![]() Thus, in this work, we leverage recent natural language processing (NLP) techniques, including in-domain pretraining and few-shot learning, to improve emotion analysis model performance across domains in an easily adaptable framework. ![]() While recent research has led to the development of more powerful deep learning–based models and annotated datasets, these models nevertheless are prone to overfitting to shallow lexical cues and often perform poorly in new domains ( 17 – 19). Previous examinations of emotions and affect expressed in tweets about the Black Lives Matter movement have relied on lexicon (Linguistic Inquiry and Word Count, LIWC) scores ( 3), and analyses of other protest events have similarly relied on lexicon-based approaches ( 15, 16). However, measuring emotions is nontrivial, and computational models that overestimate expressions of emotions, like “anger,” can reinforce negative stereotypes. ‡ Analyzing emotions in tweets about protests can provide evidence refuting these types of negative portrayals. In the context of social movements, negative stereotypes of Black protesters as violent angry “thugs” have long been used to derail civil rights activism ( 14). For example, the “angry Black woman” stereotype can result in negative physical, social, and economic impacts, such as facilitating workplace discrimination ( 12, 13). Understanding the dynamics between emotions (such as what balance between anger and optimism produces a “hopeful anticipation of impact” that motivates continued action) can provide both insight into past movements and guidance for future efforts ( 8, 9, 11).įurthermore, projected emotions have been used to falsely characterize Black people, leading to tangible harms. In the past few decades, social psychologists have recognized the important role emotions play in activism “moral shocks” can facilitate people joining a movement, while hope and pride are necessary to sustain involvement ( 7 – 10). In this work, we analyze a dataset of tweets related to Black Lives Matter protests from 24 May to 28 June 2020 using a domain adaptation model for measuring emotions perceived in tweets about specific events. Thus, social media not only provides an avenue for analyzing modern social movements, but understanding social media messaging is also essential for providing insight into these events. While forms of “digital protest” and “hashtag activism” can occur organically, they are often a tool used by community activists who may plan hashtag campaigns, promote in-person activism, and intentionally bypass traditional media ( 1, 2, 4 – 6). In addition to #BlackLivesMatter, millions of tweets were posted with hashtags like #Ferguson, #JusticeForGeorgeFloyd, and #ICantBreathe. Social media has been an integral part of these movements. ![]() The death of George Floyd, in addition to the deaths of Ahmaud Arbery and Breonna Taylor, led to widespread protests against police violence and racism. These movements have continually grown and evolved, garnering widespread attention following the deaths of Michael Brown in Ferguson and Eric Garner in New York in 2014 ( 2, 3) and more recently, George Floyd in Minneapolis (2020). * The term has since become popularized as referring to movements against police brutality and the extrajudicial killing of Black people. The term #BlackLivesMatter originated in posts made by activists Alicia Garza and Patrisse Cullors in 2013 following George Zimmerman’s acquittal over the killing of Trayvon Martin, an unarmed Black teenager ( 1). Our work offers data, analyses, and methods to support investigations of online activism and the role of emotions in social movements. The prevalence of positivity contradicts stereotypical portrayals of protesters as primarily perpetuating anger and outrage. While our analysis identifies high levels of expressed anger and disgust across overall posts, it additionally reveals the prominence of positive emotions (encompassing, e.g., pride, hope, and optimism), which are more prevalent in tweets with explicit pro-BlackLivesMatter hashtags and correlated with on the ground protests. Instead, we use a few-shot domain adaptation approach for measuring emotions perceived in this specific domain: tweets about protests in May 2020 following the death of George Floyd. Traditional off-the-shelf emotion analysis tools often fail to generalize to new datasets and are unable to adapt to how social movements can raise new ideas and perspectives in short time spans. We use natural language processing techniques to analyze emotions expressed or solicited in tweets about 2020 Black Lives Matter protests. ![]() Emotions are a central driving force of activism they motivate participation in movements and encourage sustained involvement.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |