Analyzing and learning the language for different types of harassment

Abstract

Disclaimer: This paper is concerned with violent online harassment. To describe the subject at an adequate level of realism, examples of our collected tweets involve violent, threatening, vulgar and hateful speech language in the context of racial, sexual, political, appearance and intellectual harassment. While these examples are shared to portray reality, readers are alerted in advance and may wish to avoid reading this material if it could cause discomfort and disagreeable response.The presence of a significant amount of harassment in user-generated content and its negative impact calls for robust automatic detection approaches. This requires the identification of different types of harassment. Earlier work has classified harassing language in terms of hurtfulness, abusiveness, sentiment, and profanity. However, to identify and understand harassment more accurately, it is essential to determine the contextual type that captures the interrelated conditions in which harassing language occurs. In this paper we introduce the notion of contextual type in harassment by distinguishing between five contextual types: (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual and (v) political. We utilize an annotated corpus from Twitter distinguishing these types of harassment. We study the context of each kind to shed light on the linguistic meaning, interpretation, and distribution, with results from two lines of investigation: an extensive linguistic analysis, and the statistical distribution of uni-grams. We then build type-aware classifiers to automate the identification of type-specific harassment. Our experiments demonstrate that these classifiers provide competitive accuracy for identifying and analyzing harassment on social media. We present extensive discussion and significant observations about the effectiveness of type-aware classifiers using a detailed comparison setup, providing insight into the role of type-dependent features.

Analysing the discursive strategies in the narratives of victims of an Egyptian sex predator: a corpus-assisted Discourse Historical approach

“…Other studies deal with cultural and linguistic perspectives on it (see Baugh, 2018;Gelfand, Fitzgerald and Drasgow, 1995;Tyler and Boxer, 1996). Recently, academic attention has been dedicated to studying the language of harassment on social media (see Hosseinmardi et al, 2015;Mangaonkar, Hayrapetian and Raje, 2015;Nobata et al, 2016;Rezvan et al, 2020). This study contributes to the last group since it deals with narratives of sexual harassment and violence published on social media, and more particularly, Instagram.…”

Metaphors and masculine language as breaking female stereotypes in dangdut songs lyrics with vulgar content

“…Aggressive language indicates outspoken, angry, and often violent social interactions with a definite purpose. Actions that cause injury or discomfort to another individual or group (Rezvan et al, 2020). Dangdut is stigmatised as obscene music that is mainly sung by female singers who enter the music industry with their glamorous beauty and sexuality, but this fact causes the commercialisation of dangdut in the industry (Sazzed, 2021).…”

Defining and Detecting Toxicity on Social Media: Context and Knowledge are Key

“…More sophisticated analyses employ lexicons specific to intelligence, appearance, race, sexual preference etc. [7]. Keyword based content analysis encounters a number of challenges.…”

“…As the context is crucial in capturing harassment, it will change based on the linguistic meaning, interpretation, and distribution. In [7] we offered more dimensions of harassment including; (i) sexual, (ii) racial, (iii) appearance-related, (iv) intellectual, and (v) political content, and created a type-aware lexicon and annotated dataset [41]. Then we employed a multi-class classification algorithm based on these five dimensions.…”