{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T09:27:30Z","timestamp":1772270850711,"version":"3.50.1"},"reference-count":60,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T00:00:00Z","timestamp":1669334400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Trust in the government is an important dimension of happiness according to the World Happiness Report (Skelton, 2022). Recently, social media platforms have been exploited to erode this trust by spreading hate-filled, violent, anti-government sentiment. This trend was amplified during the COVID-19 pandemic to protest the government-imposed, unpopular public health and safety measures to curb the spread of the coronavirus. Detection and demotion of anti-government rhetoric, especially during turbulent times such as the COVID-19 pandemic, can prevent the escalation of such sentiment into social unrest, physical violence, and turmoil. This article presents a classification framework to identify anti-government sentiment on Twitter during politically motivated, anti-lockdown protests that occurred in the capital of Michigan. From the tweets collected and labeled during the pair of protests, a rich set of features was computed from both structured and unstructured data. Employing feature engineering grounded in statistical, importance, and principal components analysis, subsets of these features are selected to train popular machine learning classifiers. The classifiers can efficiently detect tweets that promote an anti-government view with around 85% accuracy. With an F1-score of 0.82, the classifiers balance precision against recall, optimizing between false positives and false negatives. The classifiers thus demonstrate the feasibility of separating anti-government content from social media dialogue in a chaotic, emotionally charged real-life situation, and open opportunities for future research.<\/jats:p>","DOI":"10.7717\/peerj-cs.1127","type":"journal-article","created":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T04:43:37Z","timestamp":1669351417000},"page":"e1127","source":"Crossref","is-referenced-by-count":6,"title":["An efficient approach to identifying anti-government sentiment on Twitter during Michigan protests"],"prefix":"10.7717","volume":"8","author":[{"given":"Hieu","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Swapna","family":"Gokhale","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2022,11,25]]},"reference":[{"issue":"8","key":"10.7717\/peerj-cs.1127\/ref-1","doi-asserted-by":"publisher","first-page":"516","DOI":"10.14569\/issn.2156-5570","article-title":"Detecting violent radical accounts on Twitter","volume":"11","author":"Abd-Elaal","year":"2020","journal-title":"International Journal of Advanced Computer Science and Applications"},{"key":"10.7717\/peerj-cs.1127\/ref-2","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s13673-019-0185-6","article-title":"Detection and classification of social media-based extremist affiliation using sentiment analysis techniques","volume":"9","author":"Ahmad","year":"2019","journal-title":"Human-Centric Computing and Information Sciences"},{"key":"10.7717\/peerj-cs.1127\/ref-3","doi-asserted-by":"publisher","first-page":"943","DOI":"10.48550\/arXiv.2101.03820","article-title":"An early look at the Parler online social network","volume":"15","author":"Aliapoulios","year":"2021","journal-title":"International AAAI Conference on Web and Social Media"},{"key":"10.7717\/peerj-cs.1127\/ref-4","article-title":"Protests are popping up across the US over stay-at-home restrictions","author":"Andone","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-5","doi-asserted-by":"publisher","first-page":"17877","DOI":"10.1109\/ACCESS.2020.2967219","article-title":"An approach for radicalization detection based on emotion signals and semantic similarity","volume":"8","author":"Araque","year":"2020","journal-title":"IEEE Access"},{"issue":"30","key":"10.7717\/peerj-cs.1127\/ref-6","doi-asserted-by":"publisher","first-page":"774","DOI":"10.21105\/joss.00774","article-title":"Quanteda: an R package for the quantitative analysis of textual data","volume":"3","author":"Benoit","year":"2018","journal-title":"Journal of Open Source Software"},{"key":"10.7717\/peerj-cs.1127\/ref-7","article-title":"Thousands converge to protest Michigan governor\u2019s stay-home order in Operation Gridlock","author":"Berg","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-8","article-title":"What we know about the alleged plot to kidnap Michigan\u2019s governor","author":"Bogel-Burroughs","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-9","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1038\/s42005-020-0340-4","article-title":"The role of bot squads in political propaganda on Twitter","volume":"3","author":"Caldarelli","year":"2020","journal-title":"Communications Physics"},{"key":"10.7717\/peerj-cs.1127\/ref-10","first-page":"677","article-title":"Unmasking the mask debate on social media","author":"Cerbin","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-11","article-title":"Op-Ed: the newest variant of violent extremism? Using paranoia about the pandemic as a recruiting tool","author":"Clarke","year":"2022"},{"issue":"11","key":"10.7717\/peerj-cs.1127\/ref-12","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.3390\/sym13111995","article-title":"Unmasking people\u2019s opinions behind mask-wearing during COVID-19 pandemic: a twitter stance