Hunting for troll comments in news community forums

Todor Mihaylov, Preslav Nakov

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

25 Citations (Scopus)

Abstract

There are different definitions of what a troll is. Certainly, a troll can be somebody who teases people to make them angry, or somebody who offends people, or somebody who wants to dominate any single discussion, or somebody who tries to manipulate people's opinion (sometimes for money), etc. The last definition is the one that dominates the public discourse in Bulgaria and Eastern Europe, and this is our focus in this paper. In our work, we examine two types of opinion manipulation trolls: paid trolls that have been revealed from leaked "reputation management contracts" and "mentioned trolls" that have been called such by several different people. We show that these definitions are sensible: we build two classifiers that can distinguish a post by such a paid troll from one by a non-troll with 81-82% accuracy; the same classifier achieves 81-82% accuracy on so called mentioned troll vs. non-troll posts.

Original languageEnglish
Title of host publication54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers
PublisherAssociation for Computational Linguistics (ACL)
Pages399-405
Number of pages7
ISBN (Electronic)9781510827592
Publication statusPublished - 2016
Event54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany
Duration: 7 Aug 201612 Aug 2016

Other

Other54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
CountryGermany
CityBerlin
Period7/8/1612/8/16

Fingerprint

Classifiers
news
community
Bulgaria
Eastern Europe
reputation
manipulation
money
Hunting
Classifier
News
discourse
management
Manipulation
Public Discourse

ASJC Scopus subject areas

  • Artificial Intelligence
  • Linguistics and Language
  • Software
  • Language and Linguistics

Cite this

Mihaylov, T., & Nakov, P. (2016). Hunting for troll comments in news community forums. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers (pp. 399-405). Association for Computational Linguistics (ACL).

Hunting for troll comments in news community forums. / Mihaylov, Todor; Nakov, Preslav.

54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. p. 399-405.

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

Mihaylov, T & Nakov, P 2016, Hunting for troll comments in news community forums. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), pp. 399-405, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7/8/16.
Mihaylov T, Nakov P. Hunting for troll comments in news community forums. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL). 2016. p. 399-405
Mihaylov, Todor ; Nakov, Preslav. / Hunting for troll comments in news community forums. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers. Association for Computational Linguistics (ACL), 2016. pp. 399-405
@inproceedings{20e7c385eecc4f798b50cf878296c5a0,
title = "Hunting for troll comments in news community forums",
abstract = "There are different definitions of what a troll is. Certainly, a troll can be somebody who teases people to make them angry, or somebody who offends people, or somebody who wants to dominate any single discussion, or somebody who tries to manipulate people's opinion (sometimes for money), etc. The last definition is the one that dominates the public discourse in Bulgaria and Eastern Europe, and this is our focus in this paper. In our work, we examine two types of opinion manipulation trolls: paid trolls that have been revealed from leaked {"}reputation management contracts{"} and {"}mentioned trolls{"} that have been called such by several different people. We show that these definitions are sensible: we build two classifiers that can distinguish a post by such a paid troll from one by a non-troll with 81-82{\%} accuracy; the same classifier achieves 81-82{\%} accuracy on so called mentioned troll vs. non-troll posts.",
author = "Todor Mihaylov and Preslav Nakov",
year = "2016",
language = "English",
pages = "399--405",
booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Hunting for troll comments in news community forums

AU - Mihaylov, Todor

AU - Nakov, Preslav

PY - 2016

Y1 - 2016

N2 - There are different definitions of what a troll is. Certainly, a troll can be somebody who teases people to make them angry, or somebody who offends people, or somebody who wants to dominate any single discussion, or somebody who tries to manipulate people's opinion (sometimes for money), etc. The last definition is the one that dominates the public discourse in Bulgaria and Eastern Europe, and this is our focus in this paper. In our work, we examine two types of opinion manipulation trolls: paid trolls that have been revealed from leaked "reputation management contracts" and "mentioned trolls" that have been called such by several different people. We show that these definitions are sensible: we build two classifiers that can distinguish a post by such a paid troll from one by a non-troll with 81-82% accuracy; the same classifier achieves 81-82% accuracy on so called mentioned troll vs. non-troll posts.

AB - There are different definitions of what a troll is. Certainly, a troll can be somebody who teases people to make them angry, or somebody who offends people, or somebody who wants to dominate any single discussion, or somebody who tries to manipulate people's opinion (sometimes for money), etc. The last definition is the one that dominates the public discourse in Bulgaria and Eastern Europe, and this is our focus in this paper. In our work, we examine two types of opinion manipulation trolls: paid trolls that have been revealed from leaked "reputation management contracts" and "mentioned trolls" that have been called such by several different people. We show that these definitions are sensible: we build two classifiers that can distinguish a post by such a paid troll from one by a non-troll with 81-82% accuracy; the same classifier achieves 81-82% accuracy on so called mentioned troll vs. non-troll posts.

UR - http://www.scopus.com/inward/record.url?scp=84986229052&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84986229052&partnerID=8YFLogxK

M3 - Conference contribution

SP - 399

EP - 405

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Short Papers

PB - Association for Computational Linguistics (ACL)

ER -