Curatr: A Platform for Semantic Analysis and Curation of Historical Literary Texts

Leavy, Susan; Meaney, Gerardine; Wade, Karen; Greene, Derek

doi:10.1007/978-3-030-36599-8_31

Cited by 6 publications

(3 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given that early studies of bias in the representation of women focused study of literature, we analyse a set of over 16,000 volumes of 19th-century fiction from the British Library Digital corpus [15]. This corpus was selected due to the well-documented evidence of stereotypical and binary concepts of gender in 19th-century fiction [13], and therefore represents a useful source of baseline data, allowing methods to be tested and refined, and subsequently generalised to other corpora.…”

Section: Methodsmentioning

confidence: 99%

Mitigating Gender Bias in Machine Learning Data Sets

Leavy¹,

Meaney²,

Wade³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Algorithmic bias has the capacity to amplify and perpetuate societal bias, and presents profound ethical implications for society. Gender bias in algorithms has been identified in the context of employment advertising and recruitment tools, due to their reliance on underlying language processing and recommendation algorithms. Attempts to address such issues have involved testing learned associations, integrating concepts of fairness to machine learning, and performing more rigorous analysis of training data. Mitigating bias when algorithms are trained on textual data is particularly challenging given the complex way gender ideology is embedded in language. This paper proposes a framework for the identification of gender bias in training data for machine learning. The work draws upon gender theory and sociolinguistics to systematically indicate levels of bias in textual training data and associated neural word embedding models, thus highlighting pathways for both removing bias from training data and critically assessing its impact in the context of search and recommender systems.

show abstract

Section: Methodsmentioning

confidence: 99%

Mitigating Gender Bias in Machine Learning Data Sets

Leavy¹,

Meaney²,

Wade³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The platform provides a text mining workflow. It "combines neural word embeddings with expert domain knowledge to enable the generation of thematic lexicons, allowing researchers to curate relevant sub-corpora from a large corpus" [36].…”

Section: Related Workmentioning

confidence: 99%

“…With regard to key-phrase extraction and lexicons, compared to Curatr [36] which base the lexicons on word semantic similarities, in PREVISION, we opted for Yake [22] algorithm which is state of the art.…”

mentioning

confidence: 99%

Instruments and Tools to Identify Radical Textual Content

Mothe

Ullah

Okon³

et al. 2022

Information

View full text Add to dashboard Cite

The Internet and social networks are increasingly becoming a media of extremist propaganda. On homepages, in forums or chats, extremists spread their ideologies and world views, which are often contrary to the basic liberal democratic values of the European Union. It is not uncommon that violence is used against those of different faiths, those who think differently, and members of social minorities. This paper presents a set of instruments and tools developed to help investigators to better address hybrid security threats, i.e., threats that combine physical and cyber attacks. These tools have been designed and developed to support security authorities in identifying extremist propaganda on the Internet and classifying it in terms of its degree of danger. This concerns both extremist content on freely accessible Internet pages and content in closed chats. We illustrate the functionalities of the tools through an example related to radicalisation detection; the data used here are just a few tweets, emails propaganda, and darknet posts. This work was supported by the EU granted PREVISION (Prediction and Visual Intelligence for Security Intelligence) project.

show abstract