Suicide, Social Capital, and Hate Groups in the United States

Szendro, Brendan

doi:10.1177/00438200211053889

Cited by 5 publications

(4 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, the commons may be defined by any number of positive organizational and/or sociological outcomes, like social capital. A preliminary search shows some prior research into social capital within both organizational and societal contexts has been done (Szendro, 2021;Ozgun et al, 2022). In this context, a literature review might investigate which organizational characteristics, especially social capital, are related to this broader view of the commons.…”

Section: Recommendations For Future Researchmentioning

confidence: 99%

Social Affinity Flow Theory (SAFT) and New Insights into the Systems Archetypes of Escalation and Tragedy of the Commons

Gourdine

Morrison

2023

Journal of Behavioral and Applied Management

View full text Add to dashboard Cite

Social Affinity Flow Theory (SAFT) is a new theoretical framework based upon Constructal Law (Bejan & Zane, 2012) and explains how this law uniquely operates within human social systems, whether within small groups, non-profits, multinational corporations, or societies. We investigate the relationship between SAFT, systems thinking, and the two archetypes of Tragedy of the Commons and Escalation, two frameworks that have proven useful to leaders and decision-makers. SAFT expands the applicability of the two archetypes and uncovers new insights with implications for multiple domains of human activity, including the practice of management.

show abstract

Section: Recommendations For Future Researchmentioning

confidence: 99%

Social Affinity Flow Theory (SAFT) and New Insights into the Systems Archetypes of Escalation and Tragedy of the Commons

Gourdine

Morrison

2023

Journal of Behavioral and Applied Management

View full text Add to dashboard Cite

show abstract

“…With the rise of social media and hate speech forums online (Phadke and Mitra, 2020;Szendro, 2021) offensive language detection has become more important that ever before. Several recent works focus on characterizing various types of offensive language detection (Fortuna and Nunes, 2018;Shushkevich and Cardiff, 2019;Mishra et al, 2019;Parekh and Patel, 2017).…”

Section: Related Workmentioning

confidence: 99%

Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

Pujari¹,

Erik²,

Kulkarni³

et al. 2022

Preprint

View full text Add to dashboard Cite

As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing 'Stereotype Detection' datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et al. (2021a) show that there are significant reliability issues with the existing benchmark datasets. Annotating a reliable dataset requires a precise understanding of the subtle nuances of how stereotypes manifest in text. In this paper, we annotate a focused evaluation set for 'Stereotype Detection' that addresses those pitfalls by de-constructing various ways in which stereotypes manifest in text. Further, we present a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance on 'Stereotype Detection'. We then propose a reinforcementlearning agent that guides the multi-task learning model by learning to identify the training examples from the neighboring tasks that help the target task the most. We show that the proposed models achieve significant empirical gains over existing baselines on all the tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

Pujari¹,

Erik²,

Kulkarni³

et al. 2022

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

View full text Add to dashboard Cite

As large Pre-trained Language Models (PLMs) trained on large amounts of data in an unsupervised manner become more ubiquitous, identifying various types of bias in the text has come into sharp focus. Existing 'Stereotype Detection' datasets mainly adopt a diagnostic approach toward large PLMs. Blodgett et al. (2021a) show that there are significant reliability issues with the existing benchmark datasets. Annotating a reliable dataset requires a precise understanding of the subtle nuances of how stereotypes manifest in text. In this paper, we annotate a focused evaluation set for 'Stereotype Detection' that addresses those pitfalls by de-constructing various ways in which stereotypes manifest in text. Further, we present a multi-task model that leverages the abundance of data-rich neighboring tasks such as hate speech detection, offensive language detection, misogyny detection, etc., to improve the empirical performance on 'Stereotype Detection'. We then propose a reinforcement-learning agent that guides the multi-task learning model by learning to identify the training examples from the neighboring tasks that help the target task the most. We show that the proposed models achieve significant empirical gains over existing baselines on all the tasks.

show abstract

Suicide, Social Capital, and Hate Groups in the United States

Cited by 5 publications

References 37 publications

Social Affinity Flow Theory (SAFT) and New Insights into the Systems Archetypes of Escalation and Tragedy of the Commons

Social Affinity Flow Theory (SAFT) and New Insights into the Systems Archetypes of Escalation and Tragedy of the Commons

Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

Reinforcement Guided Multi-Task Learning Framework for Low-Resource Stereotype Detection

Contact Info

Product

Resources

About