam or malicious contents. More interestingly, in the middle between human and bot, there has emerged cyborg referred to either bot-assisted human or human-assisted bot. To assist human users in identifying who they are interacting with, this paper focuses on the classification of human, bot, and cyborg accounts on Twitter. We first conduct a set of large-scale measurements with a collection of over 500,000 accounts. We observe the difference among human, bot, and cyborg in terms of tweeting behavior, tweet content, and account properties. Based on the measurement results, we propose a classification system that includes the following four parts: 1) an entropy-based component, 2) a spam detection component, 3) an account properties component, and 4) a decision maker. It uses the combination of features extracted from an unknown user to determine the likelihood of being a human, bot, or cyborg. Our experimental evaluation demonstrates the efficacy of the proposed classification system.

Existing System

            Several previous works focus on socio-technological aspects of Twitter such as its use in the workplace or during major disaster events. Twitter has attracted spammers to post spam content, due to its popularity and openness. Fighting against spam on Twitter has been investigated in recent works Yardi et al etected spam on Twitter. According to their observations, spammers send more messages than legitimate users, and are more likely to follow other spammers than legitimate users. Thus, a high follower-to following ratio is a sign of spamming behavior.

Proposed System

            In the paper, we first conduct a series of measurements to characterize the differences among human, bot, and cyborg in terms of tweeting behavior, tweet content, and account properties. By crawling Twitter, we collect over 500,000 users and more than 40 million tweets posted by them. Then, we perform a detailed data analysis, and find a set of useful features to classify users into the three classes. Based on the measurement results, we propose an automated classification system that consists of four major components:

1. The entropy component uses tweeting interval as a measure of behavior complexity, and detects the periodic and regular timing that is an indicator of automation;

2. The spam detection component uses tweet content to check whether text patterns contain spam or not3;

3. The account properties component employs useful account properties, such as tweeting device makeup, URL ration, to detect deviations from normal; and

4. The decision maker is based on Random Forest, and it uses the combination of the features generated by the above three components to categorize an unknown user as human, bot, or cyborg.

Hardware Requirements

·         Hard disk                    :           80 GB

·         RAM                           :           1 GB

·         Processor                     :           Pentium IV

Software Requirements

·         Coding Language       :           Java

·         Database                     :           MySQL

·         Operating System       :           Windows XP

Modules:

• Get Access Token
• Get Tweets
• Calculate Entropy Measure
• Find Source Type