The dark side of news community forums: opinion manipulation trolls

Todor Mihaylov, Tsvetomila Mihaylova, Preslav Nakov, Lluis Marques, Georgi D. Georgiev, Ivan Kolev Koychev

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

Purpose: The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Design/methodology/approach: The authors are aiming to build a classifier to distinguish trolls vs regular users. Unfortunately, it is not easy to get reliable training data. The authors solve this issue pragmatically: the authors assume that a user who is called a troll by several people is likely to be such, which are called accused trolls. Based on this assumption and on leaked reports about actual paid opinion manipulation trolls, the authors build a classifier to distinguish trolls vs regular users. Findings: The authors compare the profiles of paid trolls vs accused trolls vs non-trolls, and show that a classifier trained to distinguish accused trolls from non-trolls does quite well also at telling apart paid trolls from non-trolls. Research limitations/implications: The troll detection works even for users with about 10 comments, but it achieves the best performance for users with a sizable number of comments in the forum, e.g. 100 or more. Yet, there is not such a limitation for troll comment detection. Practical implications: The approach would help forum moderators in their work, by pointing them to the most suspicious users and comments. It would be also useful to investigative journalists who want to find paid opinion manipulation trolls. Social implications: The authors can offer a better experience to online users by filtering out opinion manipulation trolls and their comments. Originality/value: The authors propose a novel approach for finding paid opinion manipulation trolls and their posts.

Original languageEnglish
Pages (from-to)1292-1312
Number of pages21
JournalInternet Research
Volume28
Issue number5
DOIs
Publication statusPublished - 2 Oct 2018

Fingerprint

manipulation
Classifiers
news
accused
community
Moderators
News
Manipulation
moderator
journalist
credibility
proliferation
methodology
performance
Classifier
Values
experience

Keywords

  • Astroturfing
  • Community networks
  • Credibility
  • Sockpuppets
  • Trollness
  • Trolls

ASJC Scopus subject areas

  • Communication
  • Sociology and Political Science
  • Economics and Econometrics

Cite this

The dark side of news community forums : opinion manipulation trolls. / Mihaylov, Todor; Mihaylova, Tsvetomila; Nakov, Preslav; Marques, Lluis; Georgiev, Georgi D.; Koychev, Ivan Kolev.

In: Internet Research, Vol. 28, No. 5, 02.10.2018, p. 1292-1312.

Research output: Contribution to journalArticle

Mihaylov, Todor ; Mihaylova, Tsvetomila ; Nakov, Preslav ; Marques, Lluis ; Georgiev, Georgi D. ; Koychev, Ivan Kolev. / The dark side of news community forums : opinion manipulation trolls. In: Internet Research. 2018 ; Vol. 28, No. 5. pp. 1292-1312.
@article{c1ba89971c6445c2a7a381d028226690,
title = "The dark side of news community forums: opinion manipulation trolls",
abstract = "Purpose: The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Design/methodology/approach: The authors are aiming to build a classifier to distinguish trolls vs regular users. Unfortunately, it is not easy to get reliable training data. The authors solve this issue pragmatically: the authors assume that a user who is called a troll by several people is likely to be such, which are called accused trolls. Based on this assumption and on leaked reports about actual paid opinion manipulation trolls, the authors build a classifier to distinguish trolls vs regular users. Findings: The authors compare the profiles of paid trolls vs accused trolls vs non-trolls, and show that a classifier trained to distinguish accused trolls from non-trolls does quite well also at telling apart paid trolls from non-trolls. Research limitations/implications: The troll detection works even for users with about 10 comments, but it achieves the best performance for users with a sizable number of comments in the forum, e.g. 100 or more. Yet, there is not such a limitation for troll comment detection. Practical implications: The approach would help forum moderators in their work, by pointing them to the most suspicious users and comments. It would be also useful to investigative journalists who want to find paid opinion manipulation trolls. Social implications: The authors can offer a better experience to online users by filtering out opinion manipulation trolls and their comments. Originality/value: The authors propose a novel approach for finding paid opinion manipulation trolls and their posts.",
keywords = "Astroturfing, Community networks, Credibility, Sockpuppets, Trollness, Trolls",
author = "Todor Mihaylov and Tsvetomila Mihaylova and Preslav Nakov and Lluis Marques and Georgiev, {Georgi D.} and Koychev, {Ivan Kolev}",
year = "2018",
month = "10",
day = "2",
doi = "10.1108/IntR-03-2017-0118",
language = "English",
volume = "28",
pages = "1292--1312",
journal = "Internet Research",
issn = "1066-2243",
publisher = "Emerald Group Publishing Ltd.",
number = "5",

