CSDE Computational Demography Working Group (CDWG) Hosts Jiahui Xu on New Natural Language Processing Models for Automated Coding (5/15/2024)
On 5/15 from 9:00 AM – 10:00 AM, CDWG will host Jiahui Xu to present her research. Jiahui Xu is a Ph.D. candidate in Sociology and Demography at Pennsylvania State University. Her research interests lie in social inequality, quantitative methodology, and computational sociology. Her actively ongoing projects include: 1). adapting the generalized random forests for causal decomposition to investigate college returns; 2). combining machine learning and causal inference methods to decompose health disparities; 3). applying natural language processing models to autocode occupational text data. The event will occur in 223 Raitt (the Demography Lab) and on Zoom (register here). Learn more about the talk in the full story.
Title: From Job Descriptions to Occupations: New Natural Language Processing Models for Automated Coding
Abstract: Occupation is a fundamental concept in social and policy research, but classifying job descriptions into occupational categories can be challenging and susceptible to errors. Traditionally, this involved expert manual coding, translating detailed, often ambiguous job descriptions to standardized categories, a process both laborious and costly. However, recent advances in computational techniques offer efficient automated coding alternatives. Existing autocoding tools, including the O*NET-SOC AutoCoder, the NIOCCS AutoCoder, and the SOCcer AutoCoder, rely on supervised machine learning methods and string-matching algorithms. Yet these autocoders are not designed to understand semantic meanings in occupational write-in text. We develop a new autocoder based on Google’s Text-to-Text Transfer Transformer (T5) model. Like GPT and other large language models, T5 is pretrained on vast amounts of text data. We develop a T5-based occupational classifier (T5-OCC) model with fine-tuned model parameters and training data from occupation write-ins from the 2019 American Community Survey. By comparing our T5-OCC with existing methods, we show that the autocoding accuracy rate increases from 61.8% to 71.1%. Considering the rapid change in neural language models, we conclude by offering suggestions on how to adapt our method for the development of occupational autocoding models in future research.
*Deadline Extended* Call for Papers: Demystifying Machine Learning for Population Researchers
*New* CSDE Computational Demography Working Group (CDWG) Hosts Jiahui Xu on New Natural Language Processing Models for Automated Coding
Kenworthy Authors New Book on the True Cost of Crowdfunding Healthcare
CSDE Affiliate Nora Kenworthy (Nursing and Health Studies, UW Bothell) authored a new book, entitled Crowded Out: The True Costs of Crowdfunding Healthcare. This book is the culmination of a decade’s worth of research examining the rising popularity of charitable crowdfunding for health and social needs. Although crowdfunding has become ubiquitous, it is often misunderstood: rather than a friendly free market “powered by the kindness” of strangers, crowdfunding is powerfully reinforcing inequalities and changing the way Americans think about and access healthcare. Crowded Out demonstrates how crowdfunding for health is fueled by—and further reinforces—financial and moral “toxicities” in market-based healthcare systems. It offers a unique and distressing look beneath the surface of some of the most popular charitable platforms and helps to foster thoughtful discussions of how we can better respond to healthcare crises and support each other in a digital world. Dr. Kenworthy will also be discussing the book at Town Hall Seattle on May 28th. Learn more and get tickets here.
*New* Senior Policy Analyst Focused on Fiscal Policy
Martin and Colleagues Discuss the Intersection Between Civil and Criminal Law
CSDE Affiliate Karin D. Martin (Evans School of Public Policy & Governance) released an essay with colleagues in Punishment and Society, entitled “Access to justice at the intersection of civil and criminal law“. Martin’s essay is part of a special issue of the journal focused on Access to Justice that she co-edited with Kathryne Young at The George Washington University Law School and Sarah Lageson at Rutgers University. Most people in the criminal legal justice system are also dealing with civil legal issues, creating unique consequences. Yet, there is a scholarly separation between criminal and civil law, meaning that this criminal-civil nexus remains understudied. In this essay, authors discuss the root of this separation and the importance of research on interactions between the criminal and civil legal systems.
Research by Berridge and Turner is Featured in an Article by Nature
An article in Nature, titled “Are robots the solution to the crisis in older-person care?“, recently cited two research articles by CSDE Affiliate Clara Berridge (Social Work). One of these articles was first-authored by CSDE Trainee Natalie Turner (Social Work). AI robots are increasingly employed in eldercare to provide social therapy for individuals with dementia. However, the evidence of their worth is not well developed and there are ethical concerns, including deception with speaking robots and the potential to reduce opportunities for human interactions. Berridge was interviewed for the article, where she discussed her research on older people’s perspectives regarding these robots (she is misidentified as an ethicist).