Browsing by Subject "Hate speech"

Now showing 1 - 2 of 2

The Brotherhood : race and gender ideologies in the white supremacist movement
(1993) Harper, Suzanne, 1961-; Feagin, Joe R.; Kurtz, Lester R.
"Race," and the ideologies surrounding this concept, have traditionally been approached as phenomena separate from gender and sexuality. This research provides insight into the construction of racist ideologies and the many ways in which gender and sexuality are integral to this project. The resurgence in the post-Civil Rights Era U.S. of the contemporary white supremacist movement provides a case study of unabashedly racist ideologies and is the focus of this dissertation. Using qualitative content analysis, I analyze 369 publications from six different white supremacist organizations. The object of the research is to examine the ways in which notions of gender and sexuality are integral to the construction of racist ideologies in the U.S. in the late 20th century. The dissertation includes a description of racist themes in white supremacist rhetoric surrounding whites, Blacks, and Jews. I conclude that the process of rearticulating "whiteness" is integral to the white supremacist project. "Race" within white supremacist rhetoric is a contested terrain, that is, "race," that which is presumably most taken-for-granted category is that which is most explained and justified within the pages of white supremacist publications. I conclude that the process of rearticulating "whiteness" is also fundamentally about reasserting hegemonic notions of gender and sexuality in a framework which privileges white, heterosexual men
Multi-task learning for hate speech detection
(2023-04-21) Lee, Sooyong; Lease, Matthew A.
Amidst the proliferation of social media and the accompanying explosion of information and content generation, the amount of online hate speech has grown rapidly. In efforts to build and train hate speech detection models to counter this, datasets have been annotated for hate speech. However, there exists incompatibility of categories of hate speech across different datasets, the lack of clear and ubiquitous definitions for hate speech, and generalization issues of models which depend highly on training data. To address this, we propose framing hate speech detection as multi-task learning (MTL) which provides a natural and principled way for a model to specialize on dataset-specific hate speech detection tasks while leveraging shared notions of hate speech across datasets to acquire more general notions of hate speech.