Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning

Ye Chan Ahn, Chang Sung Jeong

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

Abstract

This Recently, a lot of information is spreading rapidly on SNS. Inaccurate communication of news media includes fears about unreliable sources and fake news that lacks confirmation of facts. Fake news is spread through SNS, causing social confusion and further economic loss. The purpose of the news is accurate information transmission. In this regard, it is very important to judge the discrepancies in the contents of the text and the distorted reports. We try to solve the problem of judging whether the sentence to be verified is correct after collecting the facts. This paper defines the problem of extracting the related sentences from the input sentence in Fact Data Corpus which is assumed to be fact and judging whether the extracted sentence and the input sentence are true or false. In the various NLP tasks, we create a Korean-specific pre-Training model using state-of-The-Art BERT. Using this model, fine-Tuning is performed to match the data set detected by Korean fake news. The AUROC score of 83.8% is derived from the test set generated using the fine-Tuned model.

Original languageEnglish
Title of host publicationJCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering
Subtitle of host publicationKnowledge Evolution Towards Singularity of Man-Machine Intelligence
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages289-292
Number of pages4
ISBN (Electronic)9781728107196
DOIs
Publication statusPublished - 2019 Jul
Event16th International Joint Conference on Computer Science and Software Engineering, JCSSE 2019 - Chonburi, Thailand
Duration: 2019 Jul 102019 Jul 12

Publication series

NameJCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence

Conference

Conference16th International Joint Conference on Computer Science and Software Engineering, JCSSE 2019
CountryThailand
CityChonburi
Period19/7/1019/7/12

Fingerprint

Tuning
Economics
Communication
Evaluation system
Language
News
Deep learning
Discrepancy
Information transmission
News media
Natural language processing
Economic loss

Keywords

  • BERT
  • Fake news Detection
  • NLP

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Human-Computer Interaction
  • Signal Processing
  • Software
  • Information Systems and Management

Cite this

Ahn, Y. C., & Jeong, C. S. (2019). Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning. In JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence (pp. 289-292). [8864171] (JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/JCSSE.2019.8864171

Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning. / Ahn, Ye Chan; Jeong, Chang Sung.

JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence. Institute of Electrical and Electronics Engineers Inc., 2019. p. 289-292 8864171 (JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence).

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

Ahn, YC & Jeong, CS 2019, Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning. in JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence., 8864171, JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence, Institute of Electrical and Electronics Engineers Inc., pp. 289-292, 16th International Joint Conference on Computer Science and Software Engineering, JCSSE 2019, Chonburi, Thailand, 19/7/10. https://doi.org/10.1109/JCSSE.2019.8864171
Ahn YC, Jeong CS. Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning. In JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence. Institute of Electrical and Electronics Engineers Inc. 2019. p. 289-292. 8864171. (JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence). https://doi.org/10.1109/JCSSE.2019.8864171
Ahn, Ye Chan ; Jeong, Chang Sung. / Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning. JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 289-292 (JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence).
@inproceedings{4ab56e279a824b029327ca4591012da2,
title = "Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning",
abstract = "This Recently, a lot of information is spreading rapidly on SNS. Inaccurate communication of news media includes fears about unreliable sources and fake news that lacks confirmation of facts. Fake news is spread through SNS, causing social confusion and further economic loss. The purpose of the news is accurate information transmission. In this regard, it is very important to judge the discrepancies in the contents of the text and the distorted reports. We try to solve the problem of judging whether the sentence to be verified is correct after collecting the facts. This paper defines the problem of extracting the related sentences from the input sentence in Fact Data Corpus which is assumed to be fact and judging whether the extracted sentence and the input sentence are true or false. In the various NLP tasks, we create a Korean-specific pre-Training model using state-of-The-Art BERT. Using this model, fine-Tuning is performed to match the data set detected by Korean fake news. The AUROC score of 83.8{\%} is derived from the test set generated using the fine-Tuned model.",
keywords = "BERT, Fake news Detection, NLP",
author = "Ahn, {Ye Chan} and Jeong, {Chang Sung}",
year = "2019",
month = "7",
doi = "10.1109/JCSSE.2019.8864171",
language = "English",
series = "JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "289--292",
booktitle = "JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering",

}

TY - GEN

T1 - Natural Language Contents Evaluation System for Detecting Fake News using Deep Learning

AU - Ahn, Ye Chan

AU - Jeong, Chang Sung

PY - 2019/7

Y1 - 2019/7

N2 - This Recently, a lot of information is spreading rapidly on SNS. Inaccurate communication of news media includes fears about unreliable sources and fake news that lacks confirmation of facts. Fake news is spread through SNS, causing social confusion and further economic loss. The purpose of the news is accurate information transmission. In this regard, it is very important to judge the discrepancies in the contents of the text and the distorted reports. We try to solve the problem of judging whether the sentence to be verified is correct after collecting the facts. This paper defines the problem of extracting the related sentences from the input sentence in Fact Data Corpus which is assumed to be fact and judging whether the extracted sentence and the input sentence are true or false. In the various NLP tasks, we create a Korean-specific pre-Training model using state-of-The-Art BERT. Using this model, fine-Tuning is performed to match the data set detected by Korean fake news. The AUROC score of 83.8% is derived from the test set generated using the fine-Tuned model.

AB - This Recently, a lot of information is spreading rapidly on SNS. Inaccurate communication of news media includes fears about unreliable sources and fake news that lacks confirmation of facts. Fake news is spread through SNS, causing social confusion and further economic loss. The purpose of the news is accurate information transmission. In this regard, it is very important to judge the discrepancies in the contents of the text and the distorted reports. We try to solve the problem of judging whether the sentence to be verified is correct after collecting the facts. This paper defines the problem of extracting the related sentences from the input sentence in Fact Data Corpus which is assumed to be fact and judging whether the extracted sentence and the input sentence are true or false. In the various NLP tasks, we create a Korean-specific pre-Training model using state-of-The-Art BERT. Using this model, fine-Tuning is performed to match the data set detected by Korean fake news. The AUROC score of 83.8% is derived from the test set generated using the fine-Tuned model.

KW - BERT

KW - Fake news Detection

KW - NLP

UR - http://www.scopus.com/inward/record.url?scp=85074227967&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074227967&partnerID=8YFLogxK

U2 - 10.1109/JCSSE.2019.8864171

DO - 10.1109/JCSSE.2019.8864171

M3 - Conference contribution

AN - SCOPUS:85074227967

T3 - JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering: Knowledge Evolution Towards Singularity of Man-Machine Intelligence

SP - 289

EP - 292

BT - JCSSE 2019 - 16th International Joint Conference on Computer Science and Software Engineering

PB - Institute of Electrical and Electronics Engineers Inc.

ER -