Emily P. Guinee

Emily P. Guinee

Auto-generated profile, based on publicly available information

Emily P. Guinee

National Institute of Mental Health, National Institutes of Health, Bethesda, MD, United States

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 January 2024 in JMIR Mental Health
Verified
Journal Article
Open access
JLJuan Antonio Lossio-Ventura
Juan Antonio Lossio-Ventura
RWRachel Weger
Rachel Weger
ALAngela Y Lee
Angela Y Lee
EGEmily P Guinee
Emily P Guinee
JCJoyce Chung
Joyce Chung
FPFrancisco Pereira
Francisco Pereira
Background: Health care providers and health-related researchers face significant challenges when applying sentiment analysis tools to health-related free-text survey data. Most state-of-the-art applications were developed in domains such as social media, and their performance in the health care context remains relatively unknown. Moreover, existing studies indicate that these tools often lack accuracy and produce inconsistent results. Objective: This study aims to address the lack of comparative analysis on sentiment analysis tools applied to health-related free-text survey data in the context of COVID-19. The objective was to automatically predict sentence sentiment for 2 independent COVID-19 survey data sets from the National Institutes of Health and Stanford University. Methods: Gold standard labels were created for a subset of each data set using a panel of human raters. We compared 8 state-of-the-art sentiment analysis tools on both data sets to evaluate variability and disagreement across tools. In addition, few-shot learning was explored by fine-tuning Open Pre-Trained Transformers (OPT; a large language model [LLM] with publicly available weights) using a small annotated subset and zero-shot learning using ChatGPT (an LLM without available weights). Results: The comparison of sentiment analysis tools revealed high variability and disagreement across the evaluated tools when applied to health-related survey data. OPT and ChatGPT demonstrated superior performance, outperforming all other sentiment analysis tools. Moreover, ChatGPT outperformed OPT, exhibited higher accuracy by 6% and higher F-measure by 4% to 7%. Conclusions: This study demonstrates the effectiveness of LLMs, particularly the few-shot learning and zero-shot learning approaches, in the sentiment analysis of health-related survey data. These results have implications for saving human labor and improving efficiency in sentiment analysis tasks, contributing to advancements in the field of automated sentiment analysis.

22 January 2024 in medRxiv
Verified
Preprint
Open access
PDF file
EGEmily P. Guinee
Emily P. Guinee
HRHaniya Raza
Haniya Raza
EBElizabeth D. Ballard
Elizabeth D. Ballard
JSJacob S. Shaw
Jacob S. Shaw
CLC. Jason Liang
C. Jason Liang
JCJoyce Y. Chung
Joyce Y. Chung
Trauma and stressor-related symptoms have been frequently reported during the COVID-19 pandemic. Few studies compare post-traumatic stress symptoms (PTSS) between patients and non-infected controls. Using data from an ongoing natural history study of COVID-19, this study compared PTSS between patients infected with SARS-CoV-2 during the first year of the pandemic and controls. Within the COVID-19 patient cohort, we also compared PTSS between patients with and without post-COVID conditions, also known as post-acute sequelae of SARS-CoV-2 infection (PASC). This study also examined the association of PTSS with trait resilience and prior trauma exposure. PTSS were assessed using the Impact of Event Scaled-Revised (IES-R), which has a validated probable PTSD cutoff (score ≥33). The results showed that patients (n=131) reported significantly higher IES-R scores than controls (n=82) and had significantly higher odds of having scores indicative of PTSD [AOR: 4.17 p: 0.029]. IES-R scores among PASC patients (n=68) were significantly elevated compared to patients without PASC (n=63) and PASC patients did not have higher odds for probable PTSD [AOR: 2.60; p: 0.14]. Trait resilience was associated with lower PTSS. These findings help characterize the mental health impact of the COVID-19 illness experience and highlight elevated PTSS in patients with persistent post-COVID conditions.

21 June 2023 in JMIR Preprints
Verified
Preprint
Open access
JLJuan Antonio Lossio-Ventura
Juan Antonio Lossio-Ventura
RWRachel Weger
Rachel Weger
ALAngela Y Lee
Angela Y Lee
EGEmily P Guinee
Emily P Guinee
JCJoyce Chung
Joyce Chung
FPFrancisco Pereira
Francisco Pereira
BACKGROUND Health care providers and health-related researchers face significant challenges when applying sentiment analysis tools to health-related free-text survey data. Most state-of-the-art applications were developed in domains such as social media, and their performance in the health care context remains relatively unknown. Moreover, existing studies indicate that these tools often lack accuracy and produce inconsistent results. OBJECTIVE This study aims to address the lack of comparative analysis on sentiment analysis tools applied to health-related free-text survey data in the context of COVID-19. The objective was to automatically predict sentence sentiment for 2 independent COVID-19 survey data sets from the National Institutes of Health and Stanford University. METHODS Gold standard labels were created for a subset of each data set using a panel of human raters. We compared 8 state-of-the-art sentiment analysis tools on both data sets to evaluate variability and disagreement across tools. In addition, few-shot learning was explored by fine-tuning Open Pre-Trained Transformers (OPT; a large language model [LLM] with publicly available weights) using a small annotated subset and zero-shot learning using ChatGPT (an LLM without available weights). RESULTS The comparison of sentiment analysis tools revealed high variability and disagreement across the evaluated tools when applied to health-related survey data. OPT and ChatGPT demonstrated superior performance, outperforming all other sentiment analysis tools. Moreover, ChatGPT outperformed OPT, exhibited higher accuracy by 6% and higher F-measure by 4% to 7%. CONCLUSIONS This study demonstrates the effectiveness of LLMs, particularly the few-shot learning and zero-shot learning approaches, in the sentiment analysis of health-related survey data. These results have implications for saving human labor and improving efficiency in sentiment analysis tasks, contributing to advancements in the field of automated sentiment analysis.