{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T12:11:35Z","timestamp":1772885495540,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T00:00:00Z","timestamp":1745452800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Detecting hate speech in social media is challenging due to its rarity, high-dimensional complexity, and implicit expression via sarcasm or spelling variations, rendering linear models ineffective. In this study, the SVM (Support Vector Machine) algorithm is used to map text features from low-dimensional to high-dimensional space using kernel function techniques to meet complex nonlinear classification challenges. By maximizing the category interval to locate the optimal hyperplane and combining nuclear techniques to implicitly adjust the data distribution, the classification accuracy of hate speech detection is significantly improved. Data collection leverages social media APIs (Application Programming Interface) and customized crawlers with OAuth2.0 authentication and keyword filtering, ensuring relevance. Regular expressions validate data integrity, followed by preprocessing steps such as denoising, stop-word removal, and spelling correction. Word embeddings are generated using Word2Vec\u2019s Skip-gram model, combined with TF-IDF (Term Frequency\u2013Inverse Document Frequency) weighting to capture contextual semantics. A multi-level feature extraction framework integrates sentiment analysis via lexicon-based methods and BERT for advanced sentiment recognition. Experimental evaluations on two datasets demonstrate the SVM model\u2019s effectiveness, achieving accuracies of 90.42% and 92.84%, recall rates of 88.06% and 90.79%, and average inference times of 3.71 ms and 2.96 ms. These results highlight the model\u2019s ability to detect implicit hate speech accurately and efficiently, supporting real-time monitoring. This research contributes to creating a safer online environment by advancing hate speech detection methodologies.<\/jats:p>","DOI":"10.3390\/info16050344","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T08:08:41Z","timestamp":1745482121000},"page":"344","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Hate Speech Detection and Online Public Opinion Regulation Using Support Vector Machine Algorithm: Application and Impact on Social Media"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4654-6486","authenticated-orcid":false,"given":"Siyuan","family":"Li","sequence":"first","affiliation":[{"name":"Propaganda Department, Ningbo College of Health Sciences, Ningbo 315000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Li","sequence":"additional","affiliation":[{"name":"School of Media and Law, NingboTech University, Ningbo 315000, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,4,24]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1177\/1527476420982230","article-title":"Racism, hate speech, and social media: A systematic review and critique","volume":"22","author":"Farkas","year":"2021","journal-title":"Telev. New Media"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"66","DOI":"10.1080\/19331681.2019.1702607","article-title":"Detecting weak and strong Islamophobic hate speech on social media","volume":"17","author":"Vidgen","year":"2020","journal-title":"J. Inf. Technol. Politics"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1080\/1369118X.2021.1942955","article-title":"Social media hate speech in the walk of Ethiopian political reform: Analysis of hate speech prevalence, severity, and natures","volume":"26","author":"Chekol","year":"2023","journal-title":"Inf. Commun. Soc."},{"key":"ref_4","first-page":"1","article-title":"Textual analysis of select social media hate speech messages against clergymen in Nigeria","volume":"7","author":"Asemah","year":"2022","journal-title":"GVU J. Manag. Soc. Sci."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1108\/JICES-11-2022-0098","article-title":"The eradication of hate speech on social media: A systematic review","volume":"21","year":"2023","journal-title":"J. Inf. Commun. Ethics Soc."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1109\/MIC.2020.3037034","article-title":"HateClassify: A service framework for hate speech identification on social media","volume":"25","author":"Khan","year":"2020","journal-title":"IEEE Internet Comput."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1963","DOI":"10.1007\/s00530-020-00742-w","article-title":"Detection of hate speech in Arabic tweets using deep learning","volume":"28","year":"2022","journal-title":"Multimedia Syst."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"4335","DOI":"10.1016\/j.jksuci.2022.05.006","article-title":"BiCHAT: BiLSTM with deep CNN and hierarchical attention for hate speech detection","volume":"34","author":"Khan","year":"2022","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1186\/s40537-022-00628-w","article-title":"Comparative analysis of deep learning based Afaan Oromo hate speech detection","volume":"9","author":"Ganfure","year":"2022","journal-title":"J. Big Data"},{"key":"ref_10","first-page":"2115","article-title":"cyberbullying-related hate speech detection using shallow-to-deep learning","volume":"74","author":"Sultan","year":"2023","journal-title":"Comput. Mater. Contin."},{"key":"ref_11","first-page":"619","article-title":"Detecting hate speech using deep learning techniques","volume":"12","author":"Paul","year":"2021","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Kan, H., Zhang, T., and Li, Y. (2020). DU KMSVM: A framework of deep uniform kernel mapping support vector machine for short text classification. Appl. Sci., 10.","DOI":"10.3390\/app10072348"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"269","DOI":"10.32672\/jnkti.v5i2.4193","article-title":"Klasifikasi Berita Menggunakan Metode Support Vector Machine","volume":"5","author":"Nanda","year":"2022","journal-title":"J. Nas. Komputasi dan Teknol. Inf. (JNKTI)"},{"key":"ref_14","first-page":"158","article-title":"Sentiment analysis of user reviews on COVID-19 information applications using naive bayes classifier, Support Vector Machine, and K-Nearest Neighbor","volume":"6","author":"Salma","year":"2021","journal-title":"Int. Res. J. Adv. Eng. Sci."