{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T04:47:09Z","timestamp":1769316429697,"version":"3.49.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,5,22]],"date-time":"2022-05-22T00:00:00Z","timestamp":1653177600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,5,22]],"date-time":"2022-05-22T00:00:00Z","timestamp":1653177600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PTDC\/EEI-AUT\/28918\/2017"],"award-info":[{"award-number":["PTDC\/EEI-AUT\/28918\/2017"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soc. Netw. Anal. Min."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Online social networking platforms allow people to freely express their ideas, opinions, and emotions negatively or positively. Previous studies have examined sentiments on these platforms to study their behavior in different contexts and purposes. The mechanism of collecting public opinion information has attracted researchers to automatically classify the polarity of public opinions based on the use of concise language in messages, such as tweets, by analyzing social media data. In this paper, we extend the preceding work where an unsupervised approach to automatically detect extreme opinions\/posts in social networks is proposed. The performance of the proposed approach is evaluated on five different social network and media datasets. In this work, we use a semi-supervised approach known as BERT to reevaluate the accuracy of our prior approach and the obtained classified dataset. The experiment proves that in these datasets, posts that were previously classified as negative or positive extreme are extremely negative or positive in many cases while using BERT. Furthermore, BERT shows the capability to classify the extreme sentiments when fine-tuned with an appropriate extreme sentiments dataset.<\/jats:p>","DOI":"10.1007\/s13278-022-00882-z","type":"journal-article","created":{"date-parts":[[2022,5,22]],"date-time":"2022-05-22T10:02:19Z","timestamp":1653213739000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Detection of extreme sentiments on social networks with BERT"],"prefix":"10.1007","volume":"12","author":[{"given":"M. Luqman","family":"Jamil","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2337-0779","authenticated-orcid":false,"given":"Sebasti\u00e3o","family":"Pais","sequence":"additional","affiliation":[]},{"given":"Jo\u00e3o","family":"Cordeiro","sequence":"additional","affiliation":[]},{"given":"Ga\u00ebl","family":"Dias","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,5,22]]},"reference":[{"issue":"1","key":"882_CR1","first-page":"24","volume":"9","author":"S Ahmad","year":"2019","unstructured":"Ahmad S, Asghar MZ, Alotaibi FM, Awan I (2019) Detection and classification of social media-based extremist affiliations using sentiment analysis techniques. HCIS 9(1):24","journal-title":"HCIS"},{"key":"882_CR2","unstructured":"AZSecure-data (2013) Turn to Islam forum dataset. University of Arizona Artificial Intelligence Lab, AZSecure-data. https:\/\/www.azsecure-data.org\/dark-web-forums.html"},{"key":"882_CR3","unstructured":"Baccianella S, Esuli A, Sebastiani F (2010) Sentiwordnet 3.0: an enhanced lexical resource for sentiment analysis and opinion mining. In: LREC, vol. 10, pp 2200\u20132204"},{"key":"882_CR4","unstructured":"Becker H, Naaman M, Gravano L (2011) Selecting quality twitter content for events. In: Fifth international AAAI conference on weblogs and social media"},{"key":"882_CR5","doi-asserted-by":"publisher","first-page":"20617","DOI":"10.1109\/ACCESS.2017.2740982","volume":"5","author":"M Bouazizi","year":"2017","unstructured":"Bouazizi M, Ohtsuki T (2017) A pattern-based approach for multi-class sentiment analysis in twitter. IEEE Access 5:20617\u201320639","journal-title":"IEEE Access"},{"issue":"2","key":"882_CR6","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/MIS.2016.31","volume":"31","author":"E Cambria","year":"2016","unstructured":"Cambria E (2016) Affective computing and sentiment analysis. IEEE Intell Syst 31(2):102\u2013107. https:\/\/doi.org\/10.1109\/MIS.2016.31","journal-title":"IEEE Intell Syst"},{"key":"882_CR7","doi-asserted-by":"crossref","unstructured":"Cambria E, Poria S, Hazarika D, Kwok K (2018) Senticnet 5: discovering conceptual primitives for sentiment analysis by means of context embeddings. