Social sensing with big data: Detecting hate speech in social media
Uložené v:
| Názov: | Social sensing with big data: Detecting hate speech in social media |
|---|---|
| Autori: | Umar Ibrahim, Usman Lawal Gulma, Ishaq Abdullahi Lawal |
| Zdroj: | International Journal of Science and Research Archive. 11:1146-1152 |
| Informácie o vydavateľovi: | GSC Online Press, 2024. |
| Rok vydania: | 2024 |
| Predmety: | 9. Industry and infrastructure, Communication, 4. Education, Social Sciences, Speech recognition, 16. Peace & justice, Voice activity detection, Computer science, FOS: Sociology, Data science, Social media, World Wide Web, Big data, Sociology, Artificial Intelligence, Machine Learning for Internet Traffic Classification, Speech processing, Computer Science, Physical Sciences, 8. Economic growth, Automated Detection of Hate Speech and Offensive Language, Internet privacy, The Impact of Digital Media on Public Discourse, 10. No inequality, Data mining |
| Popis: | The internet's accessibility and social media platforms, like Facebook and Twitter, have accelerated the spread of hate speech and fake news, both of which can be detrimental to society's overall well-being. Identifying and tracking hate speech is becoming increasingly difficult for the public, private citizens, legislators, and academics. Despite efforts to leverage automatic detection and monitoring techniques, their performances are still far from satisfactory. This study employs Natural Language Processing (NLP) and Machine Learning (ML) approaches to detect hate speech for decision-making. The result showed that the Support Vector Machine (SVM) algorithm has the best performance with an accuracy of 0.86 compared to the Random Forest with 0.8 accuracy. The manual evaluation of the performance of our algorithm yielded an inter-annotator agreement Cronbach’s alpha (α = .775). |
| Druh dokumentu: | Article Other literature type |
| ISSN: | 2582-8185 |
| DOI: | 10.30574/ijsra.2024.11.2.0540 |
| DOI: | 10.60692/48fs7-75946 |
| DOI: | 10.60692/zzvw6-3vq28 |
| Prístupové číslo: | edsair.doi.dedup.....4b4e03ee95152b86d6c1bd456b436292 |
| Databáza: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstrakt: | The internet's accessibility and social media platforms, like Facebook and Twitter, have accelerated the spread of hate speech and fake news, both of which can be detrimental to society's overall well-being. Identifying and tracking hate speech is becoming increasingly difficult for the public, private citizens, legislators, and academics. Despite efforts to leverage automatic detection and monitoring techniques, their performances are still far from satisfactory. This study employs Natural Language Processing (NLP) and Machine Learning (ML) approaches to detect hate speech for decision-making. The result showed that the Support Vector Machine (SVM) algorithm has the best performance with an accuracy of 0.86 compared to the Random Forest with 0.8 accuracy. The manual evaluation of the performance of our algorithm yielded an inter-annotator agreement Cronbach’s alpha (α = .775). |
|---|---|
| ISSN: | 25828185 |
| DOI: | 10.30574/ijsra.2024.11.2.0540 |