Exploration of feature selection and advanced classification models for high-stakes deception detection

Christie M. Fuller, David P. Biros, Dursun Delen

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

9 Citations (Scopus)

Abstract

Recent research has demonstrated the effectiveness of automated text-based deception detection. In this study, using a variety of data sets and common classification techniques, this has been shown to be an accurate technique. Previous results have shown the need to reduce the number of inputs to these models in order to prevent overfitting. While previous results have been promising, there is a need to improve accuracy and reduce the number of false positives. Using 5 classification models and 3 variable sets, we have achieved accuracy level of 76% in this study.

Original languageEnglish
Title of host publicationProceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS
DOIs
StatePublished - 16 Sep 2008
Externally publishedYes
Event41st Annual Hawaii International Conference on System Sciences 2008, HICSS - Big Island, HI, United States
Duration: 7 Jan 200810 Jan 2008

Publication series

NameProceedings of the Annual Hawaii International Conference on System Sciences
ISSN (Print)1530-1605

Conference

Conference41st Annual Hawaii International Conference on System Sciences 2008, HICSS
CountryUnited States
CityBig Island, HI
Period7/01/0810/01/08

Fingerprint

Feature extraction

Cite this

Fuller, C. M., Biros, D. P., & Delen, D. (2008). Exploration of feature selection and advanced classification models for high-stakes deception detection. In Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS [4438783] (Proceedings of the Annual Hawaii International Conference on System Sciences). https://doi.org/10.1109/HICSS.2008.158
Fuller, Christie M. ; Biros, David P. ; Delen, Dursun. / Exploration of feature selection and advanced classification models for high-stakes deception detection. Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS. 2008. (Proceedings of the Annual Hawaii International Conference on System Sciences).
@inproceedings{c8962b7cc3d44f31b8d3a95a72b1b6a3,
title = "Exploration of feature selection and advanced classification models for high-stakes deception detection",
abstract = "Recent research has demonstrated the effectiveness of automated text-based deception detection. In this study, using a variety of data sets and common classification techniques, this has been shown to be an accurate technique. Previous results have shown the need to reduce the number of inputs to these models in order to prevent overfitting. While previous results have been promising, there is a need to improve accuracy and reduce the number of false positives. Using 5 classification models and 3 variable sets, we have achieved accuracy level of 76{\%} in this study.",
author = "Fuller, {Christie M.} and Biros, {David P.} and Dursun Delen",
year = "2008",
month = "9",
day = "16",
doi = "10.1109/HICSS.2008.158",
language = "English",
isbn = "0769530753",
series = "Proceedings of the Annual Hawaii International Conference on System Sciences",
booktitle = "Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS",

}

Fuller, CM, Biros, DP & Delen, D 2008, Exploration of feature selection and advanced classification models for high-stakes deception detection. in Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS., 4438783, Proceedings of the Annual Hawaii International Conference on System Sciences, 41st Annual Hawaii International Conference on System Sciences 2008, HICSS, Big Island, HI, United States, 7/01/08. https://doi.org/10.1109/HICSS.2008.158

Exploration of feature selection and advanced classification models for high-stakes deception detection. / Fuller, Christie M.; Biros, David P.; Delen, Dursun.

Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS. 2008. 4438783 (Proceedings of the Annual Hawaii International Conference on System Sciences).

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

TY - GEN

T1 - Exploration of feature selection and advanced classification models for high-stakes deception detection

AU - Fuller, Christie M.

AU - Biros, David P.

AU - Delen, Dursun

PY - 2008/9/16

Y1 - 2008/9/16

N2 - Recent research has demonstrated the effectiveness of automated text-based deception detection. In this study, using a variety of data sets and common classification techniques, this has been shown to be an accurate technique. Previous results have shown the need to reduce the number of inputs to these models in order to prevent overfitting. While previous results have been promising, there is a need to improve accuracy and reduce the number of false positives. Using 5 classification models and 3 variable sets, we have achieved accuracy level of 76% in this study.

AB - Recent research has demonstrated the effectiveness of automated text-based deception detection. In this study, using a variety of data sets and common classification techniques, this has been shown to be an accurate technique. Previous results have shown the need to reduce the number of inputs to these models in order to prevent overfitting. While previous results have been promising, there is a need to improve accuracy and reduce the number of false positives. Using 5 classification models and 3 variable sets, we have achieved accuracy level of 76% in this study.

UR - http://www.scopus.com/inward/record.url?scp=51449112010&partnerID=8YFLogxK

U2 - 10.1109/HICSS.2008.158

DO - 10.1109/HICSS.2008.158

M3 - Conference contribution

AN - SCOPUS:51449112010

SN - 0769530753

SN - 9780769530758

T3 - Proceedings of the Annual Hawaii International Conference on System Sciences

BT - Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS

ER -

Fuller CM, Biros DP, Delen D. Exploration of feature selection and advanced classification models for high-stakes deception detection. In Proceedings of the 41st Annual Hawaii International Conference on System Sciences 2008, HICSS. 2008. 4438783. (Proceedings of the Annual Hawaii International Conference on System Sciences). https://doi.org/10.1109/HICSS.2008.158