Stance detection in Arabic with a multi-dialectal cross-domain stance corpus

<div><p>We present a cross-domain and multi-dialectal stance corpus for Arabic, covering the major dialect groups and four Arab regions. This research provides an important language resource for automating the task of stance detection in Dialectal Arabic while carefully considering the s...

Full description

Saved in:
Bibliographic Details
Main Author: Anis Charfi (18697357) (author)
Other Authors: Mabrouka Bessghaier (22155103) (author), Andria Atalla (18697366) (author), Raghda Akasheh (18697363) (author), Sara Al-Emadi (22155106) (author), Wajdi Zaghouani (5297402) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513540982833152
author Anis Charfi (18697357)
author2 Mabrouka Bessghaier (22155103)
Andria Atalla (18697366)
Raghda Akasheh (18697363)
Sara Al-Emadi (22155106)
Wajdi Zaghouani (5297402)
author2_role author
author
author
author
author
author_facet Anis Charfi (18697357)
Mabrouka Bessghaier (22155103)
Andria Atalla (18697366)
Raghda Akasheh (18697363)
Sara Al-Emadi (22155106)
Wajdi Zaghouani (5297402)
author_role author
dc.creator.none.fl_str_mv Anis Charfi (18697357)
Mabrouka Bessghaier (22155103)
Andria Atalla (18697366)
Raghda Akasheh (18697363)
Sara Al-Emadi (22155106)
Wajdi Zaghouani (5297402)
dc.date.none.fl_str_mv 2024-08-16T09:00:00Z
dc.identifier.none.fl_str_mv 10.1007/s13278-024-01335-5
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Stance_detection_in_Arabic_with_a_multi-dialectal_cross-domain_stance_corpus/30023185
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Machine learning
Natural language processing
Arabic
Machine learning
Corpus Stance detection
Polarization
Arabic dialects
dc.title.none.fl_str_mv Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <div><p>We present a cross-domain and multi-dialectal stance corpus for Arabic, covering the major dialect groups and four Arab regions. This research provides an important language resource for automating the task of stance detection in Dialectal Arabic while carefully considering the subtle differences in stance expression across various dialects. More than 4500 sentences in our corpus have been carefully annotated according to their stance with regard to a certain subject. We gathered sentences associated with two controversial topics for every region and we had at least two annotators annotate each sentence to indicate if the author is supporting, opposing, or neutral to the sentence’s topic. Our corpus shows high balance between dialect and stance. About half of the sentences in each region are written in Modern Standard Arabic, while the other half are written in the specific dialect of that region. To evaluate our corpus, we performed a number of machine-learning experiments for the stance detection task. The best performance was achieved by AraBERT with an accuracy and an F1-score of 0.82. Furthermore, we trained and tested this model on the most similar state-of-the-art stance dataset, “MAWQIF”. The comparison results demonstrate how crucial it is to maintain balance among the three stance classes in our dataset. In particular, the model scored better when using our stance corpus than when using the MAWQIF dataset especially for the “Neutral” stance class. Using our best performing model, we developed a Web-based demonstrator for stance detection in dialectal Arabic and we show its effectiveness in analyzing stance in the context of two real-world scenarios: product boycott in the Arab world and customer reviews of a soft drink company.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Social Network Analysis and Mining<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s13278-024-01335-5" target="_blank">https://dx.doi.org/10.1007/s13278-024-01335-5</a></p>
eu_rights_str_mv openAccess
id Manara2_159c3a7dbfba5f1be0fe606ffca981be
identifier_str_mv 10.1007/s13278-024-01335-5
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/30023185
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Stance detection in Arabic with a multi-dialectal cross-domain stance corpusAnis Charfi (18697357)Mabrouka Bessghaier (22155103)Andria Atalla (18697366)Raghda Akasheh (18697363)Sara Al-Emadi (22155106)Wajdi Zaghouani (5297402)Information and computing sciencesArtificial intelligenceMachine learningNatural language processingArabicMachine learningCorpus Stance detectionPolarizationArabic dialects<div><p>We present a cross-domain and multi-dialectal stance corpus for Arabic, covering the major dialect groups and four Arab regions. This research provides an important language resource for automating the task of stance detection in Dialectal Arabic while carefully considering the subtle differences in stance expression across various dialects. More than 4500 sentences in our corpus have been carefully annotated according to their stance with regard to a certain subject. We gathered sentences associated with two controversial topics for every region and we had at least two annotators annotate each sentence to indicate if the author is supporting, opposing, or neutral to the sentence’s topic. Our corpus shows high balance between dialect and stance. About half of the sentences in each region are written in Modern Standard Arabic, while the other half are written in the specific dialect of that region. To evaluate our corpus, we performed a number of machine-learning experiments for the stance detection task. The best performance was achieved by AraBERT with an accuracy and an F1-score of 0.82. Furthermore, we trained and tested this model on the most similar state-of-the-art stance dataset, “MAWQIF”. The comparison results demonstrate how crucial it is to maintain balance among the three stance classes in our dataset. In particular, the model scored better when using our stance corpus than when using the MAWQIF dataset especially for the “Neutral” stance class. Using our best performing model, we developed a Web-based demonstrator for stance detection in dialectal Arabic and we show its effectiveness in analyzing stance in the context of two real-world scenarios: product boycott in the Arab world and customer reviews of a soft drink company.</p><p> </p></div><h2>Other Information</h2> <p> Published in: Social Network Analysis and Mining<br> License: <a href="https://creativecommons.org/licenses/by/4.0" target="_blank">https://creativecommons.org/licenses/by/4.0</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1007/s13278-024-01335-5" target="_blank">https://dx.doi.org/10.1007/s13278-024-01335-5</a></p>2024-08-16T09:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1007/s13278-024-01335-5https://figshare.com/articles/journal_contribution/Stance_detection_in_Arabic_with_a_multi-dialectal_cross-domain_stance_corpus/30023185CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/300231852024-08-16T09:00:00Z
spellingShingle Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
Anis Charfi (18697357)
Information and computing sciences
Artificial intelligence
Machine learning
Natural language processing
Arabic
Machine learning
Corpus Stance detection
Polarization
Arabic dialects
status_str publishedVersion
title Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
title_full Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
title_fullStr Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
title_full_unstemmed Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
title_short Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
title_sort Stance detection in Arabic with a multi-dialectal cross-domain stance corpus
topic Information and computing sciences
Artificial intelligence
Machine learning
Natural language processing
Arabic
Machine learning
Corpus Stance detection
Polarization
Arabic dialects