Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages
The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are ne...
Gespeichert in:
| Veröffentlicht in: | arXiv.org 2021-12 |
|---|---|
| Hauptverfasser: | , , , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | |
|---|---|
| container_issue | |
| container_start_page | |
| container_title | arXiv.org |
| container_volume | |
| creator | Mandl, Thomas Modha, Sandip Shahi, Gautam Kishore Hiren Madhu Shrey Satapara Majumder, Prasenjit Schaefer, Johannes Ranasinghe, Tharindu Zampieri, Marcos Durgesh Nandini Jaiswal, Amit Kumar |
| description | The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary classification problem (Hate and Not Offensive) offered for all three languages. Task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY offered for English and Hindi. Overall, 652 runs were submitted by 65 teams. The performance of the best classification algorithms for task A are F1 measures 0.91, 0.78 and 0.83 for Marathi, Hindi and English, respectively. This overview presents the tasks and the data development as well as the detailed results. The systems submitted to the competition applied a variety of technologies. The best performing algorithms were mainly variants of transformer architectures. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2611837763</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2611837763</sourcerecordid><originalsourceid>FETCH-proquest_journals_26118377633</originalsourceid><addsrcrecordid>eNqNisFqwkAUAJeCUFH_4YHnQLJbE-lNQiQBIdB4D6_J27gqb-3uJtJj_1yh_YBeZg4zL2IulUqi7ZuUr2Ll_TmOY5lmcrNRc_FTT-QmQ3ewGsKJoNw1dQ7N-BkcdhfAAPvqowAZy-QdSgwEzY2oOwFyD7XWxN5MBLnlQByg6p802nQYjGUwDAUPV-N__4p7G-3cNzIckIcRB_JLMdN49bT680Ks98UxL6Obs18j-dCe7ej4mVqZJslWZVmq1P-uB0wqTgY</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2611837763</pqid></control><display><type>article</type><title>Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages</title><source>Free E- Journals</source><creator>Mandl, Thomas ; Modha, Sandip ; Shahi, Gautam Kishore ; Hiren Madhu ; Shrey Satapara ; Majumder, Prasenjit ; Schaefer, Johannes ; Ranasinghe, Tharindu ; Zampieri, Marcos ; Durgesh Nandini ; Jaiswal, Amit Kumar</creator><creatorcontrib>Mandl, Thomas ; Modha, Sandip ; Shahi, Gautam Kishore ; Hiren Madhu ; Shrey Satapara ; Majumder, Prasenjit ; Schaefer, Johannes ; Ranasinghe, Tharindu ; Zampieri, Marcos ; Durgesh Nandini ; Jaiswal, Amit Kumar</creatorcontrib><description>The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary classification problem (Hate and Not Offensive) offered for all three languages. Task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY offered for English and Hindi. Overall, 652 runs were submitted by 65 teams. The performance of the best classification algorithms for task A are F1 measures 0.91, 0.78 and 0.83 for Marathi, Hindi and English, respectively. This overview presents the tasks and the data development as well as the detailed results. The systems submitted to the competition applied a variety of technologies. The best performing algorithms were mainly variants of transformer architectures.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Algorithms ; Classification ; Datasets ; Experimentation ; Hate speech ; Languages ; Social problems</subject><ispartof>arXiv.org, 2021-12</ispartof><rights>2021. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>776,780</link.rule.ids></links><search><creatorcontrib>Mandl, Thomas</creatorcontrib><creatorcontrib>Modha, Sandip</creatorcontrib><creatorcontrib>Shahi, Gautam Kishore</creatorcontrib><creatorcontrib>Hiren Madhu</creatorcontrib><creatorcontrib>Shrey Satapara</creatorcontrib><creatorcontrib>Majumder, Prasenjit</creatorcontrib><creatorcontrib>Schaefer, Johannes</creatorcontrib><creatorcontrib>Ranasinghe, Tharindu</creatorcontrib><creatorcontrib>Zampieri, Marcos</creatorcontrib><creatorcontrib>Durgesh Nandini</creatorcontrib><creatorcontrib>Jaiswal, Amit Kumar</creatorcontrib><title>Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages</title><title>arXiv.org</title><description>The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary classification problem (Hate and Not Offensive) offered for all three languages. Task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY offered for English and Hindi. Overall, 652 runs were submitted by 65 teams. The performance of the best classification algorithms for task A are F1 measures 0.91, 0.78 and 0.83 for Marathi, Hindi and English, respectively. This overview presents the tasks and the data development as well as the detailed results. The systems submitted to the competition applied a variety of technologies. The best performing algorithms were mainly variants of transformer architectures.