{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T18:49:47Z","timestamp":1773082187159,"version":"3.50.1"},"reference-count":50,"publisher":"Emerald","issue":"6","license":[{"start":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T00:00:00Z","timestamp":1647907200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.emerald.com\/insight\/site-policies"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AJIM"],"published-print":{"date-parts":[[2022,9,29]]},"abstract":"Purpose<\/jats:title>The present study was designed to investigate eight research questions that are related to the analysis and the detection of dialectal Arabic hate speech that targeted African refugees and illegal migrants on the YouTube Algerian space.<\/jats:p><\/jats:sec>Design\/methodology\/approach<\/jats:title>The transfer learning approach which recently presents the state-of-the-art approach in natural language processing tasks has been exploited to classify and detect hate speech in Algerian dialectal Arabic. Besides, a descriptive analysis has been conducted to answer the analytical research questions that aim at measuring and evaluating the presence of the anti-refugee\/migrant discourse on the YouTube social platform.<\/jats:p><\/jats:sec>Findings<\/jats:title>Data analysis revealed that there has been a gradual modest increase in the number of anti-refugee\/migrant hateful comments on YouTube since 2014, a sharp rise in 2017 and a sharp decline in later years until 2021. Furthermore, our findings stemming from classifying hate content using multilingual and monolingual pre-trained language transformers demonstrate a good performance of the AraBERT monolingual transformer in comparison with the monodialectal transformer DziriBERT and the cross-lingual transformers mBERT and XLM-R.<\/jats:p><\/jats:sec>Originality\/value<\/jats:title>Automatic hate speech detection in languages other than English is quite a challenging task that the literature has tried to address by various approaches of machine learning. Although the recent approach of cross-lingual transfer learning offers a promising solution, tackling this problem in the context of the Arabic language, particularly dialectal Arabic makes it even more challenging. Our results cast a new light on the actual ability of the transfer learning approach to deal with low-resource languages that widely differ from high-resource languages as well as other Latin-based, low-resource languages.<\/jats:p><\/jats:sec>","DOI":"10.1108\/ajim-10-2021-0293","type":"journal-article","created":{"date-parts":[[2022,3,21]],"date-time":"2022-03-21T23:51:31Z","timestamp":1647906691000},"page":"1070-1088","source":"Crossref","is-referenced-by-count":11,"title":["Evaluating transfer learning approach for detecting Arabic anti-refugee\/migrant speech on social media"],"prefix":"10.1108","volume":"74","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4878-5201","authenticated-orcid":false,"given":"Djamila","family":"Mohdeb","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2010-9527","authenticated-orcid":false,"given":"Meriem","family":"Laifa","sequence":"additional","affiliation":[]},{"given":"Fayssal","family":"Zerargui","sequence":"additional","affiliation":[]},{"given":"Omar","family":"Benzaoui","sequence":"additional","affiliation":[]}],"member":"140","published-online":{"date-parts":[[2022,3,22]]},"reference":[{"key":"key2022092904024940900_ref001","article-title":"DziriBERT: a pre-trained language model for the Algerian dialect","volume-title":"\u201d","year":"2021"},{"key":"key2022092904024940900_ref002","article-title":"Characterizing linguistic attributes for automatic classification of intent based racist\/radicalized posts on Tumblr micro-blogging website","year":"2017"},{"key":"key2022092904024940900_ref003","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00530-020-00742-w","article-title":"Detection of hate speech in Arabic tweets using deep learning","year":"2021","journal-title":"Multimedia Systems"},{"key":"key2022092904024940900_ref004","doi-asserted-by":"publisher","first-page":"106363","DOI":"10.1109\/ACCESS.2021.3100435","article-title":"Detecting white supremacist hate speech using domain specific word embedding with deep learning and BERT","volume":"9","year":"2021","journal-title":"IEEE Access"},{"key":"key2022092904024940900_ref005","article-title":"Cyber hate classification: \u2018othering\u2019 language and paragraph embedding","year":"2018"},{"issue":"23","key":"key2022092904024940900_ref006","doi-asserted-by":"crossref","first-page":"8614","DOI":"10.3390\/app10238614","article-title":"A