University of Twente Student Theses
Analysing targets of hate speech on X in the Netherlands using BERT-CNN
Vries, R. de (2024) Analysing targets of hate speech on X in the Netherlands using BERT-CNN.
|
PDF
452kB |
| Abstract: | Hate speech poses a challenge to respect and inclusivity, impacting both individuals and society as a whole. Social media platforms like X (formerly Twitter) and Facebook have made it much easier to express hate speech (anonymously), making hate speech detection an important goal. Research on hate speech on social media platforms has been performed in other countries, especially the USA. However, research on hate speech on X in the Netherlands is minimal, focusing mainly on the effects rather than the targets. This is an important motivation: to explore this research field and provide recommendations regarding hate speech target classification models. X is a suitable platform for hate speech analysis since it is one of the most popular social media platforms mainly about giving opinions and interacting with others. There are many models which can be used to detect hate speech, but this research uses a BERT-CNN model since current research indicates that is outstanding in understanding the context of text. Hate speech identification and target prediction models have been created for the IMSyPP project, but have not been used to analyse X posts on a large scale. In this research, a model is trained on a labelled dataset from the IMSyPP project. This research analyses the targets of hate speech on X in the Netherlands, to more clearly understand hate speech in the Netherlands. This contributes to society and science since it provides insights into hate speech targets and how to train the classifying models. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Link to this item: | https://purl.utwente.nl/essays/100832 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page