Distinguishing Between True and False Stories Using Various Linguistic Features

Yaakov HaCohen-Kerner; Rakefet Dilmon; Shimon Friedlich; Daniel Nissim Cohen

Distinguishing Between True and False Stories Using Various Linguistic Features

Yaakov HaCohen-Kerner, Rakefet Dilmon, Shimon Friedlich, Daniel Nissim Cohen

Department of Hebrew and Semitic Languages

Jerusalem College of Technology

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

Abstract

This paper analyzes what linguistic features differentiate true and false stories written in Hebrew. To do so, we have defined four feature sets containing 145 features: POS-Tags, quantitative, repetition, and special expressions. The examined corpus contains stories that were composed by 48 native Hebrew speakers who were asked to tell both false and true stories. Classification experiments on all possible combinations of these four feature sets using five supervised machine learning methods have been applied. The Part of Speech (POS) set was superior to all others and has been found as a key component. The best accuracy result (89.6%) has been achieved by a combination of sixteen POS-Tags and one quantitative feature.

Original language	English
Title of host publication	Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation:
Subtitle of host publication	Posters
Editors	Hai Zhao
Place of Publication	Shanghai
Publisher	Pacific Asia Conference on Language,Information and Computation
Pages	176-186
Number of pages	11
State	Published - 2015

Access to Document

https://aclanthology.org/Y15-2021/

Cite this

HaCohen-Kerner, Y., Dilmon, R., Friedlich, S., & Cohen, D. N. (2015). Distinguishing Between True and False Stories Using Various Linguistic Features. In H. Zhao (Ed.), Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters (pp. 176-186). Pacific Asia Conference on Language,Information and Computation. https://aclanthology.org/Y15-2021/

@inbook{59795bce7fbd466994f55f4dd6085f36,

title = "Distinguishing Between True and False Stories Using Various Linguistic Features",

abstract = "This paper analyzes what linguistic features differentiate true and false stories written in Hebrew. To do so, we have defined four feature sets containing 145 features: POS-Tags, quantitative, repetition, and special expressions. The examined corpus contains stories that were composed by 48 native Hebrew speakers who were asked to tell both false and true stories. Classification experiments on all possible combinations of these four feature sets using five supervised machine learning methods have been applied. The Part of Speech (POS) set was superior to all others and has been found as a key component. The best accuracy result (89.6%) has been achieved by a combination of sixteen POS-Tags and one quantitative feature.",

author = "Yaakov HaCohen-Kerner and Rakefet Dilmon and Shimon Friedlich and Cohen, {Daniel Nissim}",

year = "2015",

language = "אנגלית",

pages = "176--186",

editor = "Zhao, {Hai }",

booktitle = "Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation:",

publisher = "Pacific Asia Conference on Language,Information and Computation",

}

HaCohen-Kerner, Y, Dilmon, R, Friedlich, S & Cohen, DN 2015, Distinguishing Between True and False Stories Using Various Linguistic Features. in H Zhao (ed.), Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters. Pacific Asia Conference on Language,Information and Computation, Shanghai, pp. 176-186. <https://aclanthology.org/Y15-2021/>

Distinguishing Between True and False Stories Using Various Linguistic Features. / HaCohen-Kerner, Yaakov; Dilmon, Rakefet; Friedlich, Shimon et al.
Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation: Posters. ed. / Hai Zhao. Shanghai: Pacific Asia Conference on Language,Information and Computation, 2015. p. 176-186.

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

TY - CHAP

T1 - Distinguishing Between True and False Stories Using Various Linguistic Features

AU - HaCohen-Kerner, Yaakov

AU - Dilmon, Rakefet

AU - Friedlich, Shimon

AU - Cohen, Daniel Nissim

PY - 2015

Y1 - 2015

N2 - This paper analyzes what linguistic features differentiate true and false stories written in Hebrew. To do so, we have defined four feature sets containing 145 features: POS-Tags, quantitative, repetition, and special expressions. The examined corpus contains stories that were composed by 48 native Hebrew speakers who were asked to tell both false and true stories. Classification experiments on all possible combinations of these four feature sets using five supervised machine learning methods have been applied. The Part of Speech (POS) set was superior to all others and has been found as a key component. The best accuracy result (89.6%) has been achieved by a combination of sixteen POS-Tags and one quantitative feature.

AB - This paper analyzes what linguistic features differentiate true and false stories written in Hebrew. To do so, we have defined four feature sets containing 145 features: POS-Tags, quantitative, repetition, and special expressions. The examined corpus contains stories that were composed by 48 native Hebrew speakers who were asked to tell both false and true stories. Classification experiments on all possible combinations of these four feature sets using five supervised machine learning methods have been applied. The Part of Speech (POS) set was superior to all others and has been found as a key component. The best accuracy result (89.6%) has been achieved by a combination of sixteen POS-Tags and one quantitative feature.

UR - http://www.scopus.com/inward/record.url?scp=84967189087&partnerID=8YFLogxK

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.chapter???

SP - 176

EP - 186

BT - Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation:

A2 - Zhao, Hai

PB - Pacific Asia Conference on Language,Information and Computation

CY - Shanghai

ER -

Distinguishing Between True and False Stories Using Various Linguistic Features

Abstract

Access to Document

Other files and links

Fingerprint

Cite this