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11559"},{"key":"882_CR8","doi-asserted-by":"crossref","unstructured":"Cambria E, Hussain A (2015) Senticnet. In: Sentic computing. Springer, pp 23\u201371","DOI":"10.1007\/978-3-319-23654-4_2"},{"key":"882_CR9","doi-asserted-by":"publisher","unstructured":"Cambria E, Li Y, Xing FZ, Poria S, Kwok K (2020) Senticnet 6: ensemble application of symbolic and subsymbolic AI for sentiment analysis. CIKM \u201920. Association for Computing Machinery, New York, NY, USA, pp 105\u2013114 . https:\/\/doi.org\/10.1145\/3340531.3412003","DOI":"10.1145\/3340531.3412003"},{"key":"882_CR10","unstructured":"DN (2022) PJ deteve estudante que preparava atentado na Faculdade de Ci\u00eancias. https:\/\/www.dn.pt\/sociedade\/pj-deteve-jovem-com-planos-e-armas-para-atentado-numa-universidade-de-lisboa-14578423.html"},{"key":"882_CR11","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert: pre-training of deep bidirectional transformers for language understanding. In: NAACL"},{"key":"882_CR12","doi-asserted-by":"publisher","DOI":"10.1080\/17539153.2022.2032550","author":"P Dixit","year":"2022","unstructured":"Dixit P, Miller K (2022) Erasing historical violence from the study of violent extremism: memorialization of white supremacy at stone mountain, united states. Crit Stud Terror. https:\/\/doi.org\/10.1080\/17539153.2022.2032550","journal-title":"Crit Stud Terror"},{"key":"882_CR13","unstructured":"Friedrich N, Bowman TD, Stock WG, Haustein S (2015) Adapting sentiment analysis for tweets linking to scientific papers. arXiv preprint arXiv:1507.01967"},{"key":"882_CR14","unstructured":"Go A, Bhayani R, Huang L (2009) Twitter sentiment classification using distant supervision. CS224N Project Report, Stanford, vol 1, p 2009"},{"key":"882_CR15","doi-asserted-by":"crossref","unstructured":"Gon\u00e7alves P, Ara\u00fajo M, Benevenuto F, Cha M (2013) Comparing and combining sentiment analysis methods. In: Proceedings of the first ACM conference on online social networks, pp 27\u201338","DOI":"10.1145\/2512938.2512951"},{"key":"882_CR16","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. http:\/\/www.deeplearningbook.org"},{"key":"882_CR17","unstructured":"Jaki S, Smedt TD (2019) Right-wing german hate speech on twitter: analysis and automatic detection. CoRR. arXiv:1910.07518"},{"key":"882_CR18","unstructured":"Kaur A, Saini JK, Bansal D (2019) Detecting radical text over online media using deep learning. CoRR. arXiv:1907.12368"},{"key":"882_CR19","unstructured":"Krumm JS (2013) Influence of social media on crowd behavior and the operational environment. Technical report, Army Command and Geberal Staff College Fort Leavenworth KS School of $$\\ldots $$"},{"key":"882_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107643","author":"B Liang","year":"2022","unstructured":"Liang B, Su H, Gui L, Cambria E, Xu R (2022) Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks. Knowl Based Syst. https:\/\/doi.org\/10.1016\/j.knosys.2021.107643","journal-title":"Knowl Based Syst"},{"issue":"3","key":"882_CR21","first-page":"3098","volume":"5","author":"SB Mane","year":"2014","unstructured":"Mane SB, Sawant Y, Kazi S, Shinde V (2014) Real time sentiment analysis of twitter data using hadoop. IJCSIT Int J Comput Sci Inf Technol 5(3):3098\u20133100","journal-title":"IJCSIT Int J Comput Sci Inf Technol"},{"key":"882_CR22","unstructured":"Mikolov T, Chen K, Corrado G, Dean J (2013) Efficient estimation of word representations in vector space"},{"key":"882_CR23","doi-asserted-by":"publisher","unstructured":"Pais S, Tanoli IK, Albardeiro M, Cordeiro J (2020) Unsupervised approach to detect extreme sentiments on social networks. In: 2020 IEEE\/ACM international conference on advances in social networks analysis and mining (ASONAM), pp 651\u2013658 . https:\/\/doi.org\/10.1109\/ASONAM49781.2020.9381420","DOI":"10.1109\/ASONAM49781.2020.9381420"},{"key":"882_CR24","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L et al (2008) Opinion mining and sentiment analysis. Found Trends\u00ae Inf Retr 2(1\u20132):1\u2013135","DOI":"10.1561\/1500000011"},{"key":"882_CR25","doi-asserted-by":"crossref","unstructured":"Pang B, Lee L (2005) Seeing stars: exploiting class relationships for sentiment categorization with respect to rating scales. In: Proceedings of the ACL","DOI":"10.3115\/1219840.1219855"},{"key":"882_CR26","doi-asserted-by":"crossref","unstructured":"Pappagari R, \u017belasko P, Villalba J, Carmiel Y, Dehak N (2019) Hierarchical transformers for long document classification. Automatic speech recognition and understanding workshop. arXiv:1910.10781v1","DOI":"10.1109\/ASRU46091.2019.9003958"},{"key":"882_CR27","doi-asserted-by":"crossref","unstructured":"Persia F, D\u2019Auria D (2017) A survey of online social networks: challenges and opportunities. In: 2017 IEEE International Conference on Information Reuse and Integration (IRI), pp 614\u2013620 . IEEE","DOI":"10.1109\/IRI.2017.74"},{"key":"882_CR28","unstructured":"Politico (2021) Germany records highest level of right-wing extremist crime in 20 years. https:\/\/www.politico.eu\/article\/germany-records-highest-level-of-right-wing-extremist-crimes-in-20-years\/"},{"issue":"1","key":"882_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjds\/s13688-016-0085-1","volume":"5","author":"FN Ribeiro","year":"2016","unstructured":"Ribeiro FN, Ara\u00fajo M, Gon\u00e7alves P, Gon\u00e7alves MA, Benevenuto F (2016) Sentibench-a benchmark comparison of state-of-the-practice