The study was presented at the 2024 International Innovation and Intellectual Technologies Conference. Developers are sure that algorithms often exceed the existing systems that are often wrong and significantly marking harmless messages.
According to the leading writer of the Akhsan Study, the growth of the number of aggressive comments on the Internet leads to serious psychological consequences, including anxiety, depression and even suicide. Despite the efforts of social platforms to limit the toxic content, manual verification is impossible due to many users.
The team tested three machine learning algorithms in English and Bengal comments collected from different social networks. The optimized version of the model showed the highest accuracy -87.6%in front of other algorithms with 69.9%and 83.4%results.
Developers plan to develop the model using neural networks and add more language support. In order to automatically filter the comments, negotiations with social platforms related to the implementation of technology are continuing.
Source: Ferra
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
