Syntactic stylometry for deception detection

Song Feng; Ritwik Banerjee; Yejin Choi

Syntactic stylometry for deception detection

Song Feng
, Ritwik Banerjee
, Yejin Choi

Computer Science

Stony Brook University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

486 Scopus citations

Abstract

Most previous studies in computerized deception detection have relied only on shallow lexico-syntactic patterns. This paper investigates syntactic stylometry for deception detection, adding a somewhat unconventional angle to prior literature. Over four different datasets spanning from the product review to the essay domain, we demonstrate that features driven from Context Free Grammar (CFG) parse trees consistently improve the detection performance over several baselines that are based only on shallow lexico-syntactic features. Our results improve the best published result on the hotel review data (Ott et al., 2011) reaching 91.2% accuracy with 14% error reduction.

Original language	English
Title of host publication	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages	171-175
Number of pages	5
State	Published - 2012
Event	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of Duration: Jul 8 2012 → Jul 14 2012

Publication series

Name	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Volume	2

Conference

Conference	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Country/Territory	Korea, Republic of
City	Jeju Island
Period	07/8/12 → 07/14/12

Cite this

@inproceedings{3141dc8f8c3c488981a91bd762f341c9,

title = "Syntactic stylometry for deception detection",

abstract = "Most previous studies in computerized deception detection have relied only on shallow lexico-syntactic patterns. This paper investigates syntactic stylometry for deception detection, adding a somewhat unconventional angle to prior literature. Over four different datasets spanning from the product review to the essay domain, we demonstrate that features driven from Context Free Grammar (CFG) parse trees consistently improve the detection performance over several baselines that are based only on shallow lexico-syntactic features. Our results improve the best published result on the hotel review data (Ott et al., 2011) reaching 91.2\% accuracy with 14\% error reduction.",

author = "Song Feng and Ritwik Banerjee and Yejin Choi",

year = "2012",

language = "English",

isbn = "9781937284251",

series = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

pages = "171--175",

booktitle = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

note = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 ; Conference date: 08-07-2012 Through 14-07-2012",

}

Feng, S, Banerjee, R & Choi, Y 2012, Syntactic stylometry for deception detection. in 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference, vol. 2, pp. 171-175, 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012, Jeju Island, Korea, Republic of, 07/8/12.

Syntactic stylometry for deception detection. / Feng, Song; Banerjee, Ritwik; Choi, Yejin.
50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. 2012. p. 171-175 (50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference; Vol. 2).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Syntactic stylometry for deception detection

AU - Feng, Song

AU - Banerjee, Ritwik

AU - Choi, Yejin

PY - 2012

Y1 - 2012

N2 - Most previous studies in computerized deception detection have relied only on shallow lexico-syntactic patterns. This paper investigates syntactic stylometry for deception detection, adding a somewhat unconventional angle to prior literature. Over four different datasets spanning from the product review to the essay domain, we demonstrate that features driven from Context Free Grammar (CFG) parse trees consistently improve the detection performance over several baselines that are based only on shallow lexico-syntactic features. Our results improve the best published result on the hotel review data (Ott et al., 2011) reaching 91.2% accuracy with 14% error reduction.

AB - Most previous studies in computerized deception detection have relied only on shallow lexico-syntactic patterns. This paper investigates syntactic stylometry for deception detection, adding a somewhat unconventional angle to prior literature. Over four different datasets spanning from the product review to the essay domain, we demonstrate that features driven from Context Free Grammar (CFG) parse trees consistently improve the detection performance over several baselines that are based only on shallow lexico-syntactic features. Our results improve the best published result on the hotel review data (Ott et al., 2011) reaching 91.2% accuracy with 14% error reduction.

UR - https://www.scopus.com/pages/publications/84878196060

M3 - Conference contribution

AN - SCOPUS:84878196060

SN - 9781937284251

T3 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

SP - 171

EP - 175

BT - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

T2 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

Y2 - 8 July 2012 through 14 July 2012

ER -

Syntactic stylometry for deception detection

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this