Angela Yuson Lee

All Publications

• A Comparison of ChatGPT and Fine-Tuned Open Pre-Trained Transformers (OPT) Against Widely Used Sentiment Analysis Tools: Sentiment Analysis of COVID-19 Survey Data. JMIR mental health Lossio-Ventura, J. A., Weger, R., Lee, A. Y., Guinee, E. P., Chung, J., Atlas, L., Linos, E., Pereira, F. 2024; 11: e50150

  Abstract

  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.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.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).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%.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.

  View details for DOI 10.2196/50150

  View details for PubMedID 38271138

• Developing digital resilience: An educational intervention improves elementary students' response to digital challenges COMPUTERS AND EDUCATION OPEN Lee, A. Y., Hancock, J. T. 2023; 5

  View details for DOI 10.1016/j.caeo.2023.100144

  View details for Web of Science ID 001042328700001

• Too tired to connect: Understanding the associations between video-conferencing, social connection and well-being through the lens of zoom fatigue COMPUTERS IN HUMAN BEHAVIOR Queiroz, A. M., Lee, A. Y., Luo, M., Fauville, G., Hancock, J. T., Bailenson, J. N. 2023; 149

  View details for DOI 10.1016/j.chb.2023.107968

  View details for Web of Science ID 001095519300001

• Social media mindsets: a new approach to understanding social media use and psychological well-being JOURNAL OF COMPUTER-MEDIATED COMMUNICATION Lee, A. Y., Hancock, J. T. 2023; 29 (1)

  View details for DOI 10.1093/jcmc/zmad048

  View details for Web of Science ID 001169394600001

• To use or be used? The role of agency in social media use and well-being FRONTIERS IN COMPUTER SCIENCE Lee, A. Y., Ellison, N. B., Hancock, J. T. 2023; 5

  View details for DOI 10.3389/fcomp.2023.1123323

  View details for Web of Science ID 000969401000001

• The Role of Subjective Construals on Reporting and Reasoning about Social Media Use SOCIAL MEDIA + SOCIETY Lee, A. Y., Katz, R., Hancock, J. 2021; 7 (3)

  View details for DOI 10.1177/20563051211035350

  View details for Web of Science ID 000697973000001

• Age-Related Differences in Experiences with Social Distancing at the Onset of the COVID-19 Pandemic: A Computational and Content Analytic Investigation of Natural Language. JMIR human factors Moore, R. C., Lee, A. Y., Hancock, J. T., Halley, M. C., Linos, E. 2021

  Abstract

  BACKGROUND: As COVID-19 poses different levels of threat to people of different ages, health communication regarding prevention measures such as social distancing and isolation may be strengthened by understanding the unique experiences of different age groups.OBJECTIVE: The aim was to examine how people of different ages (1) experienced the impact of the COVID-19 pandemic and (2) their respective rates and reasons for compliance or non-compliance with social distancing and isolation health guidance.METHODS: We fielded a survey on social media (N = 17,287) early in the pandemic to examine the emotional impact of COVID-19 and individuals' rates and reasons for non-compliance with public health guidance, using computational and content analytic methods of linguistic analysis. The majority of our participants (76.5%) were from the United States.RESULTS: Younger (18-31), middle-aged (32-44, 45-64), and older (65+) individuals significantly varied in how they described the impact of COVID-19 on their lives, including their emotional experience, self-focused attention, and topical concerns. Younger individuals were more emotionally negative and self-focused, while middle-aged people were other-focused and concerned with family. The oldest and most at-risk group was most concerned with health-related terms but were also lower in anxiety and higher in the use of emotionally positive terms than the other, less at-risk age groups. While all groups discussed topics such as acquiring essential supplies, they differentially experienced the impact of school closures and limited social interactions. We also found relatively high rates of non-compliance with COVID-19 prevention measures, such as social distancing and self-isolation, with younger people being more likely to be non-compliant than older people, (P < .001). Among the 43% of respondents who did not fully comply with health orders, people differed substantially in the reasons they gave for non-compliance. The most common reason for non-compliance was not being able to afford missing work (57.3%). While work obligations proved challenging for participants across ages, younger people struggled more to find adequate space to self-isolate and manage their mental and physical health; middle-aged people faced more concerns regarding childcare; and older people perceived themselves as able to take sufficient precautions.CONCLUSIONS: Analysis of natural language can provide insight into rapidly developing public health challenges like the COVID-19 pandemic, uncovering individual differences in emotional experiences and health-related behaviors. In this case, our analyses revealed significant differences between different age groups in feelings about and responses to public health orders aimed to mitigate the spread of COVID-19. To improve public compliance with health orders as the pandemic continues, health communication strategies could be made more effective by being tailored to these age-related differences.CLINICALTRIAL:

  View details for DOI 10.2196/26043

  View details for PubMedID 33914689

• Identifying Silver Linings During the Pandemic Through Natural Language Processing. Frontiers in psychology Lossio-Ventura, J. A., Lee, A. Y., Hancock, J. T., Linos, N., Linos, E. 2021; 12: 712111

  Abstract

  COVID-19 has presented an unprecedented challenge to human welfare. Indeed, we have witnessed people experiencing a rise of depression, acute stress disorder, and worsening levels of subclinical psychological distress. Finding ways to support individuals' mental health has been particularly difficult during this pandemic. An opportunity for intervention to protect individuals' health & well-being is to identify the existing sources of consolation and hope that have helped people persevere through the early days of the pandemic. In this paper, we identified positive aspects, or "silver linings," that people experienced during the COVID-19 crisis using computational natural language processing methods and qualitative thematic content analysis. These silver linings revealed sources of strength that included finding a sense of community, closeness, gratitude, and a belief that the pandemic may spur positive social change. People's abilities to engage in benefit-finding and leverage protective factors can be bolstered and reinforced by public health policy to improve society's resilience to the distress of this pandemic and potential future health crises.

  View details for DOI 10.3389/fpsyg.2021.712111

  View details for PubMedID 34539512

• "Bringing you into the zoom": The power of authentic engagement in a time of crisis in the USA JOURNAL OF CHILDREN AND MEDIA Lee, A. Y., Moskowitz-Sweet, G., Pelavin, E., Rivera, O., Hancock, J. T. 2020

  View details for DOI 10.1080/17482798.2020.1858437

  View details for Web of Science ID 000599856600001

• Priming Effects of Social Media Use Scales on Well-Being Outcomes: The Influence of Intensity and Addiction Scales on Self-Reported Depression SOCIAL MEDIA + SOCIETY Mieczkowski, H., Lee, A. Y., Hancock, J. T. 2020; 6 (4)

  View details for DOI 10.1177/2056305120961784

  View details for Web of Science ID 000595936900001

• Jumpstart program efficacy: The impact of early childhood education advancement initiatives on low-income preschool children's literacy, agency, and social relations COGENT EDUCATION Yen, S., Lee, A. Y. 2019; 6 (1)

  View details for DOI 10.1080/2331186X.2019.1592063

  View details for Web of Science ID 000462853600001

• Learning online, offline, and in-between: comparing student academic outcomes and course satisfaction in face-to-face, online, and blended teaching modalities EDUCATION AND INFORMATION TECHNOLOGIES Yen, S., Lo, Y., Lee, A., Enriquez, J. 2018; 23 (5): 2141–53

  View details for DOI 10.1007/s10639-018-9707-5

  View details for Web of Science ID 000442598800020

• A Media Mediation: Countering the Implications of Digital Communication on Conflict in Romantic Relationships Lee, A. ROUTLEDGE JOURNALS, TAYLOR & FRANCIS LTD. 2016: 837

  View details for Web of Science ID 000413720406086