Identifying Silver Linings During the Pandemic Through Natural Language Processing

Lossio-Ventura, Juan Antonio; Lee, Angela Y.; Hancock, Jeffrey T.; Linos, Natalia; Linos, Eleni

doi:10.3389/fpsyg.2021.712111

Cited by 21 publications

(19 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to many other survey-based studies assessing the impact of the COVID-19 pandemic on physical and mental health and daily life [72][73][74], our overall study population was skewed, with respondents who were mainly White, educated, and female [34]. Interestingly, even within this skewed sample, those who responded to the free-response question were even more likely to be female, White, non-Hispanic, more educated, and older.…”

Section: Free Response Likelihood Varied Based On Demographic Factorssupporting

confidence: 66%

“…Across individuals, not surprisingly, the sentiment over the course of the COVID-19 pandemic was generally negative. Other studies performing sentiment analyses on social media with overlapping time ranges during the pandemic have found overall negativity [77,78], overall positivity [73,79,80], or mixed results [81]. This variability is likely a result of the type of language assessed, location of the participants, period, and sentiment analysis algorithm.…”

Section: Average Sentiment Was Consistently Negativementioning

confidence: 97%

See 1 more Smart Citation

Trends in Language Use During the COVID-19 Pandemic and Relationship Between Language Use and Mental Health: Text Analysis Based on Free Responses From a Longitudinal Study

et al. 2023

Self Cite

View full text Add to dashboard Cite

Background The COVID-19 pandemic and its associated restrictions have been a major stressor that has exacerbated mental health worldwide. Qualitative data play a unique role in documenting mental states through both language features and content. Text analysis methods can provide insights into the associations between language use and mental health and reveal relevant themes that emerge organically in open-ended responses. Objective The aim of this web-based longitudinal study on mental health during the early COVID-19 pandemic was to use text analysis methods to analyze free responses to the question, “Is there anything else you would like to tell us that might be important that we did not ask about?” Our goals were to determine whether individuals who responded to the item differed from nonresponders, to determine whether there were associations between language use and psychological status, and to characterize the content of responses and how responses changed over time. Methods A total of 3655 individuals enrolled in the study were asked to complete self-reported measures of mental health and COVID-19 pandemic–related questions every 2 weeks for 6 months. Of these 3655 participants, 2497 (68.32%) provided at least 1 free response (9741 total responses). We used various text analysis methods to measure the links between language use and mental health and to characterize response themes over the first year of the pandemic. Results Response likelihood was influenced by demographic factors and health status: those who were male, Asian, Black, or Hispanic were less likely to respond, and the odds of responding increased with age and education as well as with a history of physical health conditions. Although mental health treatment history did not influence the overall likelihood of responding, it was associated with more negative sentiment, negative word use, and higher use of first-person singular pronouns. Responses were dynamically influenced by psychological status such that distress and loneliness were positively associated with an individual’s likelihood to respond at a given time point and were associated with more negativity. Finally, the responses were negative in valence overall and exhibited fluctuations linked with external events. The responses covered a variety of topics, with the most common being mental health and emotion, social or physical distancing, and policy and government. Conclusions Our results identify trends in language use during the first year of the pandemic and suggest that both the content of responses and overall sentiments are linked to mental health.

show abstract

Section: Free Response Likelihood Varied Based On Demographic Factorssupporting

confidence: 66%

Section: Average Sentiment Was Consistently Negativementioning

confidence: 97%

Trends in Language Use During the COVID-19 Pandemic and Relationship Between Language Use and Mental Health: Text Analysis Based on Free Responses From a Longitudinal Study

et al. 2023

Self Cite

View full text Add to dashboard Cite

show abstract

“…Like many other survey-based studies assessing the COVID-19 pandemic's impact on physical and mental health and daily life [58][59][60], our overall study population was skewed, with respondents who were mainly white, educated, and female [57]. Interestingly, even within this skewed sample, those who responded to the free response question were even more likely to be female, white, non-Hispanic, more educated, and older.…”

Section: Discussionmentioning

confidence: 76%

“…Across individuals, the sentiment over the course of the COVID-19 pandemic was generally negative. Other studies performing sentiment analyses on social media with overlapping time ranges during the pandemic have found overall negativity [63,64], overall positivity [59,65,66], or mixed results [67]. This variability is likely a result of type of language assessed, location of the participants, time period, and sentiment analysis algorithm.…”

