Measurement and Conceptual Approaches to Religious Violence: The Use of Natural Language Processing to Generate Religious Violence Event-Data

Brathwaite, Robert; Park, Baekkwan

doi:10.1017/s1755048318000317

Cited by 5 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This discrimination then leads to identity conflicts in various aspects of social politics (Fleischmann & Phalet, 2016). Furthermore, the conflicts as such will be more complicated when interconnected with political interests (Brathwaite & Park, 2019).…”

Section: A Introductionmentioning

confidence: 99%

Muslim Minority in Yogyakarta: Between Social Relationship and Religious Motivation

Warsah¹,

Masduki

Imron

et al. 2019

Qijis

View full text Add to dashboard Cite

This study aimed to investigate the relationship between minority Muslim families and those of non-Muslims in Banjarasri, Kalibawang, Kulon Progo Yogyakarta; and to find out the religious diversity motivation of the Muslim families. This study used descriptive qualitative method by applying a phenomenological approach. The data were garnered using observation and interview. This study revealed that the acculturation of arts, cultures, and social community made Muslim families and non-Muslim families live side by side. The religious motivation of Muslim minority for the sake of maintaining their faith rested upon both extrinsic and intrinsic motivations. Extrinsically, it could be seen from the strong influence of the mosque administrators, the power of various religious activities to enhance religious awareness, and the solid cohesiveness of the group to strengthen as well as protect religious motivation. Intrinsically, the religious motivation of Muslims in Banjarsari was basically the effect of self-awareness by reasons of their minor position, so that such motivation yielded strong inner capacity from each Muslim family to revive and get more deeply into Islam.

show abstract

Section: A Introductionmentioning

confidence: 99%

Muslim Minority in Yogyakarta: Between Social Relationship and Religious Motivation

Warsah¹,

Masduki

Imron

et al. 2019

Qijis

View full text Add to dashboard Cite

show abstract

“…Using dictionaries to identify events has several advantages: dictionaries are technically simple to implement, easy to interpret, and very fast to run over large corpora of text. Some event types and actors are easily identified using a small number of unique patterns, making dictionaries a useful tool for custom event datasets that are narrowly focused on a small number of actors and discrete events such as military offensives in Syria (Halterman, 2019a), rebel-government violence in Chechnya (Toft and Zhukov, 2015), or communal violence in India (Brathwaite and Park, 2018).…”

Section: Limitations Of Dictionary-based Codersmentioning

confidence: 99%

PLOVER and POLECAT: A New Political Event Ontology and Dataset

Halterman¹,

Bagozzi²,

Beger³

et al. 2023

Preprint

View full text Add to dashboard Cite

POLECAT is a new global political event dataset intended to serve as the successor to the dataset produced by the DARPA Integrated Conflict Early Warning System (ICEWS) project. POLECAT's event data are machine coded from millions of multi-language international news reports and will soon cover the period 2010-to-present. These data are generated using the Next Generation Event Coder (NGEC), a new automated coder that replaces the use of extensive (and difficult to update) dictionaries with a more flexible set of expert annotations of an event's characteristics. In contrast to existing automated event coders, it uses a combination of NLP tools, transformer-based neural networks, and actor information sourced from Wikipedia. POLECAT's event data are based on an event-mode-context ontology, the Political Language Ontology for Verifiable Event Records (PLOVER), that replaces the older CAMEO ontology used in past datasets such as ICEWS and Phoenix. These innovations offer substantial improvements in the scope and accuracy of political event data in terms of the what, how, why, where, and when of domestic and international interactions. After detailing PLOVER and POLECAT, we illustrate the innovations and improvements through a preliminary comparison to the existing-ICEWS event data system.

show abstract

“…Political event extraction. Automated event extraction in social science is generally performed using dictionary methods and a set of substantively motivated event types and actor categories (Schrodt et al, 1994;Gerner et al, 2002;Boschee, 2016;Radford, 2016;Brathwaite and Park, 2018;Liang et al, 2018). Other work uses supervised learning to infer events such as conflict or cooperation (Beieler, 2016) and protests (Hanna, 2017).…”

Section: Related Workmentioning

confidence: 99%

“…How many people attend protests (Chenoweth and Lewis, 2013)? Which religious groups are engaged in violence (Brathwaite and Park, 2018)? Why do some governments try to prevent anti-minority riots while others do not (Wilkinson, 2006)?…”

Section: Introductionmentioning

confidence: 99%

Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence

Halterman¹,

Keith²,

Sarwar³

et al. 2021

Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021

View full text Add to dashboard Cite

Automated event extraction in social science applications often requires corpus-level evaluations: for example, aggregating text predictions across metadata and unbiased estimates of recall. We combine corpus-level evaluation requirements with a real-world, social science setting and introduce the INDIAPO-LICEEVENTS corpus-all 21,391 sentences from 1,257 English-language Times of India articles about events in the state of Gujarat during March 2002. Our trained annotators read and label every document for mentions of police activity events, allowing for unbiased recall evaluations. In contrast to other datasets with structured event representations, we gather annotations by posing natural questions, and evaluate off-the-shelf models for three different tasks: sentence classification, document ranking, and temporal aggregation of target events. We present baseline results from zero-shot BERT-based models fine-tuned on natural language inference and passage retrieval tasks. Our novel corpus-level evaluations and annotation approach can guide creation of similar social-science-oriented resources in the future.

show abstract

Measurement and Conceptual Approaches to Religious Violence: The Use of Natural Language Processing to Generate Religious Violence Event-Data

Cited by 5 publications

References 54 publications

Muslim Minority in Yogyakarta: Between Social Relationship and Religious Motivation

Muslim Minority in Yogyakarta: Between Social Relationship and Religious Motivation

PLOVER and POLECAT: A New Political Event Ontology and Dataset

Corpus-Level Evaluation for Event QA: The IndiaPoliceEvents Corpus Covering the 2002 Gujarat Violence

Contact Info

Product

Resources

About