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 language | English |
---|---|
Title of host publication | International Conference Recent Advances in Natural Language Processing, RANLP |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 443-450 |
Number of pages | 8 |
Volume | 2015-January |
Publication status | Published - 2015 |
Event | 10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 - Hissar, Bulgaria Duration: 7 Sep 2015 → 9 Sep 2015 |
Other
Other | 10th International Conference on Recent Advances in Natural Language Processing, RANLP 2015 |
---|---|
Country | Bulgaria |
City | Hissar |
Period | 7/9/15 → 9/9/15 |
Fingerprint
ASJC Scopus subject areas
- Artificial Intelligence
- Computer Science Applications
- Software
- Electrical and Electronic Engineering
Cite this
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 proceeding › Conference contribution
}
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
AN - SCOPUS:84949769559
VL - 2015-January
SP - 443
EP - 450
BT - International Conference Recent Advances in Natural Language Processing, RANLP
PB - Association for Computational Linguistics (ACL)
ER -