Part-of-speech (POS) tagging is often used in other modules of natural language processing and therefore the results of this process should be as precise as possible. Many different types of taggers have been developed to improve the accuracy of the results in the field of literature or newspapers. Nowadays when the internet is widespread, the environments for online collaboration as chats, forums, blogs, wikis have become important means of communication. The purpose of this research is to analyse the results of tagging the words obtained from the labelling of the words from the online collaboration environments and literary texts with the corresponding parts of speech. In the case of POS tagging, the ambiguities arise due to the fact that a word may have multiple morphological values depending on context.