Exposing paid opinion manipulation trolls

Todor Mihaylov, Ivan Koychev, Georgi D. Georgiev, Preslav Nakov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Recently, Web forums have been invaded by opinion manipulation trolls. Some trolls try to influence the other users driven by their own convictions, while in other cases they can be organized and paid, e.g., by a political party or a PR agency that gives them specific instructions what to write. Finding paid trolls automatically using machine learning is a hard task, as there is no enough training data to train a classifier; yet some test data is possible to obtain, as these trolls are sometimes caught and widely exposed. In this paper, we solve the training data problem by assuming that a user who is called a troll by several different people is likely to be such, and one who has never been called a troll is unlikely to be such. We compare the profiles of (i) paid trolls vs. (ii) "mentioned" trolls vs. (iii) non-trolls, and we further show that a classifier trained to distinguish (ii) from (iii) does quite well also at telling apart (i) from (iii).

Original languageEnglish
Title of host publicationInternational Conference Recent Advances in Natural Language Processing, RANLP
PublisherAssociation for Computational Linguistics (ACL)
Pages443-450
Number of pages8
Volume2015-January
Publication statusPublished - 2015
Event10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 - Hissar, Bulgaria
Duration: 7 Sep 20159 Sep 2015

Other

Other10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015
CountryBulgaria
CityHissar
Period7/9/159/9/15

Fingerprint

Classifiers
Learning systems

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications
  • Software
  • Electrical and Electronic Engineering

Cite this

Mihaylov, T., Koychev, I., Georgiev, G. D., & Nakov, P. (2015). Exposing paid opinion manipulation trolls. In International Conference Recent Advances in Natural Language Processing, RANLP (Vol. 2015-January, pp. 443-450). Association for Computational Linguistics (ACL).

Exposing paid opinion manipulation trolls. / Mihaylov, Todor; Koychev, Ivan; Georgiev, Georgi D.; Nakov, Preslav.

International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. p. 443-450.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mihaylov, T, Koychev, I, Georgiev, GD & Nakov, P 2015, Exposing paid opinion manipulation trolls. in International Conference Recent Advances in Natural Language Processing, RANLP. vol. 2015-January, Association for Computational Linguistics (ACL), pp. 443-450, 10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015, Hissar, Bulgaria, 7/9/15.
Mihaylov T, Koychev I, Georgiev GD, Nakov P. Exposing paid opinion manipulation trolls. In International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January. Association for Computational Linguistics (ACL). 2015. p. 443-450
Mihaylov, Todor ; Koychev, Ivan ; Georgiev, Georgi D. ; Nakov, Preslav. / Exposing paid opinion manipulation trolls. International Conference Recent Advances in Natural Language Processing, RANLP. Vol. 2015-January Association for Computational Linguistics (ACL), 2015. pp. 443-450
@inproceedings{73a2feb6b80c414c977ef7c3939dc439,
title = "Exposing paid opinion manipulation trolls",
abstract = "Recently, Web forums have been invaded by opinion manipulation trolls. Some trolls try to influence the other users driven by their own convictions, while in other cases they can be organized and paid, e.g., by a political party or a PR agency that gives them specific instructions what to write. Finding paid trolls automatically using machine learning is a hard task, as there is no enough training data to train a classifier; yet some test data is possible to obtain, as these trolls are sometimes caught and widely exposed. In this paper, we solve the training data problem by assuming that a user who is called a troll by several different people is likely to be such, and one who has never been called a troll is unlikely to be such. We compare the profiles of (i) paid trolls vs. (ii) {"}mentioned{"} trolls vs. (iii) non-trolls, and we further show that a classifier trained to distinguish (ii) from (iii) does quite well also at telling apart (i) from (iii).",
author = "Todor Mihaylov and Ivan Koychev and Georgiev, {Georgi D.} and Preslav Nakov",
year = "2015",
language = "English",
volume = "2015-January",
pages = "443--450",
booktitle = "International Conference Recent Advances in Natural Language Processing, RANLP",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Exposing paid opinion manipulation trolls

AU - Mihaylov, Todor

AU - Koychev, Ivan

AU - Georgiev, Georgi D.

AU - Nakov, Preslav

PY - 2015

Y1 - 2015

N2 - Recently, Web forums have been invaded by opinion manipulation trolls. Some trolls try to influence the other users driven by their own convictions, while in other cases they can be organized and paid, e.g., by a political party or a PR agency that gives them specific instructions what to write. Finding paid trolls automatically using machine learning is a hard task, as there is no enough training data to train a classifier; yet some test data is possible to obtain, as these trolls are sometimes caught and widely exposed. In this paper, we solve the training data problem by assuming that a user who is called a troll by several different people is likely to be such, and one who has never been called a troll is unlikely to be such. We compare the profiles of (i) paid trolls vs. (ii) "mentioned" trolls vs. (iii) non-trolls, and we further show that a classifier trained to distinguish (ii) from (iii) does quite well also at telling apart (i) from (iii).

AB - Recently, Web forums have been invaded by opinion manipulation trolls. Some trolls try to influence the other users driven by their own convictions, while in other cases they can be organized and paid, e.g., by a political party or a PR agency that gives them specific instructions what to write. Finding paid trolls automatically using machine learning is a hard task, as there is no enough training data to train a classifier; yet some test data is possible to obtain, as these trolls are sometimes caught and widely exposed. In this paper, we solve the training data problem by assuming that a user who is called a troll by several different people is likely to be such, and one who has never been called a troll is unlikely to be such. We compare the profiles of (i) paid trolls vs. (ii) "mentioned" trolls vs. (iii) non-trolls, and we further show that a classifier trained to distinguish (ii) from (iii) does quite well also at telling apart (i) from (iii).

UR - http://www.scopus.com/inward/record.url?scp=84949769559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84949769559&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2015-January

SP - 443

EP - 450

BT - International Conference Recent Advances in Natural Language Processing, RANLP

PB - Association for Computational Linguistics (ACL)

ER -