A social-event based approach to sentiment analysis of identities and behaviors in text

Joseph, Kenneth; Wei, Wei; Benigni, Matthew; Carley, Kathleen M.

doi:10.1080/0022250x.2016.1159206

Cited by 19 publications

(16 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…From a methodological standpoint, we finally remark on the wide variety of tools used to further understand online hate speech dynamics. More specifically, we show how machine learning, network science methods, as well as insights from social scientific theory can be used to better understand online hate speech as it spreads ‘in the wild’ [ 45 , 63 , 76 , 80 ]. Burgeoning literature on online disinformation and social cybersecurity advocates such integrated approaches to understanding sociotechnical problems like online hate speech [ 15 , 22 , 34 ].…”

Section: Discussionmentioning

confidence: 99%

“…To determine the targets of hate speech, we employed an identity-based approach [17,50]. Past research had developed a comprehensive lexicon of identity terms which have also been made available on the Netmapper software [23,45]. Each identity term in the lexicon was further subdivided into four classes: political identities (e.g., senator, president), gendered identities (e.g., women, transgender), racial/ nationality identities (e.g., Black, Filipino), and religious identities (e.g., priest, imam).…”

Section: Identity Analysismentioning

confidence: 99%

See 1 more Smart Citation

Bots and online hate during the COVID-19 pandemic: case studies in the United States and the Philippines

Uyheng

Carley

2020

J Comput Soc Sc

Self Cite

View full text Add to dashboard Cite

Online hate speech represents a serious problem exacerbated by the ongoing COVID-19 pandemic. Although often anchored in real-world social divisions, hate speech in cyberspace may also be fueled inorganically by inauthentic actors like social bots. This work presents and employs a methodological pipeline for assessing the links between hate speech and bot-driven activity through the lens of social cybersecurity. Using a combination of machine learning and network science tools, we empirically characterize Twitter conversations about the pandemic in the United States and the Philippines. Our integrated analysis reveals idiosyncratic relationships between bots and hate speech across datasets, highlighting different network dynamics of racially charged toxicity in the US and political conflicts in the Philippines. Most crucially, we discover that bot activity is linked to higher hate in both countries, especially in communities which are denser and more isolated from others. We discuss several insights for probing issues of online hate speech and coordinated disinformation, especially through a global approach to computational social science.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Identity Analysismentioning

confidence: 99%

Bots and online hate during the COVID-19 pandemic: case studies in the United States and the Philippines

Uyheng

Carley

2020

J Comput Soc Sc

Self Cite

View full text Add to dashboard Cite

show abstract

“…More specifically, we probe how network clusters with higher levels of hate speech systematically differ from others both in terms of structural (e.g., density, echo chambers) and functional (e.g., targeting of specific identities) features (Crenshaw 1990 ; Joseph et al. 2016 ; Kim 2020 ). Taken together, our findings bear theoretical and methodological implications for the scientific study of hate speech and understanding the pandemic’s broader societal impacts both online and offline (Luengo-Oroz et al.…”

Section: Introductionmentioning

confidence: 99%

Characterizing network dynamics of online hate communities around the COVID-19 pandemic

Uyheng

Carley

2021

Appl Netw Sci

Self Cite

View full text Add to dashboard Cite

Hate speech has long posed a serious problem for the integrity of digital platforms. Although significant progress has been made in identifying hate speech in its various forms, prevailing computational approaches have tended to consider it in isolation from the community-based contexts in which it spreads. In this paper, we propose a dynamic network framework to characterize hate communities, focusing on Twitter conversations related to COVID-19 in the United States and the Philippines. While average hate scores remain fairly consistent over time, hate communities grow increasingly organized in March, then slowly disperse in the succeeding months. This pattern is robust to fluctuations in the number of network clusters and average cluster size. Infodemiological analysis demonstrates that in both countries, the spread of hate speech around COVID-19 features similar reproduction rates as other COVID-19 information on Twitter, with spikes in hate speech generation at time points with highest community-level organization of hate speech. Identity analysis further reveals that hate in the US initially targets political figures, then grows predominantly racially charged; in the Philippines, targets of hate consistently remain political over time. Finally, we demonstrate that higher levels of community hate are consistently associated with smaller, more isolated, and highly hierarchical network clusters across both contexts. This suggests potentially shared structural conditions for the effective spread of hate speech in online communities even when functionally targeting distinct identity groups. Our findings bear theoretical and methodological implications for the scientific study of hate speech and understanding the pandemic’s broader societal impacts both online and offline.

show abstract

“…While several studies have investigated how ACT could be used to evaluate different narrative forms, such as folktales, frames, retellings, and newspaper articles (Ahothali and Hoey 2015; Dunphy and MacKinnon 2002; Hunzaker 2016; Shuster and Campos-Castillo 2017), few have asked how narrative and character analysis might improve or expand concepts in affect control theory. In one extension, Joseph et al (2016) develop a model they apply to newspaper articles on the Arab uprisings that can extract social events from text and generate affective meanings for identities and behaviors not currently in ACT dictionaries. Just as models can now rely on public texts to help define EPA ratings, we can also turn to other cultural artifacts to better understand fundamental sentiments.…”

Section: Introductionmentioning

confidence: 99%

“…ACT also details the importance of a third dimension, active versus passive. Although both are cultural approaches and highlight emotions, CT comes out of the analysis of cultural products, while ACT speaks to the social psychology of individuals and their motivations (although ACT has also been applied to news texts: Ahothali and Hoey 2015; Joseph et al 2016). We can use the findings of CT to test ACT predictions for these three identities.…”

mentioning

confidence: 99%

Villains, Victims, and Heroes in Character Theory and Affect Control Theory

Bergstrand

Jasper

2018

Soc Psychol Q

View full text Add to dashboard Cite

We examine three basic tropes-villain, victim, and hero-that emerge in images, claims, and narratives. We compare recent research on characters with the predictions of an established tradition, affect control theory (ACT). Combined, the theories describe core traits of the villain-victim-hero triad and predict audiences' reactions. Character theory (CT) can help us understand the cultural roots of evaluation, potency, and activity profiles and the robustness of profile ratings. It also provides nuanced information regarding multiplicity in, and subtypes of, characters and how characters work together to define roles. Character types can be strategically deployed in political realms, potentially guiding strategies, goals, and group dynamics. ACT predictions hold up well, but CT suggests several paths for extension and elaboration. In many cases, cultural research and social psychology work on parallel tracks, with little cross-talk. They have much to learn from each other.

show abstract

A social-event based approach to sentiment analysis of identities and behaviors in text

Cited by 19 publications

References 18 publications

Bots and online hate during the COVID-19 pandemic: case studies in the United States and the Philippines

Bots and online hate during the COVID-19 pandemic: case studies in the United States and the Philippines

Characterizing network dynamics of online hate communities around the COVID-19 pandemic

Villains, Victims, and Heroes in Character Theory and Affect Control Theory

Contact Info

Product

Resources

About