2019/04/08 by Anjalie Field, Field, Anjalie, Gayatri Bhat +3
Computer Science · #Hate Speech and Cyberbullying Detection #Sentiment Analysis and Opinion Mining
paper · pdf · doi:10.48550/arxiv.1904.04164
In October 2017, numerous women accused producer Harvey Weinstein of sexual\nharassment. Their stories encouraged other women to voice allegations of sexual\nharassment against many high profile men, including politicians, actors, and\nproducers. These events are broadly referred to as the #MeToo movement, named\nfor the use of the hashtag "#metoo" on social media platforms like Twitter and\nFacebook. The movement has widely been referred to as "empowering" because it\nhas amplified the voices of previously unheard women over those of\ntraditionally powerful men. In this work, we investigate dynamics of sentiment,\npower and agency in online media coverage of these events. Using a corpus of\nonline media articles about the #MeToo movement, we present a contextual\naffective analysis---an entity-centric approach that uses contextualized\nlexicons to examine how people are portrayed in media articles. We show that\nwhile these articles are sympathetic towards women who have experienced sexual\nharassment, they consistently present men as most powerful, even after sexual\nassault allegations. While we focus on media coverage of the #MeToo movement,\nour method for contextual affective analysis readily generalizes to other\ndomains.\n