Sentiment analysis methods for politics and hate speech contents in Spanish language: a systematic review

Abstract

The political debate in social networks, and its derivatives such as hate speech, has surfaced at the top of the social agenda due to its impact on public opinion and, consequently, in the communication strategies of political parties, public institutions, media corporations, and lobbies. The scientific community has been working to respond to the demand for tools that allow studying the political attitude of citizens in these networks, focusing on sentiment analysis methodologies. However, their work has been hampered by several significant challenges, such as the absence of standardized investigation methodologies, the filtering of content created by bots and spammers, or the interpretation of slang and other conventionalisms that are specific to microblogging platforms. In addition to these challenges and the generic problems related to the interpretation of human language, researchers from the Spanish-speaking community have found themselves with the additional problem of developing strategies and methodologies suitable for Spanish text, in a scenario dominated by research aimed at the English language. In this paper, we present a systematic review that describes the state of the art in sentiment analysis methods for politics and hate speech contents in the Spanish language, by systematically reviewing the relevant papers available.