Expressively vulgar : the socio-dynamics and intentionality of vulgarity and its effects on sentiment analysis in social media




Holgate, Eric Stephen

Journal Title

Journal ISSN

Volume Title



Vulgarity is a common linguistic expression and is used to perform a diverse array of linguistic functions. Understanding its usage can aid in exploring of both linguistic and psychological phenomena as well as benefit downstream natural language processing applications such as sentiment analysis. This report presents a large-scale, data-driven empirical analysis of vulgar words using social media data. We analyze the socio-cultural and pragmatic aspects of vulgarity using tweets from users with known demographic information. Further, we collect sentiment ratings and intentionality annotations for vulgar tweets. We use these to study the relationship between the use of vulgar words and the perceived sentiment of the expression and show that explicitly modeling vulgar words can boost sentiment analysis performance. We also present a baseline vulgar intentionality classification system



LCSH Subject Headings