The following results are related to DARIAH EU. Are you interested to view more results? Visit OpenAIRE - Explore.

1 Research products

DARIAH EU
Publications
Research data
Research software
2019-2023
Open Access
Article
Preprint
DE
arXiv.org e-Print Archive
DARIAH EU

Sort by

Date (most recent)

arrow_drop_down

Neural Based Statement Classification for Biased Language
descriptionPublicationkeyboard_double_arrow_right Article , Conference object , Preprint 2019ACM EC | AFEL, EC | ALEXANDRIA, EC | DESIR
EC| AFEL ,
EC| ALEXANDRIA ,
EC| DESIR
Authors: Christoph Hube; Besnik Fetahu;
Christoph Hube; Besnik Fetahu;
doi: 10.1145/3289600.3291018 , 10.48550/arxiv.1811.05740
doi: 10.1145/3289600.3291018 , 10.48550/arxiv.1811.05740
Biased language commonly occurs around topics which are of controversial nature, thus, stirring disagreement between the different involved parties of a discussion. This is due to the fact that for language and its use, specifically, the understanding and use of phrases, the stances are cohesive within the particular groups. However, such cohesiveness does not hold across groups. In collaborative environments or environments where impartial language is desired (e.g. Wikipedia, news media), statements and the language therein should represent equally the involved parties and be neutrally phrased. Biased language is introduced through the presence of inflammatory words or phrases, or statements that may be incorrect or one-sided, thus violating such consensus. In this work, we focus on the specific case of phrasing bias, which may be introduced through specific inflammatory words or phrases in a statement. For this purpose, we propose an approach that relies on a recurrent neural networks in order to capture the inter-dependencies between words in a phrase that introduced bias. We perform a thorough experimental evaluation, where we show the advantages of a neural based approach over competitors that rely on word lexicons and other hand-crafted features in detecting biased language. We are able to distinguish biased statements with a precision of P=0.92, thus significantly outperforming baseline models with an improvement of over 30%. Finally, we release the largest corpus of statements annotated for biased language. Comment: The Twelfth ACM International Conference on Web Search and Data Mining, February 11--15, 2019, Melbourne, VIC, Australia
arXiv.org e-Print Ar...arrow_drop_down
arXiv.org e-Print Archive
Preprint . 2018
Data sources: arXiv.org e-Print Archive
http://arxiv.org/pdf/1811.0574...
Conference object
Data sources: UnpayWall
https://doi.org/10.1145/328960...
Conference object . 2019
License: http://www.acm.org/publications/policies/copyright_policy#Background
Data sources: Crossref
https://doi.org/10.48550/arxiv...
Article . 2018
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Data sources: Datacite
linkLink to
shareshareShare
citeCite
addClaim
Please grant OpenAIRE to access and update your ORCID works.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.
Select content type to embed
All Research products
arrow_drop_down
<script type="text/javascript">  </script>
COPY SCRIPT
For further information contact us at helpdesk@openaire.eu
27
citations 27
popularity Top 10%
influence Top 10%
impulse Top 10%
Powered by BIP!
more_vert
arXiv.org e-Print Ar...arrow_drop_down
arXiv.org e-Print Archive
Preprint . 2018
Data sources: arXiv.org e-Print Archive
http://arxiv.org/pdf/1811.0574...
Conference object
Data sources: UnpayWall
https://doi.org/10.1145/328960...
Conference object . 2019
License: http://www.acm.org/publications/policies/copyright_policy#Background
Data sources: Crossref
https://doi.org/10.48550/arxiv...
Article . 2018
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Data sources: Datacite
linkLink to
shareshareShare
citeCite
addClaim
Please grant OpenAIRE to access and update your ORCID works.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.
Select content type to embed
All Research products
arrow_drop_down
<script type="text/javascript">  </script>
COPY SCRIPT
For further information contact us at helpdesk@openaire.eu

The following results are related to DARIAH EU. Are you interested to view more results? Visit OpenAIRE - Explore.

