-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy patharabicHatespeechDatasets.html
1 lines (1 loc) · 16.8 KB
/
arabicHatespeechDatasets.html
1
<html><head><meta content="text/html; charset=UTF-8" http-equiv="content-type"><style type="text/css">@import url('https://themes.googleusercontent.com/fonts/css?kit=OPeqXG-QxW3ZD8BtmPikfA');ol{margin:0;padding:0}table td,table th{padding:0}.c17{border-right-style:solid;padding-top:0pt;border-top-width:0pt;border-right-width:0pt;padding-left:0pt;padding-bottom:0pt;line-height:1.25;border-left-width:0pt;border-top-style:solid;background-color:#ffffff;border-left-style:solid;border-bottom-width:0pt;border-bottom-style:solid;text-align:left;padding-right:0pt}.c9{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:46.5pt;border-top-color:#000000;border-bottom-style:solid}.c1{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:109.5pt;border-top-color:#000000;border-bottom-style:solid}.c2{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:130.5pt;border-top-color:#000000;border-bottom-style:solid}.c8{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:80.2pt;border-top-color:#000000;border-bottom-style:solid}.c4{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:82.5pt;border-top-color:#000000;border-bottom-style:solid}.c6{border-right-style:solid;padding:5pt 5pt 5pt 5pt;border-bottom-color:#000000;border-top-width:1pt;border-right-width:1pt;border-left-color:#000000;vertical-align:top;border-right-color:#000000;border-left-width:1pt;border-top-style:solid;border-left-style:solid;border-bottom-width:1pt;width:117.8pt;border-top-color:#000000;border-bottom-style:solid}.c0{color:#000000;font-weight:400;text-decoration:none;vertical-align:baseline;font-size:11pt;font-family:"Arial";font-style:normal}.c15{background-color:#ffffff;font-size:12pt;font-family:"Roboto";color:#212529;font-weight:400}.c3{padding-top:0pt;padding-bottom:0pt;line-height:1.0;text-align:left}.c16{margin-left:-39.8pt;border-spacing:0;border-collapse:collapse;margin-right:auto}.c13{padding-top:0pt;padding-bottom:0pt;line-height:1.15;text-align:left}.c14{background-color:#ffffff;max-width:468pt;padding:72pt 72pt 72pt 72pt}.c7{orphans:2;widows:2}.c12{background-color:#ffffff;font-size:10.5pt}.c5{height:11pt}.c11{height:0pt}.c10{font-size:11pt}.title{padding-top:0pt;color:#000000;font-size:26pt;padding-bottom:3pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}.subtitle{padding-top:0pt;color:#666666;font-size:15pt;padding-bottom:16pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}li{color:#000000;font-size:11pt;font-family:"Arial"}p{margin:0;color:#000000;font-size:11pt;font-family:"Arial"}h1{padding-top:20pt;color:#000000;font-size:20pt;padding-bottom:6pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}h2{padding-top:18pt;color:#000000;font-size:16pt;padding-bottom:6pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}h3{padding-top:16pt;color:#434343;font-size:14pt;padding-bottom:4pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}h4{padding-top:14pt;color:#666666;font-size:12pt;padding-bottom:4pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}h5{padding-top:12pt;color:#666666;font-size:11pt;padding-bottom:4pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;orphans:2;widows:2;text-align:left}h6{padding-top:12pt;color:#666666;font-size:11pt;padding-bottom:4pt;font-family:"Arial";line-height:1.15;page-break-after:avoid;font-style:italic;orphans:2;widows:2;text-align:left}</style></head><body class="c14"><p class="c13 c7 c5"><span class="c0"></span></p><a id="t.21ed4bc5bc5783c0d8ed509ddae0bcebd462d1df"></a><a id="t.0"></a><table class="c16"><tbody><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Name</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Year </span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Language </span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Link</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Data type</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c7"><span class="c0">Size </span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">Analysis and Detection of Religious Hate Speech in the Arabic Twittersphere(IEEE)</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2018</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Dialectal Arabic and Modern Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://github.com/nuhaalbadi/Arabic_hatespeech</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">Post of Twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">6,136</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">MLMA_hate_speech</span></p><p class="c3"><span class="c0">Multi-Aspect Hate Speech Analysis (ArXiv)</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2019</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://github.com/HKUST-KnowComp/MLMA_hate_speech</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">Twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">3,353</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">L-HSAB: A Levantine Twitter Dataset for Hate Speech and Abusive Language</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2019</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://github.com/Hala-Mulki/L-HSAB-First-Arabic-Levantine-HateSpeech-Dataset</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">Twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">5,846</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span>Abusive Language Detection on Arabic Social Media (</span><span class="c15">Association for Computational Linguistics)</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2017</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://github.com/leondz/hatespeechdata#:~:text=http%3A//alt.qcri.org/~hmubarak/offensive/TweetClassification-Summary.xlsx</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">Twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">1,100</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">Abusive Language Detection on Arabic Social Media (Al Jazeera)</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2017</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Dialectal Arabic and Modern Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">http://alt.qcri.org/~hmubarak/offensive/TweetClassification-Summary.xlsx</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">Twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">32,000</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">Dataset Construction for the Detection of Anti-Social Behaviour in Online Communication in Arabic</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2018</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Dialectal Arabic and Modern Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://onedrive.live.com/?authkey=!ACDXj_ZNcZPqzy0&id=6EF6951FBF8217F9!105&cid=6EF6951FBF8217F9</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">YouTube</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">15,050</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><h2 class="c17" id="h.tgxgzv5ztvn2"><span class="c10">Arabic Levantine Hate Speech dataset</span></h2></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c12">2019</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Arabic Levantine</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://www.kaggle.com/haithemhermessi/arabic-levantine-hate-speech-detection?select=train.csv</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">kaggle</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">4,624</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">Terrorism And Jihadism Speech dataset</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2019</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Standard Arabic</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://www.kaggle.com/haithemhermessi/terrorism-and-jihadist-speech-detection?select=train.csv</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">twitter</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">400</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3"><span class="c0">MSDA Datasets(ump6)</span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3"><span class="c0">2020</span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3"><span class="c0">Arabic dialect</span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3"><span class="c0">https://msda.um6p.ma/api/upload/files/Sentiment%20Anaysis.csv</span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3"><span class="c0">social media posts</span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3"><span class="c0">50K posts</span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr><tr class="c11"><td class="c6" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c9" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c1" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c2" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c8" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td><td class="c4" colspan="1" rowspan="1"><p class="c3 c5"><span class="c0"></span></p></td></tr></tbody></table><p class="c7 c5 c13"><span class="c0"></span></p></body></html>