}

TY - JOUR

T1 - The dark side of news community forums

T2 - opinion manipulation trolls

AU - Mihaylov, Todor

AU - Mihaylova, Tsvetomila

AU - Nakov, Preslav

AU - Marques, Lluis

AU - Georgiev, Georgi D.

AU - Koychev, Ivan Kolev

PY - 2018/10/2

Y1 - 2018/10/2

N2 - Purpose: The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Design/methodology/approach: The authors are aiming to build a classifier to distinguish trolls vs regular users. Unfortunately, it is not easy to get reliable training data. The authors solve this issue pragmatically: the authors assume that a user who is called a troll by several people is likely to be such, which are called accused trolls. Based on this assumption and on leaked reports about actual paid opinion manipulation trolls, the authors build a classifier to distinguish trolls vs regular users. Findings: The authors compare the profiles of paid trolls vs accused trolls vs non-trolls, and show that a classifier trained to distinguish accused trolls from non-trolls does quite well also at telling apart paid trolls from non-trolls. Research limitations/implications: The troll detection works even for users with about 10 comments, but it achieves the best performance for users with a sizable number of comments in the forum, e.g. 100 or more. Yet, there is not such a limitation for troll comment detection. Practical implications: The approach would help forum moderators in their work, by pointing them to the most suspicious users and comments. It would be also useful to investigative journalists who want to find paid opinion manipulation trolls. Social implications: The authors can offer a better experience to online users by filtering out opinion manipulation trolls and their comments. Originality/value: The authors propose a novel approach for finding paid opinion manipulation trolls and their posts.

AB - Purpose: The purpose of this paper is to explore the dark side of news community forums: the proliferation of opinion manipulation trolls. In particular, it explores the idea that a user who is called a troll by several people is likely to be one. It further demonstrates the utility of this idea for detecting accused and paid opinion manipulation trolls and their comments as well as for predicting the credibility of comments in news community forums. Design/methodology/approach: The authors are aiming to build a classifier to distinguish trolls vs regular users. Unfortunately, it is not easy to get reliable training data. The authors solve this issue pragmatically: the authors assume that a user who is called a troll by several people is likely to be such, which are called accused trolls. Based on this assumption and on leaked reports about actual paid opinion manipulation trolls, the authors build a classifier to distinguish trolls vs regular users. Findings: The authors compare the profiles of paid trolls vs accused trolls vs non-trolls, and show that a classifier trained to distinguish accused trolls from non-trolls does quite well also at telling apart paid trolls from non-trolls. Research limitations/implications: The troll detection works even for users with about 10 comments, but it achieves the best performance for users with a sizable number of comments in the forum, e.g. 100 or more. Yet, there is not such a limitation for troll comment detection. Practical implications: The approach would help forum moderators in their work, by pointing them to the most suspicious users and comments. It would be also useful to investigative journalists who want to find paid opinion manipulation trolls. Social implications: The authors can offer a better experience to online users by filtering out opinion manipulation trolls and their comments. Originality/value: The authors propose a novel approach for finding paid opinion manipulation trolls and their posts.

KW - Astroturfing

KW - Community networks

KW - Credibility

KW - Sockpuppets

KW - Trollness

KW - Trolls

UR - http://www.scopus.com/inward/record.url?scp=85054141169&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054141169&partnerID=8YFLogxK

U2 - 10.1108/IntR-03-2017-0118

DO - 10.1108/IntR-03-2017-0118

M3 - Article

AN - SCOPUS:85054141169

VL - 28

SP - 1292

EP - 1312

JO - Internet Research

JF - Internet Research

SN - 1066-2243

IS - 5

ER -