University of Twente Student Theses
Toxic comment classification in discord
Magzoub, Z. (2023) Toxic comment classification in discord.
|
PDF
611kB |
| Abstract: | In March 2020, the COVID-19 pandemic forced educational institutions to close their campuses and move all educational activities to online education. In addition, social media platforms were the leading platforms for communication between people. While it was easier to shift to online lectures, one aspect that took more work to deal with was student-student communication. In offline education, students interact in a real-life environment where students can ask questions and receive feedback more efficiently. In order to achieve better online education, educational institutions have decided to use the platforms the students are familiar with, Discord being one of these popular platforms. However, sharing toxic comments is hard to control in Discord since there is no feature in Discord to detect toxicity in shared messages. In this paper, various machine learning models were trained to classify toxic messages shared on University's discord servers. Machine learning-based solutions were used because they can achieve better results than traditional rule-based approaches. |
| 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/94373 |
| 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