Using artificial ıntelligence algorithms to detect hate speech in social media posts
| dc.contributor.author | Yerden, Aytaç Uğur | |
| dc.contributor.author | Turgut, Kadir | |
| dc.date.accessioned | 2025-02-09T14:32:52Z | |
| dc.date.available | 2025-02-09T14:32:52Z | |
| dc.date.issued | 2024 | |
| dc.department | Fakülteler, Mühendislik Fakültesi, Endüstri Mühendisliği Bölümü | |
| dc.description.abstract | Detecting hate speech on social media is of great importance to prevent negative impacts on people and communities and to remove such content. However, detecting hate speech is a complex and challenging process due to linguistic and cultural diversity. Therefore, it is important to develop powerful and effective machine learning algorithms. Since detecting such content using traditional methods can be time-consuming and costly, it is stated that artificial intelligence-based machine learning algorithms have great potential in this regard. The aim of this study is to evaluate the performance of artificial intelligence-based machine learning algorithms used in detecting posts containing hate speech on social media. The study focuses on the problem of detecting and managing hate speech on social media platforms. In this study, we will compare the performances of different algorithms and determine the most suitable methods. Additionally, the effects of the dataset and feature extraction methods on algorithm performance will be analyzed. Algorithms are often based on natural language processing techniques and try to detect hate speech by learning features in texts. The performance of these algorithms can vary depending on factors such as language, culture, the attributes they use, and the training dataset, so a comprehensive analysis is required. In the research, the performance of the algorithms used in detecting hate speech was compared with the dataset and feature extraction methods. In this process, the algorithms' linguistic and cross-cultural effectiveness, feature selection and representation, false positive and false negative rates, and overall accuracy will be analyzed. | |
| dc.identifier.doi | 10.61150/ijonfest.2024020102 | |
| dc.identifier.endpage | 16 | |
| dc.identifier.issn | 3023-4379 | |
| dc.identifier.issue | 1 | |
| dc.identifier.startpage | 8 | |
| dc.identifier.uri | https://hdl.handle.net/11501/1636 | |
| dc.identifier.uri | https://doi.org/10.61150/ijonfest.2024020102 | |
| dc.identifier.volume | 2 | |
| dc.institutionauthor | Yerden, Aytaç Uğur | |
| dc.institutionauthorid | 0000-0002-3886-802X | |
| dc.language.iso | en | |
| dc.publisher | Istanbul Gedik University | |
| dc.relation.ispartof | International Journal of New Findings in Engineering, Science and Technology | |
| dc.relation.publicationcategory | Makale - Ulusal Hakemli Dergi - Kurum Öğretim Elemanı | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.snmz | KA_DergiPark_20250209 | |
| dc.subject | Social Media | |
| dc.subject | Hate Speech | |
| dc.subject | Artificial Intelligence | |
| dc.title | Using artificial ıntelligence algorithms to detect hate speech in social media posts | |
| dc.type | Article |
Dosyalar
Orijinal paket
1 - 1 / 1
