Posts with defamatory content or hate speech are constantly found
on social media. The results for readers are numerous, not restricted
only to the psychological impact, but also to the growth of this
social phenomenon. With the General Law on the Protection of
Personal Data and the Marco Civil da Internet, service providers
became responsible for the content in their platforms. Considering
the importance of this issue, this paper aims to analyze the content
published (news and comments) on the G1 News Portal with techniques
based on data visualization and Natural Language Processing,
such as sentiment analysis and topic modeling. The results show
that even with most of the comments being neutral or negative and
classified or not as hate speech, the majority of them were accepted
by the users.