A5005046138- Artificial Intelligence in Healthcare and Education
- Hate Speech and Cyberbullying Detection
- Topic Modeling
- Geriatric Care and Nursing Homes
- Social Media and Politics
- Frailty in Older Adults
- Adversarial Robustness in Machine Learning
- Employment and Welfare Studies
- Online Learning and Analytics
- Workplace Health and Well-being
- Vaccine Coverage and Hesitancy
- Sentiment Analysis and Opinion Mining
- Misinformation and Its Impacts
- Health Literacy and Information Accessibility
- Computational and Text Analysis Methods
- COVID-19 Pandemic Impacts
- Explainable Artificial Intelligence (XAI)
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Occupational Health and Safety Research
- Patient Satisfaction in Healthcare
- Emergency and Acute Care Studies
- Scientific Computing and Data Management
- Dementia and Cognitive Impairment Research
- Ethics and Social Impacts of AI
University of Michigan
2022-2024
Brown University
2021-2022
University of California, Los Angeles
2020-2021
Nursing staff turnover has long been considered an important indicator of nursing home quality. However, never reported on the Home Compare website, likely because lack adequate data. On July 1, 2016, Centers for Medicare and Medicaid Services began collecting auditable payroll-based daily staffing data US homes. We used 492 million nurse shifts from these to calculate a novel metric representing percentage hours care that turned over annually at each 15,645 facilities. Mean median annual...
Abstract As the COVID‐19 pandemic has unfolded, Hate Speech on social media about China and Chinese people encouraged stigmatization. For historical humanistic purposes, this history‐in‐the‐making needs to be archived analyzed. Using query “china+and+coronavirus” scrape from Twitter API, we have obtained 3,457,402 key tweets relating COVID‐19. In archive, in which 40% of are U.S., identify 25,467 occurrences analyze them according lexicon‐based emotions demographics using machine learning...
Abstract Objective To describe the association between nursing home staff turnover and presence scope of infection control citations. Data Sources Secondary data for all US homes March 31, 2017, through December 2019 were obtained from Payroll‐Based Journal (PBJ), Nursing Home Compare, Long‐Term Care: Facts on Care in (LTC Focus). Study Design We estimated nurse probability an citation while controlling fixed effects. Our measure is percent facility's hours that provided by new (less than 60...
The rapid advancements in generative AI models present new opportunities the education sector. However, it is imperative to acknowledge and address potential risks concerns that may arise with their use. We analyzed Twitter data identify key related use of ChatGPT education. employed BERT-based topic modeling conduct a discourse analysis social network influential users conversation. While generally ex-pressed positive attitude towards ChatGPT, converged five specific categories: academic...
Abstract On March 16, 2021, six Asian women were killed in Atlanta, US, possibly out of racist motivations. This tragic event, now known as the 2021 Atlanta Spa Shootings, precipitated a massive increase volume counter‐anti‐Asian declarations and discussion on social media platforms such Twitter. In pilot study to chronicle profile public opinions, movements patterns global Twitter discourse we scraped API using query term “StopAsianHate”, obtaining more than 5.5 million tweets their...
Simulated patient systems play a crucial role in modern medical education and research, providing safe, integrative learning environments enabling clinical decision-making simulations. Large Language Models (LLM) could advance simulated by replicating conditions patient-doctor interactions with high fidelity low cost. However, ensuring the effectiveness trustworthiness of these remains challenge, as they require large, diverse, precise knowledgebase, along robust stable knowledge diffusion...
Prior studies indicate that older members of LGBTQ+ communities have specific health provision and information needs related to coping with COVID-19, its long-term effects, the social economic impact pandemic. This study addresses issue a lack timely, complete, high-quality data about this population's healthcare behaviors. Recognizing also is diverse population made up multiple identities different concerns experiences, research seeks develop refine method can provide additional nuanced...
This paper reports on a study using machine learning to identify incidences and shifting dynamics of hate speech in social media archives. To better cope with the archival processing need for such large scale fast evolving archives, we propose Data-driven Circulating Archival Processing (DCAP) method. As proof-of-concept, our focuses an English language Twitter archive relating COVID-19: tweets were repeatedly scraped between February June 2020, ingested aggregated within COVID-19 Hate...
Addressing increasing calls to surface hidden and counter-narratives from within archival collections, this paper reports on a study that provides proof-of-concept of automatic methods could be used archived social media collections. Using test collection 3,457,434 unique tweets relating COVID-19, China Chinese people, it sought identify instances Hate Speech as well hard-to-pinpoint trends in anti-Chinese racist sentiment. The study, part larger research effort investigating for appraisal...
Objective: To describe the association between nursing home staff turnover and presence scope of infection control citations. Data Sources: Secondary data for all U.S. homes March 31, 2017 through December 2019 from Payroll-Based Journal (PBJ), Nursing Home Compare, Long-Term Care Facts on in U.S.Study Design: We estimated nurse probability an citation citation, while controlling fixed effects. Our measure is percent facility's hours that were provided by new (less than 60 days experience...
This article reports on a study using machine learning to identify incidences and shifting dynamics of hate speech in social media archives. To better cope with the archival processing need for such large-scale fast evolving archives, we propose Data-driven Circulating Archival Processing (DCAP) method. As proof-of-concept, our focuses an English language Twitter archive relating COVID-19: Tweets were repeatedly scraped between February June 2020, ingested aggregated within COVID-19 Hate...