analysis","volume":"13","author":"Cotfas","year":"2021","journal-title":"Symmetry"},{"key":"10.7717\/peerj-cs.1127\/ref-13","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1080\/17439884.2018.1544149","article-title":"Memes and symbolic violence: #proudboys and the use of memes for propaganda and the construction of collective identity","volume":"43","author":"DeCook","year":"2018","journal-title":"Learning, Media and Technology"},{"key":"10.7717\/peerj-cs.1127\/ref-14","article-title":"Recent developments in multilayer perceptron neural networks","author":"Delashmit","year":"2005"},{"key":"10.7717\/peerj-cs.1127\/ref-15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"ArXiv preprint"},{"key":"10.7717\/peerj-cs.1127\/ref-16","article-title":"Trump supporters are staging armed protests to stick it to Coronavirus","author":"Ecarma","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-17","first-page":"2487","article-title":"Identifying social media content supporting proud boys","author":"Fahim","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-18","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/s10606-021-09409-0","article-title":"Future protest made risky: examining social media based civil unrest prediction research and products","volume":"30","author":"Grill","year":"2021","journal-title":"Computer Supported Coop Work"},{"key":"10.7717\/peerj-cs.1127\/ref-19","article-title":"Political polarization over global warming: analyzing Twitter data on climate change (poster)","author":"Hajibagheri","year":"2014"},{"key":"10.7717\/peerj-cs.1127\/ref-20","article-title":"Happiness, trust and deaths under COVID-19","author":"Helliwell","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-21","article-title":"This is how a group linked to Betsy DeVos is organizing protests to end social distancing, now with Trump\u2019s support","author":"Hernandez","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-22","first-page":"216","article-title":"Vader: a parsimonious rule-based model for sentiment analysis of social media text","volume":"8","author":"Hutto","year":"2014"},{"issue":"2065","key":"10.7717\/peerj-cs.1127\/ref-23","doi-asserted-by":"publisher","first-page":"20150202","DOI":"10.1098\/rsta.2015.0202","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philosophical Transactions: Mathematical, Physical and Engineering Sciences"},{"key":"10.7717\/peerj-cs.1127\/ref-24","article-title":"Collecting Twitter data","author":"Kearney","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-25","first-page":"688","article-title":"A parsimonious and practical approach to detecting offensive speech","author":"Khan","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-26","first-page":"297","article-title":"From Twitter to Charlottesville: analyzing the fighting words between the alt-right and antifa","volume":"13","author":"Klein","year":"2019","journal-title":"International Journal of Communication"},{"issue":"3","key":"10.7717\/peerj-cs.1127\/ref-27","first-page":"18","article-title":"Classification and regression by randomForest","volume":"2","author":"Liaw","year":"2002","journal-title":"R News"},{"key":"10.7717\/peerj-cs.1127\/ref-28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.cs\/0205028","article-title":"NLTK: the natural language toolkit","author":"Loper","year":"2002","journal-title":"CoRR"},{"key":"10.7717\/peerj-cs.1127\/ref-29","article-title":"An analysis of the early dialogue on vaccine passports on Twitter","author":"Mann","year":"2022"},{"key":"10.7717\/peerj-cs.1127\/ref-30","article-title":"Protesters, some armed, enter Michigan Capitol in rally against COVID-19 limits","author":"Mauger","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-31","first-page":"3111","article-title":"Distributed Representations of Words and Phrases and Their Compositionality","volume":"2","author":"Mikolov","year":"2013"},{"key":"10.7717\/peerj-cs.1127\/ref-32","first-page":"549","article-title":"A study of radicalism contents detection in Twitter: insights from support vector machine technique","author":"Miranda","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-33","first-page":"1","article-title":"On detecting online radicalization and extremism using natural language processing","author":"Mussiraliyeva","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-34","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1007\/978-981-15-3242-9_26","article-title":"Ascent of pre-trained state-of-the-art language models","volume-title":"Advanced Computing Technologies and Applications","author":"Nagda","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-35","article-title":"The rise of digital extremism: how social media eroded America\u2019s political stability","author":"Nguyen","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-36","article-title":"A beginner\u2019s guide to word2vec and neural word embeddings","author":"Nicholson","year":"2019"},{"key":"10.7717\/peerj-cs.1127\/ref-37","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2019.2938389","article-title":"Not all lies are equal. a study into the engineering of political misinformation in the 2016 US presidential election","volume":"7","author":"Oehmichen","year":"2019","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.1127\/ref-38","first-page":"163","article-title":"Network-based group account classification","author":"Park","year":"2015"},{"key":"10.7717\/peerj-cs.1127\/ref-39","article-title":"Parler\u2014where free speech thrives","author":"Parler","year":"2022"},{"key":"10.7717\/peerj-cs.1127\/ref-40","first-page":"3220","article-title":"Analysis