مشروع البحث: A RULE-BASED NORMALIZATION MODEL WITH EMBEDDING TECHNIQUES FOR BI-LSTM HATE SPEECH DETECTION MODEL
| dc.contributor.advisor | UNIVERSITI KEBANGSAAN MALAYSIA | |
| dc.date.accessioned | 2024-12-15T09:35:11Z | |
| dc.date.available | 2024-12-15T09:35:11Z | |
| dc.description | ABSTRACT The topic of identifying hate speech at scale remains unresolved despite the several strategies lately proposed in natural language processing research for detecting various types of abusive language. The challenge facing the online hate speech detection problem is that the content generated by users resorts to being noisy that may contain shorter slang words or different creative spelling. However, normalization methods have not been extensively examined in the hateful context to reduce the out-ofvocabulary (OOV) issue. Among the words used to compose social media messages are words that have repeated letters. Several techniques have been developed to normalize words with repeated letters. However | |
| dc.description.abstract | ABSTRAK Topik bagi mengenal pasti ucapan kebencian secara berskala masih tidak dapat diselesaikan walaupun beberapa strategi dicadangkan dalam penyelidikan pemprosesan bahasa tabii untuk mengesan pelbagai jenis bahasa kesat. Cabaran yang dihadapi oleh masalah pengesanan ucapan kebencian dalam talian ialah kandungan yang dijana oleh pengguna selalunya hingar yang mungkin mengandungi perkataan slanga yang lebih pendek atau ejaan kreatif yang berbeza. Walau bagaimanapun, kaedah penormalan belum diteliti secara meluas dalam konteks kebencian untuk mengurangkan isu luarperbendaharaan-kata (LPK). Antara perkataan yang digunakan untuk mengarang mesej media sosial ialah perkataan yang mempunyai huruf berulang. Beberapa teknik telah dibangunkan untuk menormalkan perkataan | |
| dc.identifier | 404 | |
| dc.identifier.uri | https://dspace.academy.edu.ly/handle/123456789/883 | |
| dc.subject | A RULE-BASED NORMALIZATION MODEL WITH EMBEDDING TECHNIQUES FOR BI-LSTM HATE SPEECH DETECTION MODEL | |
| dc.title | A RULE-BASED NORMALIZATION MODEL WITH EMBEDDING TECHNIQUES FOR BI-LSTM HATE SPEECH DETECTION MODEL | |
| dspace.entity.type | Project | |
| project.endDate | 2024 | |
| project.funder.name | الفلسفة | |
| project.investigator | ZAINAB A ALSAIED MANSUR | |
| project.startDate | 2023 | |
| relation.isOrgUnitOfProject | 5b44e99f-ae43-484b-a321-bd4eb13fa0e1 | |
| relation.isOrgUnitOfProject.latestForDiscovery | 5b44e99f-ae43-484b-a321-bd4eb13fa0e1 |