Analysing the controversial social media community

Abstract

We can learn most of the information we need about the world by reading unstructured text on the internet. The role of artificial intelligence is to understand this text and correctly understand it, categorize it, and make the correct system response. Texts in languages like English, which is spoken by most of the world, have their own trained tools. These models are fairly good at determining things like part of speech, sentence structure, and the like. If we want to teach artificial intelligence to recognize even minority languages, we run into a problem. In our case, we chose Slovak as the minority language. In the previous article, we reported on the misidentification of word types by the available tools. In this paper, we have significantly improved the identification of words in the second place. We plan to continue the development of Slovak-optimized software.