Amandalynne Paullada

Before the Labels: How Dataset Construction Shapes Suicidality Detection in Clinical Text

P. Garg, Ishita Rao, Jieqiong Ding, Amandalynne Paullada

Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media. We argue that this framing obscures how EHR-based suicidality datasets encode a particular operationalization of suicidality, shaped …

Before the Labels: How Dataset Construction Shapes Suicidality Detection in Clinical Text

Priyanshi Garg, Ishita Rao, Jieqiong Ding, Amandalynne Paullada

Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media. We argue that this framing obscures how EHR-based suicidality datasets encode a particular operationalization of suicidality, shaped …

us (code pays fourni par la source)

Exploring Feature Priorities and User Needs in Developing Virtual Study Assistants

Chi-shan Tsai, HyunHae Lee, Warren Szewczyk, Julia K. Palmer et autres

This formative research explored health science researchers' perspectives on the development of an artificial intelligence-based virtual study assistant and identified 8 potential features and their priorities.

us (code pays fourni par la source)

Language Justice and Machine Translation on Social Media

Amandalynne Paullada, Levon Haroutunian

Machine translation (MT), which involves the use of algorithms to translate between languages, has advanced to a high level of quality for dozens of language pairs and is employed in an array of everyday contexts, including on social media. However, there are …

us (code pays fourni par la source)

Before the Labels: How Dataset Construction Shapes Suicidality Detection in Clinical Text

Priyanshi Garg, Ishita Rao, Jieqiong Ding, Amandalynne Paullada

Clinical NLP increasingly relies on electronic health record (EHR) data to detect suicidal behaviors, treating clinical documentation as more reliable ground truth than social media.We argue that this framing obscures how EHR-based suicidality datasets encode a particular operationalization of suicidality, shaped by …

us (code pays fourni par la source)

Exploring Feature Priorities and User Needs in Developing Virtual Study Assistants (Preprint)

Chi-Shan Tsai, HyunHae Lee, Warren Szewczyk, June W. Palmer et autres

UNSTRUCTURED This formative research explored health science researchers’ perspectives on the development of an artificial intelligence–based virtual study assistant and identified 8 potential features and their priorities.

Opportunities for incorporating intersectionality into biomedical informatics

Oliver J. Bear Don’t Walk, Amandalynne Paullada, Avery Everhart, Reggie Casanova-Pérez et autres

Many approaches in biomedical informatics (BMI) rely on the ability to define, gather, and manipulate biomedical data to support health through a cyclical research-practice lifecycle. Researchers within this field are often fortunate to work closely with healthcare and public health systems to …

us, ca (code pays fourni par la source)

Text Classification

Trevor Cohen, Serguei Pakhomov, Amandalynne Paullada, Meliha Yetişgen

us (code pays fourni par la source)

Behind the Mask: Demographic bias in name detection for PII masking

Courtney Mansfield, Amandalynne Paullada, Kristen Howell

Many datasets contain personally identifiable information, or PII, which poses privacy risks to individuals. PII masking is commonly used to redact personal information such as names, addresses, and phone numbers from text data. Most modern PII masking pipelines involve machine learning algorithms. …

Behind the Mask: Demographic bias in name detection for PII masking

Courtney Mansfield, Amandalynne Paullada, Kristen Howell

Many datasets contain personally identifiable information, or PII, which poses privacy risks to individuals.PII masking is commonly used to redact personal information such as names, addresses, and phone numbers from text data.Most modern PII masking pipelines involve machine learning algorithms.However, these systems …

us (code pays fourni par la source)

An Interactive Exploratory Tool for the Task of Hate Speech Detection

Angelina McMillan-Major, Amandalynne Paullada, Yacine Jernite

With the growth of Automatic Content Moderation (ACM) on widely used social media platforms, transparency into the design of moderation technology and policy is necessary for online communities to advocate for themselves when harms occur.In this work, we describe a suite of …

us (code pays fourni par la source)

AI and the Everything in the Whole Wide World Benchmark

Inioluwa Deborah Raji, Emily M. Bender, Amandalynne Paullada, Emily Denton et autres

There is a tendency across different subfields in AI to valorize a small collection of influential benchmarks. These benchmarks operate as stand-ins for a range of anointed common problems that are frequently framed as foundational milestones on the path towards flexible and …

us (code pays fourni par la source)