and classification of vaccine dialogue in the coronavirus era","author":"Paul","year":"2020"},{"issue":"Oct","key":"10.7717\/peerj-cs.1127\/ref-41","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.48550\/arXiv.1201.0490","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"Journal of Machine Learning Research"},{"key":"10.7717\/peerj-cs.1127\/ref-42","first-page":"6192","article-title":"Tracking political events in social media: a case study of Hong Kong protests","author":"Qi","year":"2019"},{"key":"10.7717\/peerj-cs.1127\/ref-43","first-page":"45","article-title":"Software framework for topic modelling with large corpora","author":"Rehurek","year":"2010"},{"key":"10.7717\/peerj-cs.1127\/ref-44","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/978-3-030-47214-6_6","article-title":"Examining the physical manifestation of alt-right gangs: from online trolling to steet fighting","volume-title":"Gangs in the Era of Internet and Social Media","author":"Reid","year":"2020"},{"key":"10.7717\/peerj-cs.1127\/ref-45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.01108","article-title":"DistilBERT, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"ArXiv preprint"},{"key":"10.7717\/peerj-cs.1127\/ref-46","first-page":"3687","article-title":"CARER: contextualized affect representations for emotion recognition","author":"Saravia","year":"2018"},{"key":"10.7717\/peerj-cs.1127\/ref-47","article-title":"The world happiness report 2022\u2014happiness is about benevolence and trust","author":"Skelton","year":"2022"},{"issue":"3","key":"10.7717\/peerj-cs.1127\/ref-48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1017\/S0003055421001507","article-title":"Why botter: how pro-government bots fight opposition in Russia","volume":"116","author":"Stukal","year":"2022","journal-title":"American Political Science Review"},{"key":"10.7717\/peerj-cs.1127\/ref-49","first-page":"293","article-title":"Sparse least squares support vector machine classifiers","author":"Suykens","year":"2000"},{"key":"10.7717\/peerj-cs.1127\/ref-50","first-page":"114","article-title":"The Flesch index: an easily programmable readability analysis algorithm","author":"Talburt","year":"1985"},{"key":"10.7717\/peerj-cs.1127\/ref-51","article-title":"Like, retweet and quote tweet: understanding the Twitterverse","author":"Tweettabs","year":"2022"},{"key":"10.7717\/peerj-cs.1127\/ref-52","article-title":"COVID-19 misleading information policy","author":"Twitter","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-53","article-title":"The use of the internet for terrorist purposes","author":"UN","year":"2012"},{"issue":"3","key":"10.7717\/peerj-cs.1127\/ref-54","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1108\/00330330610681295","article-title":"The Porter stemming algorithm: then and now","volume":"40","author":"Willett","year":"2006","journal-title":"Program Electronic Library and Information Systems"},{"key":"10.7717\/peerj-cs.1127\/ref-55","article-title":"The rightwing groups behind wave of protests against COVID-19 restrictions","author":"Wilson","year":"2020"},{"issue":"3","key":"10.7717\/peerj-cs.1127\/ref-56","doi-asserted-by":"publisher","first-page":"106646","DOI":"10.1016\/j.chb.2020.106646","article-title":"Faces of radicalism: differentiating between violent and non-violent radicals by their social media profiles","volume":"116","author":"Wolfowicz","year":"2021","journal-title":"Computers in Human Behavior"},{"issue":"1","key":"10.7717\/peerj-cs.1127\/ref-57","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/TCSS.2017.2763128","article-title":"Forecasting civil unrest using social media and protest participation theory","volume":"5","author":"Wu","year":"2018","journal-title":"IEEE Transactions on Computational Social Systems"},{"key":"10.7717\/peerj-cs.1127\/ref-58","first-page":"868","article-title":"Pos weighted tf-idf algorithm and its application for an mooc search engine","author":"Xu","year":"2014"},{"key":"10.7717\/peerj-cs.1127\/ref-59","first-page":"1","article-title":"Study of radical views on social media: classification and group dynamics analysis","author":"Yasin","year":"2021"},{"key":"10.7717\/peerj-cs.1127\/ref-60","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139088510","volume-title":"Social media mining: an introduction","author":"Zafarani","year":"2014"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-1127.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1127.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1127.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-1127.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T04:43:51Z","timestamp":1669351431000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-1127"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,25]]},"references-count":60,"alternative-id":["10.7717\/peerj-cs.1127"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.1127","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{"has-review":[{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.2\/reviews\/2","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.2\/reviews\/1","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.2\/reviews\/3","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.1\/reviews\/3","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.1\/reviews\/2","asserted-by":"object"},{"id-type":"doi","id":"10.7287\/peerj-cs.1127v0.1\/reviews\/1","asserted-by":"object"}]},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,25]]},"article-number":"e1127"}}