deep learning approach for automatic hate speech detection in the Saudi Twittersphere","volume":"10","year":"2020","journal-title":"Applied Sciences"},{"key":"key2022092904024940900_ref007","article-title":"Arabert: transformer-based model for Arabic language understanding","year":"2020"},{"key":"key2022092904024940900_ref008","volume-title":"Alg\u00e9rie : pourquoi la situation des migrants subsahariens est-elle si probl\u00e9matique","year":"2017"},{"key":"key2022092904024940900_ref009","first-page":"15","article-title":"Cross-lingual transfer learning for hate speech detection","year":"2021"},{"issue":"2","key":"key2022092904024940900_ref010","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1002\/poi3.85","article-title":"Cyber hate speech on Twitter: an application of machine classification and statistical modeling for policy and decision making","volume":"7","year":"2015","journal-title":"Policy and Internet"},{"key":"key2022092904024940900_ref011","article-title":"Hatebert: retraining BERT for abusive language detection in English","year":"2020"},{"key":"key2022092904024940900_ref012","article-title":"Algeria to grant legal status to African migrants amid worker shortages, racism","year":"2017"},{"key":"key2022092904024940900_ref013","article-title":"Trump sues Twitter, Google and Facebook alleging \u2018censorship","year":"2021"},{"key":"key2022092904024940900_ref014","article-title":"Unsupervised cross-lingual representation learning at scale","year":"2019"},{"key":"key2022092904024940900_ref015","article-title":"Automated hate speech detection and the problem of offensive language","year":"2017"},{"key":"key2022092904024940900_ref016","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","year":"2018"},{"key":"key2022092904024940900_ref017","article-title":"Modeling the detection of textual cyberbullying","year":"2011"},{"key":"key2022092904024940900_ref018","article-title":"Facebook's AI treats palestinian activists like it treats American Black activists. It blocks them","year":"2021"},{"key":"key2022092904024940900_ref019","first-page":"5522","article-title":"Go simple and pre-train on domain-specific corpora: on the role of training data for text classification","year":"2020"},{"key":"key2022092904024940900_ref020","article-title":"Hate lingo: a target-based linguistic analysis of hate speech in social media","year":"2018"},{"issue":"4","key":"key2022092904024940900_ref021","first-page":"1","article-title":"A survey on automatic detection of hate speech in text","volume":"51","year":"2018","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"key2022092904024940900_ref022","volume-title":"Countering Online Hate Speech\u201d","year":"2015"},{"issue":"4","key":"key2022092904024940900_ref023","doi-asserted-by":"crossref","first-page":"215","DOI":"10.14257\/ijmue.2015.10.4.21","article-title":"A lexicon-based approach for hate speech detection","volume":"10","year":"2015","journal-title":"International Journal of Multimedia and Ubiquitous Engineering"},{"key":"key2022092904024940900_ref024","first-page":"468","article-title":"Classifying racist texts using a support vector machine","year":"2004"},{"key":"key2022092904024940900_ref025","first-page":"76","article-title":"Arabic offensive language detection with attention-based deep neural networks","year":"2020"},{"key":"key2022092904024940900_ref026","article-title":"L'Alg\u00e9rie re\u00e7oit quotidiennement plus de migrants que toute l'Europe","year":"2019"},{"key":"key2022092904024940900_ref027","first-page":"333","article-title":"The problem of identifying misogynist language on twitter (and other online social spaces)","year":"2016"},{"key":"key2022092904024940900_ref028","doi-asserted-by":"crossref","first-page":"179","DOI":"10.17231\/comsoc.38(2020).2582","article-title":"Migrants, refugees and othering: constructing Europeanness, an exploration of Portuguese and German media","volume":"38","year":"2020","journal-title":"Comunica\u00e7\u00e3o e sociedade"},{"key":"key2022092904024940900_ref029","volume-title":"Discussing the Value of Automatic Hate Speech Detection in Online Debates\u201d, Multikonferenz Wirtschaftsinformatik (MKWI 2018): Data Driven X-Turning Data in Value, Leuphana 2018","year":"2018"},{"key":"key2022092904024940900_ref030","first-page":"487","article-title":"New classification models for detecting hate and violence web content","year":"2015"},{"key":"key2022092904024940900_ref031","article-title":"Neural