sentiment analysis methods. EPJ Data Sci 5(1):1\u201329","journal-title":"EPJ Data Sci"},{"key":"882_CR30","doi-asserted-by":"crossref","unstructured":"Ruder S, Peters ME, Swayamdipta S, Wolf T (2019) Transfer learning in natural language processing. In: Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: tutorials, pp 15\u201318","DOI":"10.18653\/v1\/N19-5004"},{"issue":"1","key":"882_CR31","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13388-014-0005-5","volume":"3","author":"JR Scanlon","year":"2014","unstructured":"Scanlon JR, Gerber MS (2014) Automatic detection of cyber-recruitment by violent extremists. Secur Inf 3(1):5","journal-title":"Secur Inf"},{"issue":"2","key":"882_CR32","first-page":"81","volume":"16","author":"I Smeureanu","year":"2012","unstructured":"Smeureanu I, Bucur C et al (2012) Applying supervised opinion mining techniques on online user reviews. Inf Econ 16(2):81\u201391","journal-title":"Inf Econ"},{"key":"882_CR33","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Xu Y, Huang X (2019) How to fine-tune bert for text classification?. In: CCL","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"882_CR34","unstructured":"Tanoli IK, Pais S (2020) A lexicon based approach to detect extreme sentiments"},{"issue":"1","key":"882_CR35","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1002\/asi.21662","volume":"63","author":"M Thelwall","year":"2012","unstructured":"Thelwall M, Buckley K, Paltoglou G (2012) Sentiment strength detection for the social web. J Am Soc Inf Sci Technol 63(1):163\u2013173. https:\/\/doi.org\/10.1002\/asi.21662","journal-title":"J Am Soc Inf Sci Technol"},{"key":"882_CR36","unstructured":"University\u00a0of Arizona Artificial Intelligence\u00a0Lab, D.H.C. AZSecure-data: Ansar1 Forum Dataset (2013)"},{"key":"882_CR37","unstructured":"VOA (2020) Germany sees right-wing extremism as top security threat. https:\/\/www.voanews.com\/a\/europe_germany-sees-right-wing-extremism-top-security-threat\/6192511.html"},{"key":"882_CR38","doi-asserted-by":"crossref","unstructured":"Vadicamo L, Carrara F, Cimino A, Cresci S, Dell\u2019Orletta F, Falchi F, Tesconi M (2017) Cross-media learning for image sentiment analysis in the wild. In: Proceedings of the IEEE international conference on computer vision, pp 308\u2013317","DOI":"10.1109\/ICCVW.2017.45"},{"key":"882_CR39","doi-asserted-by":"publisher","unstructured":"Vadicamo L, Carrara F, Cimino A, Cresci S, Dell\u2019Orletta F, Falchi F, Tesconi M (2017) Cross-media learning for image sentiment analysis in the wild. In: 2017 IEEE international conference on computer vision workshops (ICCVW), pp 308\u2013317. https:\/\/doi.org\/10.1109\/ICCVW.2017.45","DOI":"10.1109\/ICCVW.2017.45"},{"issue":"12","key":"882_CR40","doi-asserted-by":"publisher","first-page":"37","DOI":"10.23956\/ijermt.v6i12.32","volume":"6","author":"B Wagh","year":"2018","unstructured":"Wagh B, Shinde J, Kale P (2018) A twitter sentiment analysis using NLTK and machine learning techniques. Int J Emerg Res Manag Technol 6(12):37\u201344","journal-title":"Int J Emerg Res Manag Technol"},{"key":"882_CR41","unstructured":"Wu Y, Schuster M, Chen Z, Le QV, Norouzi M, Macherey W, Krikun M, Cao Y, Gao Q, Macherey K, et al (2016) Google\u2019s neural machine translation system: bridging the gap between human and machine translation. arXiv preprint arXiv:1609.08144"},{"key":"882_CR42","unstructured":"Zhang A, Lipton ZC, Li M, Smola AJ (2020) Dive into deep learning. https:\/\/d2l.ai"}],"container-title":["Social Network Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-022-00882-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13278-022-00882-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-022-00882-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T14:00:18Z","timestamp":1672668018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13278-022-00882-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,22]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["882"],"URL":"https:\/\/doi.org\/10.1007\/s13278-022-00882-z","relation":{},"ISSN":["1869-5450","1869-5469"],"issn-type":[{"value":"1869-5450","type":"print"},{"value":"1869-5469","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,22]]},"assertion":[{"value":"27 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"The authors declare that they have no known competing financial interests or personal relationships or conflicts of interest that could have appeared to influence the work reported in this paper.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The author\u2019s consent publication.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The author\u2019s consent participates.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"The authors declare that they have no known ethics issue that could have appeared to influence the work reported in this paper.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"55"}}