Deception detection in Twitter

Jalal S. Alowibdi, Ugo A. Buy, Philip S. Yu, Sohaib Ghani, Mohamed Mokbel

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user’s privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, and spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.

Original languageEnglish
Article number32
Pages (from-to)1-16
Number of pages16
JournalSocial Network Analysis and Mining
Volume5
Issue number1
DOIs
Publication statusPublished - 1 Jan 2015
Externally publishedYes

Fingerprint

twitter
Color
social network
Clustering algorithms
gender
layout
privacy

Keywords

  • Deception detection
  • Gender classification
  • Location classification
  • Profile characteristics
  • Profile classification
  • Profile indicators
  • Twitter

ASJC Scopus subject areas

  • Information Systems
  • Communication
  • Media Technology
  • Human-Computer Interaction
  • Computer Science Applications

Cite this

Alowibdi, J. S., Buy, U. A., Yu, P. S., Ghani, S., & Mokbel, M. (2015). Deception detection in Twitter. Social Network Analysis and Mining, 5(1), 1-16. [32]. https://doi.org/10.1007/s13278-015-0273-1

Deception detection in Twitter. / Alowibdi, Jalal S.; Buy, Ugo A.; Yu, Philip S.; Ghani, Sohaib; Mokbel, Mohamed.

In: Social Network Analysis and Mining, Vol. 5, No. 1, 32, 01.01.2015, p. 1-16.

Research output: Contribution to journalArticle

Alowibdi, JS, Buy, UA, Yu, PS, Ghani, S & Mokbel, M 2015, 'Deception detection in Twitter', Social Network Analysis and Mining, vol. 5, no. 1, 32, pp. 1-16. https://doi.org/10.1007/s13278-015-0273-1
Alowibdi, Jalal S. ; Buy, Ugo A. ; Yu, Philip S. ; Ghani, Sohaib ; Mokbel, Mohamed. / Deception detection in Twitter. In: Social Network Analysis and Mining. 2015 ; Vol. 5, No. 1. pp. 1-16.
@article{326111972d994633a51be30ec25c29fd,
title = "Deception detection in Twitter",
abstract = "Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user’s privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, and spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.",
keywords = "Deception detection, Gender classification, Location classification, Profile characteristics, Profile classification, Profile indicators, Twitter",
author = "Alowibdi, {Jalal S.} and Buy, {Ugo A.} and Yu, {Philip S.} and Sohaib Ghani and Mohamed Mokbel",
year = "2015",
month = "1",
day = "1",
doi = "10.1007/s13278-015-0273-1",
language = "English",
volume = "5",
pages = "1--16",
journal = "Social Network Analysis and Mining",
issn = "1869-5450",
publisher = "Springer Wien",
number = "1",

}

TY - JOUR

T1 - Deception detection in Twitter

AU - Alowibdi, Jalal S.

AU - Buy, Ugo A.

AU - Yu, Philip S.

AU - Ghani, Sohaib

AU - Mokbel, Mohamed

PY - 2015/1/1

Y1 - 2015/1/1

N2 - Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user’s privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, and spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.

AB - Online Social Networks (OSNs) play a significant role in the daily life of hundreds of millions of people. However, many user profiles in OSNs contain deceptive information. Existing studies have shown that lying in OSNs is quite widespread, often for protecting a user’s privacy. In this paper, we propose a novel approach for detecting deceptive profiles in OSNs. We specifically define a set of analysis methods for detecting deceptive information about user genders and locations in Twitter. First, we collected a large dataset of Twitter profiles and tweets. Next, we defined methods for gender guessing from Twitter profile colors and names. Subsequently, we apply Bayesian classification and K-means clustering algorithms to Twitter profile characteristics (e.g., profile layout colors, first names, user names, and spatiotemporal information) and geolocations to analyze the user behavior. We establish the overall accuracy of each indicator through extensive experimentation with our crawled dataset. Based on the outcomes of our approach, we are able to detect deceptive profiles about gender and location with a reasonable accuracy.

KW - Deception detection

KW - Gender classification

KW - Location classification

KW - Profile characteristics

KW - Profile classification

KW - Profile indicators

KW - Twitter

UR - http://www.scopus.com/inward/record.url?scp=84947287167&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947287167&partnerID=8YFLogxK

U2 - 10.1007/s13278-015-0273-1

DO - 10.1007/s13278-015-0273-1

M3 - Article

VL - 5

SP - 1

EP - 16

JO - Social Network Analysis and Mining

JF - Social Network Analysis and Mining

SN - 1869-5450

IS - 1

M1 - 32

ER -