Search

Named Entity Recognition (NER), the automated identification and tagging of entities in text, is a popular natural language processing task, and has the power to transform restricted data into open datasets of entities for further research. This project benchmarks four NER models–Stanford NER, BookNLP, spaCy‐trf and RoBERTa–to identify the most accurate approach and generate an open‐access, gold‐standard dataset of human annotated entities. To meet a real‐world use case, we benchmark these models on a sample dataset of sentences from Native American authored literature, identifying edge cases and areas of improvement for future NER work. [ABSTRACT FROM AUTHOR]

We propose a bottom‐up, data‐driven pipeline to uncover the structure of biodiversity subject metadata using a combination of text mining approaches. In this study, we analyze 721,035 subject terms in the Biodiversity Heritage Library (BHL). We utilize named entity recognition and word‐embedding methods to systematically label and group terms based on their vector‐space distances. The results show that the subject terms from BHL are clustered into several prominent themes relating to environmental regulations, geographic locations, organisms, and subject access points. We hope that our approach can serve as a first step to group similar subject terms together in large‐scale, constant growing digital collections with aggregated metadata from multiple sources. Ultimately, we hope the next phases of this project can become a basis for biodiversity digital libraries to standardize their vocabularies. [ABSTRACT FROM AUTHOR]

Given the size of digital library collections and the inconsistencies in their genre‐related bibliographic metadata, as digital libraries grow and their contents are opened for computational analysis, finding materials of interest becomes a major challenge. This challenge increases for sub‐genres and other categories of text data that are less distinct from the whole. This project pilots machine learning methods and word feature analysis for identifying Black Fantastic genre texts within the HathiTrust Digital Library. These texts are sometimes referred to as "Afrofuturism" but more commonly today described as "Black Fantastic," in which African Diaspora artists and creators engage with the intersections of race and technology in their works with a primary focus on world‐building. Black Fantastic texts pose a challenge to genre classification, as they incorporate aspects of science fiction and fantasy with typical characteristics of African Diaspora‐produced literature. This paper presents and reports on results from a pilot predictive modeling process to computationally identify Black Fantastic texts using curated word feature sets for each class of data: general English‐language fiction, Black‐authored fiction, and Black Fantastic fiction. [ABSTRACT FROM AUTHOR]

The COVID‐19 pandemic has impacted all aspects of our lives, including the information spread on social media. Prior literature has found that information diffusion dynamics on social networks mirror that of a virus, but applying the epidemic Susceptible‐Infected‐Removed model (SIR) model to examine how information spread is not sufficient to claim that information spreads like a virus. In this study, we explore whether there are similarities in the simulated SIR model (SIRsim), observed SIR model based on actual COVID‐19 cases (SIRemp), and observed information cascades on Twitter about the virus (INFOcas) by using network analysis and diffusion modeling. We propose three primary research questions: (a) What are the diffusion patterns of COVID‐19 virus spread, based on SIRsim and SIRemp? (b) What are the diffusion patterns of information cascades on Twitter (INFOcas), with respect to retweets, quote tweets, and replies? and (c) What are the major differences in diffusion patterns between SIRsim, SIRemp, and INFOcas? Our study makes a contribution to the information sciences community by showing how epidemic modeling of virus and information diffusion analysis of online social media are distinct but interrelated concepts. [ABSTRACT FROM AUTHOR]

Retraction removes seriously flawed papers from the scientific literature. However, even papers retracted for scientific fraud continue to be cited and used as valid after their retraction. Retracted papers are inadequately identified on publisher pages and in scholarly databases, and scholars' personal libraries frequently contain retracted papers. To address this, we are developing a tool called ReTracker (https://github.com/nikolausn/ReTrackers) that automatically checks a user's Zotero library for retracted articles, and adds retraction status as a new metadata field directly in the library. In this paper, we present the current version of ReTracker, which automatically flags retracted articles from PubMed. We describe how we have iteratively improved ReTracker's matching performance through its initial two versions. Our tests show that the current version of ReTracker is able to flag retracted articles from PubMed with high precision and recall, and to distinguish retracted articles from articles about retraction. In its current state, ReTracker can actively and automatically bring retraction metadata into Zotero, and in future work we will test its usability with scholars. [ABSTRACT FROM AUTHOR]

Scientific retractions occur for a multitude of reasons. A growing body of research has studied the phenomenon of retraction through systematic analyses of the characteristics of retracted articles and their associated citations. In our study, we focus on the characteristics of articles that cite retracted articles, and the changes in citation dynamics pre‐ and post‐retraction. We leverage descriptive statistics and ego‐network methods to examine 4,871 retracted articles and their citations before and after retraction. Our retracted articles data was obtained from PubMed, Scopus, and Retraction Watch and their citing articles from Scopus. Our findings indicate a stark decrease in post‐retraction citations and that most of these citations came from countries different from the retracted article's country of publication. Citation context analyses of a subset of retracted articles also reveal that post‐retraction citations came from articles with disciplinary and geographical boundaries different from that of the retracted article. [ABSTRACT FROM AUTHOR]