character-based composition models for abuse detection","year":"2018"},{"key":"key2022092904024940900_ref032","article-title":"Let-Mi: an Arabic Levantine twitter dataset for misogynistic language","year":"2021"},{"key":"key2022092904024940900_ref033","volume-title":"Alg\u00e9rie: les facettes de la migration pour cause de crises","year":"2014"},{"key":"key2022092904024940900_ref034","article-title":"Multilingual and multi-aspect hate speech analysis","year":"2019"},{"issue":"1","key":"key2022092904024940900_ref035","doi-asserted-by":"crossref","first-page":"204","DOI":"10.1093\/jrs\/feaa022","article-title":"Discussing the populist features of anti-refugee discourses on social media: an anti-Syrian Hashtag in Turkish Twitter","volume":"34","year":"2021","journal-title":"Journal of Refugee Studies"},{"issue":"7","key":"key2022092904024940900_ref036","doi-asserted-by":"publisher","first-page":"34","DOI":"10.3390\/mti5070034","article-title":"Multimodal hate speech detection in Greek social media","volume":"5","year":"2021","journal-title":"Multimodal Technologies and Interaction"},{"key":"key2022092904024940900_ref037","article-title":"How multilingual is multilingual BERT?","year":"2019"},{"key":"key2022092904024940900_ref038","article-title":"Us vs them: the sinister techniques of \u2018Othering\u2019 \u2013 and how to avoid them","year":"2017","journal-title":"The Guardian"},{"key":"key2022092904024940900_ref039","first-page":"39","volume-title":"The Health Of Refugees: Public Health Perspectives from Crisis to SettlementSocial Exclusion, Othering, and Refugee Health Policy","year":"2018"},{"key":"key2022092904024940900_ref040","article-title":"Transfer learning for hate speech detection in social media","year":"2019"},{"key":"key2022092904024940900_ref041","article-title":"Measuring the reliability of hate speech annotations: the case of the European refugee crisis","year":"2017"},{"key":"key2022092904024940900_ref042","first-page":"255","article-title":"Prevalence and psychological effects of hateful speech in online college communities","year":"2019"},{"key":"key2022092904024940900_ref043","first-page":"56","article-title":"Online hate speech. social media and democracy: the state of the field","year":"2020","journal-title":"Prospects for Reform"},{"key":"key2022092904024940900_ref044","unstructured":"Siegel, A., Tucker, J., Nagler, J. and Bonneau, R. (2017), \u201cSocially mediated sectarianism\u201d, Unpublished Manuscript, available at: http:\/\/alexandra-siegel.com\/wp-content\/uploads\/2017\/08\/Siegel_Sectarianism_January2017.pdf."},{"key":"key2022092904024940900_ref045","unstructured":"UNHCR (2016), \u201cUNHCR viewpoint: \u2018Refugee' or \u2018migrant' \u2013 which is right\u201d, available at: https:\/\/www.unhcr.org\/news\/latest\/2016\/7\/55df0e556\/unhcr-viewpoint-refugee-migrant-right.html (accessed 01 October 2021)."},{"key":"key2022092904024940900_ref046","first-page":"19","article-title":"Detecting hate speech on the world wide web","year":"2012"},{"key":"key2022092904024940900_ref047","first-page":"88","article-title":"Hateful symbols or hateful people? Predictive features for hate speech detection on Twitter","year":"2016"},{"key":"key2022092904024940900_ref048","article-title":"CRAB: class representation attentive BERT for hate speech identification in social media","year":"2020"},{"key":"key2022092904024940900_ref049","first-page":"745","article-title":"Detecting hate speech on twitter using a convolution-GRU based deep neural network","year":"2018"},{"key":"key2022092904024940900_ref050","first-page":"43","article-title":"A comprehensive survey on transfer learning","year":"2020"}],"container-title":["Aslib Journal of Information Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/AJIM-10-2021-0293\/full\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.emerald.com\/insight\/content\/doi\/10.1108\/AJIM-10-2021-0293\/full\/html","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T23:01:21Z","timestamp":1753398081000},"score":1,"resource":{"primary":{"URL":"http:\/\/www.emerald.com\/ajim\/article\/74\/6\/1070-1088\/45703"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,22]]},"references-count":50,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,3,22]]},"published-print":{"date-parts":[[2022,9,29]]}},"alternative-id":["10.1108\/AJIM-10-2021-0293"],"URL":"https:\/\/doi.org\/10.1108\/ajim-10-2021-0293","relation":{},"ISSN":["2050-3806"],"issn-type":[{"value":"2050-3806","type":"print"}],"subject":[],"published":{"date-parts":[[2022,3,22]]}}}