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Alkomah, F., and Ma, X. (2022). A literature review of textual hate speech detection methods and datasets. Information, 13.","DOI":"10.14569\/IJACSA.2022.01308100"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1007\/s00607-019-00745-0","article-title":"Automatic hate speech detection using killer natural language processing optimizing ensemble deep learning approach","volume":"102","author":"Tolba","year":"2020","journal-title":"Computing"},{"key":"ref_17","first-page":"001","article-title":"Trends in machine learning on automatic detection of hate speech on social media platforms: A systematic review","volume":"7","author":"Simon","year":"2022","journal-title":"FUW Trends Sci. Technol. J."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1177\/0165551520917651","article-title":"Intelligent detection of hate speech in Arabic social network: A machine learning approach","volume":"47","author":"Aljarah","year":"2021","journal-title":"J. Inf. Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1007\/s10772-024-10116-6","article-title":"Automatic hate speech detection in audio using machine learning algorithms","volume":"27","author":"Imbwaga","year":"2024","journal-title":"Int. J. Speech Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/IJDSST.286680","article-title":"Hate speech detection using text mining and machine learning","volume":"14","author":"Alaoui","year":"2022","journal-title":"Int. J. Decis. Support Syst. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3734","DOI":"10.11591\/ijece.v10i4.pp3734-3742","article-title":"Text classification based on gated recurrent unit combines with support vector machine","volume":"10","author":"Zulqarnain","year":"2020","journal-title":"Int. J. Electr. Comput. Eng. (IJECE)"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"129","DOI":"10.30998\/string.v6i2.10133","article-title":"Penerapan Algoritma Support Vector Machine (SVM) dengan TF-IDF N-Gram untuk Text Classification","volume":"6","author":"Arifin","year":"2021","journal-title":"STRING (Satuan Tulisan Ris. dan Inov. Teknol."},{"key":"ref_23","first-page":"178","article-title":"Persian Text classification using naive bayes algorithms and support vector machine algorithm","volume":"8","author":"Rezaeian","year":"2020","journal-title":"Indones. J. Electr. Eng. Informatics (IJEEI)"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"109","DOI":"10.13057\/ijas.v3i2.44337","article-title":"Implementasi Text Mining Pada Analisis Sentimen Pengguna Twitter Terhadap Marketplace di Indonesia Menggunakan Algoritma Support Vector Machine","volume":"3","author":"Agustina","year":"2021","journal-title":"Indones. J. Appl. Stat."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"20614","DOI":"10.1007\/s10489-023-04590-9","article-title":"An integrated approach implementing sliding window and DTW distance for time series forecasting tasks","volume":"53","author":"Tao","year":"2023","journal-title":"Appl. Intell."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kulanuwat, L., Chantrapornchai, C., Maleewong, M., Wongchaisuwat, P., Wimala, S., Sarinnapakorn, K., and Boonya-Aroonnet, S. (2021). Anomaly detection using a sliding window technique and data imputation with machine learning for hydrological time series. Water, 13.","DOI":"10.3390\/w13131862"},{"key":"ref_27","first-page":"71","article-title":"Entity extraction based on the combination of information entropy and TF-IDF","volume":"15","author":"Yilahun","year":"2023","journal-title":"Int. J. Reason. Intell. Syst."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"2780","DOI":"10.11591\/eei.v10i5.3157","article-title":"Performance comparison of TF-IDF and Word2Vec models for emotion text classification","volume":"10","author":"Cahyani","year":"2021","journal-title":"Bull. Electr. Eng. Inform."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"37979","DOI":"10.1007\/s11042-023-17007-z","article-title":"A detailed review on word embedding techniques with emphasis on word2vec","volume":"83","author":"Johnson","year":"2024","journal-title":"Multimedia Tools Appl."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.1007\/s00521-020-04725-w","article-title":"A deep learning analysis on question classification task using Word2vec representations","volume":"32","author":"Yilmaz","year":"2020","journal-title":"Neural Comput. Appl."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"40","DOI":"10.4018\/IJDCF.20210701.oa4","article-title":"A big data text coverless information hiding based on topic distribution and TF-IDF","volume":"13","author":"Qin","year":"2021","journal-title":"Int. J. Digit. Crime Forensics"},{"key":"ref_32","first-page":"976","article-title":"The effect of the TF-IDF algorithm in times series in forecasting word on social media","volume":"22","author":"Lubis","year":"2021","journal-title":"Indones. J. Electr. Eng. Comput. Sci."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"27","DOI":"10.56471\/slujst.v4i.266","article-title":"Sentiment classification: Review of text vec-torization methods: Bag of words, Tf-Idf, Word2vec and Doc2vec","volume":"4","author":"Abubakar","year":"2022","journal-title":"SLU J. Sci. Technol."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"225","DOI":"10.30595\/juita.v10i2.13262","article-title":"Emotional text classification using TF-IDF (term frequency-inverse document frequency) and LSTM (long short-term memory)","volume":"10","author":"Alfarizi","year":"2022","journal-title":"JUITA J. Inform."},{"key":"ref_35","first-page":"1181","article-title":"Implementation of TF-IDF method and support vector machine algorithm for job applicants text classification","volume":"4","author":"Luthfi","year":"2020","journal-title":"J. Media Inform. Budidarma"}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/344\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:20:47Z","timestamp":1760030447000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/16\/5\/344"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,24]]},"references-count":35,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,5]]}},"alternative-id":["info16050344"],"URL":"https:\/\/doi.org\/10.3390\/info16050344","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,24]]}}}