1 Research products

Neural Based Statement Classification for Biased Language
descriptionPublicationkeyboard_double_arrow_right Article , Conference object , Preprint 2019ACM EC | AFEL, EC | ALEXANDRIA, EC | DESIR
EC| AFEL ,
EC| ALEXANDRIA ,
EC| DESIR
Authors: Christoph Hube; Besnik Fetahu;
Christoph Hube; Besnik Fetahu;
doi: 10.1145/3289600.3291018 , 10.48550/arxiv.1811.05740
doi: 10.1145/3289600.3291018 , 10.48550/arxiv.1811.05740
Biased language commonly occurs around topics which are of controversial nature, thus, stirring disagreement between the different involved parties of a discussion. This is due to the fact that for language and its use, specifically, the understanding and use of phrases, the stances are cohesive within the particular groups. However, such cohesiveness does not hold across groups. In collaborative environments or environments where impartial language is desired (e.g. Wikipedia, news media), statements and the language therein should represent equally the involved parties and be neutrally phrased. Biased language is introduced through the presence of inflammatory words or phrases, or statements that may be incorrect or one-sided, thus violating such consensus. In this work, we focus on the specific case of phrasing bias, which may be introduced through specific inflammatory words or phrases in a statement. For this purpose, we propose an approach that relies on a recurrent neural networks in order to capture the inter-dependencies between words in a phrase that introduced bias. We perform a thorough experimental evaluation, where we show the advantages of a neural based approach over competitors that rely on word lexicons and other hand-crafted features in detecting biased language. We are able to distinguish biased statements with a precision of P=0.92, thus significantly outperforming baseline models with an improvement of over 30%. Finally, we release the largest corpus of statements annotated for biased language. Comment: The Twelfth ACM International Conference on Web Search and Data Mining, February 11--15, 2019, Melbourne, VIC, Australia
arXiv.org e-Print Ar...arrow_drop_down
arXiv.org e-Print Archive
Preprint . 2018
Data sources: arXiv.org e-Print Archive
http://arxiv.org/pdf/1811.0574...
Conference object
Data sources: UnpayWall
https://doi.org/10.1145/328960...
Conference object . 2019
License: http://www.acm.org/publications/policies/copyright_policy#Background
Data sources: Crossref
https://doi.org/10.48550/arxiv...
Article . 2018
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Data sources: Datacite
linkLink to
shareshareShare
citeCite
addClaim
Please grant OpenAIRE to access and update your ORCID works.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.
Select content type to embed
All Research products
arrow_drop_down
<script type="text/javascript">  </script>
COPY SCRIPT
For further information contact us at helpdesk@openaire.eu
27
citations 27
popularity Top 10%
influence Top 10%
impulse Top 10%
Powered by BIP!
more_vert
arXiv.org e-Print Ar...arrow_drop_down
arXiv.org e-Print Archive
Preprint . 2018
Data sources: arXiv.org e-Print Archive
http://arxiv.org/pdf/1811.0574...
Conference object
Data sources: UnpayWall
https://doi.org/10.1145/328960...
Conference object . 2019
License: http://www.acm.org/publications/policies/copyright_policy#Background
Data sources: Crossref
https://doi.org/10.48550/arxiv...
Article . 2018
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Data sources: Datacite
linkLink to
shareshareShare
citeCite
addClaim
Please grant OpenAIRE to access and update your ORCID works.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
This Research product is the result of merged Research products in OpenAIRE.

You have already added works in your ORCID record related to the merged Research product.
Do the share buttons not appear? Please make sure, any blocking addon is disabled, and then reload the page.
Select content type to embed
All Research products
arrow_drop_down
<script type="text/javascript">  </script>
COPY SCRIPT
For further information contact us at helpdesk@openaire.eu

Filters

Access (1)

Type (4)

Document Type (3)

Year range

Field of Science [Beta] (6)

Funder (1)

Country (2)

Source (1)

Research community (3)

DARIAH EU
Publications
Research data
Research software
2019-2023
Open Access
Article
Preprint
DE
arXiv.org e-Print Archive
DARIAH EU

Neural Based Statement Classification for Biased Language

Neural Based Statement Classification for Biased Language

Searching Fields	Terms
Any field arrow_drop_down includes arrow_drop_down

	citations	27
	popularity	Top 10%
	influence	Top 10%
	impulse	Top 10%

	citations	27
	popularity	Top 10%
	influence	Top 10%
	impulse	Top 10%

Filters

Access (1)

Type (4)

Document Type (3)

Year range

Field of Science [Beta] (6)

Funder (1)

Country (2)

Source (1)

Research community (3)

Loading

DARIAH EU PublicationscloseResearch datacloseResearch softwareclose2019-2023close Open Access close Article close Preprint close DE close arXiv.org e-Print Archive close DARIAH EU close

Neural Based Statement Classification for Biased Language

Loading

Neural Based Statement Classification for Biased Language

DARIAH EU
Publications
Research data
Research software
2019-2023
Open Access
Article
Preprint
DE
arXiv.org e-Print Archive
DARIAH EU