Section: Discussionmentioning

confidence: 96%

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

Weger¹,

Lossio-Ventura²,

Rose-McCandlish³

et al. 2022

Preprint

View full text Add to dashboard Cite

The COVID-19 pandemic and associated restrictions have been a major stressor and exacerbated mental health worldwide. Qualitative data play a unique role in documenting mental state, via both language features and content. Within a longitudinal study on mental health during the COVID-19 pandemic, we analyzed free responses to the question: “Is there anything else you would like to tell us that might be important that we did not ask about?” We applied text analysis methods to ask whether individuals who responded to the item differed from non- responders, whether there were associations between language use and psychological status, and to characterize the content of responses and how responses changed over time. 3,655 individuals provided biweekly measures of mental health and responses to the COVID-19 pandemic for 6 months. Of these, 2,497 participants provided at least one free response (9,741 total responses). Response likelihood was influenced by demographic factors and health status: Participants who were male, Asian, Black, or Hispanic were less likely to respond, and odds of responding increased with age and education as well as with a history of physical health conditions. Although mental illness history did not influence an individual’s overall likelihood of responding, it was associated with more negative sentiment, negative word use, and higher usage of first-person singular pronouns. Responses were dynamically influenced by psychological status, such that distress and loneliness were positively associated with an individuals’ likelihood to respond at a given timepoint, and predicted more negativity. Finally, responses were negative in valence overall, exhibited fluctuations linked with external events, and covered a variety of topics, with the most common being mental health and emotion. Our results identify trends in language use during the first year of the pandemic, and suggest that the both the content of responses and overall sentiment are linked to mental health.

show abstract

“…These methods were used in conjunction with social media data mining to examine patterns in data and perform a thematic analysis [ 23 , 24 , 26 ]. For the thematic analysis, CulturIntel tagged and sorted data; determined key sentiments toward depression, drivers of those sentiments, motivations and barriers to seeking help, and overarching mindsets; and assigned underlying drivers and barriers, when possible, throughout decision journey stages.…”

Section: Methodsmentioning

confidence: 99%

Applying the Health Belief Model to Characterize Racial/Ethnic Differences in Digital Conversations Related to Depression Pre- and Mid-COVID-19: Descriptive Analysis

Castilla-Puentes¹,

Pesa²,

Brethenoux³

et al. 2022

JMIR Form Res

View full text Add to dashboard Cite

Background The prevalence of depression in the United States is >3 times higher mid-COVID-19 versus prepandemic. Racial/ethnic differences in mindsets around depression and the potential impact of the COVID-19 pandemic are not well characterized. Objective This study aims to describe attitudes, mindsets, key drivers, and barriers related to depression pre- and mid-COVID-19 by race/ethnicity using digital conversations about depression mapped to health belief model (HBM) concepts. Methods Advanced search, data extraction, and artificial intelligence–powered tools were used to harvest, mine, and structure open-source digital conversations of US adults who engaged in conversations about depression pre- (February 1, 2019-February 29, 2020) and mid-COVID-19 pandemic (March 1, 2020-November 1, 2020) across the internet. Natural language processing, text analytics, and social data mining were used to categorize conversations that included a self-identifier into racial/ethnic groups. Conversations were mapped to HBM concepts (ie, perceived susceptibility, perceived severity, perceived benefits, perceived barriers, cues to action, and self-efficacy). Results are descriptive in nature. Results Of 2.9 and 1.3 million relevant digital conversations pre- and mid-COVID-19, race/ethnicity was determined among 1.8 million (62.2%) and 979,000 (75.3%) conversations, respectively. Pre-COVID-19, 1.3 million (72.1%) conversations about depression were analyzed among non-Hispanic Whites (NHW), 227,200 (12.6%) among Black Americans (BA), 189,200 (10.5%) among Hispanics, and 86,800 (4.8%) among Asian Americans (AS). Mid-COVID-19, a total of 736,100 (75.2%) conversations about depression were analyzed among NHW, 131,800 (13.5%) among BA, 78,300 (8.0%) among Hispanics, and 32,800 (3.3%) among AS. Conversations among all racial/ethnic groups had a negative tone, which increased pre- to mid-COVID-19; finding support from others was seen as a benefit among most groups. Hispanics had the highest rate of any racial/ethnic group of conversations showing an avoiding mindset toward their depression. Conversations related to external barriers to seeking treatment (eg, stigma, lack of support, and lack of resources) were generally more prevalent among Hispanics, BA, and AS than among NHW. Being able to benefit others and building a support system were key drivers to seeking help or treatment for all racial/ethnic groups. Conclusions There were considerable racial/ethnic differences in drivers and barriers to seeking help and treatment for depression pre- and mid-COVID-19. As expected, COVID-19 has made conversations about depression more negative and with frequent discussions of barriers to seeking care. Applying concepts of the HBM to data on digital conversation about depression allowed organization of the most frequent themes by race/ethnicity. Individuals of all groups came online to discuss their depression. These data highlight opportunities for culturally competent and targeted approaches to addressing areas amenable to change that might impact the ability of people to ask for or receive mental health help, such as the constructs that comprise the HBM.

show abstract

Identifying Silver Linings During the Pandemic Through Natural Language Processing

Cited by 21 publications

References 39 publications

Trends in Language Use During the COVID-19 Pandemic and Relationship Between Language Use and Mental Health: Text Analysis Based on Free Responses From a Longitudinal Study

Trends in Language Use During the COVID-19 Pandemic and Relationship Between Language Use and Mental Health: Text Analysis Based on Free Responses From a Longitudinal Study

“Is there anything else you would like to tell us?”: An analysis of language features in text responses to a study on mental health during the COVID-19 pandemic

Applying the Health Belief Model to Characterize Racial/Ethnic Differences in Digital Conversations Related to Depression Pre- and Mid-COVID-19: Descriptive Analysis

Contact Info

Product

Resources

About