</description><subject>Algorithms</subject><subject>Classification</subject><subject>Datasets</subject><subject>Experimentation</subject><subject>Hate speech</subject><subject>Languages</subject><subject>Social problems</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>BENPR</sourceid><recordid>eNqNisFqwkAUAJeCUFH_4YHnQLJbE-lNQiQBIdB4D6_J27gqb-3uJtJj_1yh_YBeZg4zL2IulUqi7ZuUr2Ll_TmOY5lmcrNRc_FTT-QmQ3ewGsKJoNw1dQ7N-BkcdhfAAPvqowAZy-QdSgwEzY2oOwFyD7XWxN5MBLnlQByg6p802nQYjGUwDAUPV-N__4p7G-3cNzIckIcRB_JLMdN49bT680Ks98UxL6Obs18j-dCe7ej4mVqZJslWZVmq1P-uB0wqTgY</recordid><startdate>20211217</startdate><enddate>20211217</enddate><creator>Mandl, Thomas</creator><creator>Modha, Sandip</creator><creator>Shahi, Gautam Kishore</creator><creator>Hiren Madhu</creator><creator>Shrey Satapara</creator><creator>Majumder, Prasenjit</creator><creator>Schaefer, Johannes</creator><creator>Ranasinghe, Tharindu</creator><creator>Zampieri, Marcos</creator><creator>Durgesh Nandini</creator><creator>Jaiswal, Amit Kumar</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20211217</creationdate><title>Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages</title><author>Mandl, Thomas ; Modha, Sandip ; Shahi, Gautam Kishore ; Hiren Madhu ; Shrey Satapara ; Majumder, Prasenjit ; Schaefer, Johannes ; Ranasinghe, Tharindu ; Zampieri, Marcos ; Durgesh Nandini ; Jaiswal, Amit Kumar</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_26118377633</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Algorithms</topic><topic>Classification</topic><topic>Datasets</topic><topic>Experimentation</topic><topic>Hate speech</topic><topic>Languages</topic><topic>Social problems</topic><toplevel>online_resources</toplevel><creatorcontrib>Mandl, Thomas</creatorcontrib><creatorcontrib>Modha, Sandip</creatorcontrib><creatorcontrib>Shahi, Gautam Kishore</creatorcontrib><creatorcontrib>Hiren Madhu</creatorcontrib><creatorcontrib>Shrey Satapara</creatorcontrib><creatorcontrib>Majumder, Prasenjit</creatorcontrib><creatorcontrib>Schaefer, Johannes</creatorcontrib><creatorcontrib>Ranasinghe, Tharindu</creatorcontrib><creatorcontrib>Zampieri, Marcos</creatorcontrib><creatorcontrib>Durgesh Nandini</creatorcontrib><creatorcontrib>Jaiswal, Amit Kumar</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science & Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection (ProQuest)</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Mandl, Thomas</au><au>Modha, Sandip</au><au>Shahi, Gautam Kishore</au><au>Hiren Madhu</au><au>Shrey Satapara</au><au>Majumder, Prasenjit</au><au>Schaefer, Johannes</au><au>Ranasinghe, Tharindu</au><au>Zampieri, Marcos</au><au>Durgesh Nandini</au><au>Jaiswal, Amit Kumar</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages</atitle><jtitle>arXiv.org</jtitle><date>2021-12-17</date><risdate>2021</risdate><eissn>2331-8422</eissn><abstract>The widespread of offensive content online such as hate speech poses a growing societal problem. AI tools are necessary for supporting the moderation process at online platforms. For the evaluation of these identification tools, continuous experimentation with data sets in different languages are necessary. The HASOC track (Hate Speech and Offensive Content Identification) is dedicated to develop benchmark data for this purpose. This paper presents the HASOC subtrack for English, Hindi, and Marathi. The data set was assembled from Twitter. This subtrack has two sub-tasks. Task A is a binary classification problem (Hate and Not Offensive) offered for all three languages. Task B is a fine-grained classification problem for three classes (HATE) Hate speech, OFFENSIVE and PROFANITY offered for English and Hindi. Overall, 652 runs were submitted by 65 teams. The performance of the best classification algorithms for task A are F1 measures 0.91, 0.78 and 0.83 for Marathi, Hindi and English, respectively. This overview presents the tasks and the data development as well as the detailed results. The systems submitted to the competition applied a variety of technologies. The best performing algorithms were mainly variants of transformer architectures.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | EISSN: 2331-8422 |
| ispartof | arXiv.org, 2021-12 |
| issn | 2331-8422 |
| language | eng |
| recordid | cdi_proquest_journals_2611837763 |
| source | Free E- Journals |
| subjects | Algorithms Classification Datasets Experimentation Hate speech Languages Social problems |
| title | Overview of the HASOC Subtrack at FIRE 2021: Hate Speech and Offensive Content Identification in English and Indo-Aryan Languages |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-07T21%3A39%3A50IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=Overview%20of%20the%20HASOC%20Subtrack%20at%20FIRE%202021:%20Hate%20Speech%20and%20Offensive%20Content%20Identification%20in%20English%20and%20Indo-Aryan%20Languages&rft.jtitle=arXiv.org&rft.au=Mandl,%20Thomas&rft.date=2021-12-17&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2611837763%3C/proquest%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2611837763&rft_id=info:pmid/&rfr_iscdi=true |