Alcohol Advertising on Twitter—A Topic Model

Barry, Adam E.; Valdez, Danny; Padon, Alisa A.; Russell, Alex M.

doi:10.1080/19325037.2018.1473180

Cited by 27 publications

(20 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simply, words with high probabilities of association (ie, a high likelihood to appear in proximity with other words) are grouped together to form a latent theme, or topic, that qualitatively represents a content area within the collection of text. These methods have been applied in many ways such as to determine common themes in product reviews [26], to map themes within bodies of scientific literature [27], and to identify themes in social media data [28]. Thus, these tools are appropriate for exploratory analyses that seek to consolidate dense text data.…”

Section: Latent Dirichlet Allocation Topic Modelsmentioning

confidence: 99%

Social Media Insights Into US Mental Health During the COVID-19 Pandemic: Longitudinal Analysis of Twitter Data

Valdez¹,

Thij²,

Bathina³

et al. 2020

J Med Internet Res

Self Cite

226

151

View full text Add to dashboard Cite

Background The COVID-19 pandemic led to unprecedented mitigation efforts that disrupted the daily lives of millions. Beyond the general health repercussions of the pandemic itself, these measures also present a challenge to the world’s mental health and health care systems. Considering that traditional survey methods are time-consuming and expensive, we need timely and proactive data sources to respond to the rapidly evolving effects of health policy on our population’s mental health. Many people in the United States now use social media platforms such as Twitter to express the most minute details of their daily lives and social relations. This behavior is expected to increase during the COVID-19 pandemic, rendering social media data a rich field to understand personal well-being. Objective This study aims to answer three research questions: (1) What themes emerge from a corpus of US tweets about COVID-19? (2) To what extent did social media use increase during the onset of the COVID-19 pandemic? and (3) Does sentiment change in response to the COVID-19 pandemic? Methods We analyzed 86,581,237 public domain English language US tweets collected from an open-access public repository in three steps. First, we characterized the evolution of hashtags over time using latent Dirichlet allocation (LDA) topic modeling. Second, we increased the granularity of this analysis by downloading Twitter timelines of a large cohort of individuals (n=354,738) in 20 major US cities to assess changes in social media use. Finally, using this timeline data, we examined collective shifts in public mood in relation to evolving pandemic news cycles by analyzing the average daily sentiment of all timeline tweets with the Valence Aware Dictionary and Sentiment Reasoner (VADER) tool. Results LDA topics generated in the early months of the data set corresponded to major COVID-19–specific events. However, as state and municipal governments began issuing stay-at-home orders, latent themes shifted toward US-related lifestyle changes rather than global pandemic-related events. Social media volume also increased significantly, peaking during stay-at-home mandates. Finally, VADER sentiment analysis scores of user timelines were initially high and stable but decreased significantly, and continuously, by late March. Conclusions Our findings underscore the negative effects of the pandemic on overall population sentiment. Increased use rates suggest that, for some, social media may be a coping mechanism to combat feelings of isolation related to long-term social distancing. However, in light of the documented negative effect of heavy social media use on mental health, social media may further exacerbate negative feelings in the long-term for many individuals. Thus, considering the overburdened US mental health care structure, these findings have important implications for ongoing mitigation efforts.

show abstract

Section: Latent Dirichlet Allocation Topic Modelsmentioning

confidence: 99%

Social Media Insights Into US Mental Health During the COVID-19 Pandemic: Longitudinal Analysis of Twitter Data

Valdez¹,

Thij²,

Bathina³

et al. 2020

J Med Internet Res

Self Cite

226

151

View full text Add to dashboard Cite

show abstract

“…We divided the COVID-19 corpus into daily segments and generated one topic model per day consisting of 20 topics each. We chose this number to reflect the widest possible span of themes while summarizing the major themes of the online discussion, which is a process used in previous studies 29,35 . We then looked at the top 20 associated words per topic and collapsed similar words into general themes, taking into account similarities of words (i.e.…”

Section: Methodsmentioning

confidence: 99%

“…These methods have been applied in myriad ways, e.g. to determine common themes in product reviews 27 , to map themes within bodies of scientific literature 28 , and to identify themes in social media data 29 . Thus, these tools are appropriate for exploratory analyses that seek to consolidate dense text data.…”

Section: Analysesmentioning

confidence: 99%

Social Media Insights Into US Mental Health Amid the COVID-19 Pandemic. A Longitudinal Twitter Analysis (JANUARY-APRIL 2020)

Valdez

Thij

Bathina

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

BackgroundThe COVID-19 pandemic led to unprecedented mitigation efforts that disrupted the daily lives of millions. Beyond the general health repercussions of the pandemic itself, these measures also present a significant challenge to the world’s mental health and healthcare systems. Considering traditional survey methods are time-consuming and expensive, we need timely and proactive data sources to respond to the rapidly evolving effects of health policy on our population’s mental health. Significant pluralities of the US population now use social media platforms, such as Twitter, to express the most minute details of their daily lives and social relations. This behavior is expected to increase during the COVID-19 pandemic, rendering social media data a rich field from which to understand personal wellbeing.PurposeBroadly, this study answers three research questions: RQ1: What themes emerge from a corpus of US tweets about COVID-19?; RQ2: To what extent does social media use increase during the onset of the COVID-19 pandemic?; and RQ3: Does sentiment change in response to the COVID-19 pandemic?MethodsWe analyzed 86,581,237 public domain English-language US tweets collected from an open-access public repository in three steps1. First, we characterized the evolution of hashtags over time using Latent Dirichlet Allocation (LDA) topic modeling. Second, we increased the granularity of this analysis by downloading Twitter timelines of a large cohort of individuals (n = 354,738) in 20 major US cities to assess changes in social media use. Finally, using this timeline data, we examined collective shifts in public mood in relation to evolving pandemic news cycles by analyzing the average daily sentiment of all timeline tweets with the Valence Aware Dictionary and sEntiment Reasoner (VADER) sentiment tool2.ResultsLDA topics generated in the early months of the dataset corresponded to major COVID-19 specific events. However, as state and municipal governments began issuing stay-at-home orders, latent themes shifted towards US-related lifestyle changes rather than global pandemic-related events. Social media volume also increased significantly, peaking during stay-at-home mandates. Finally, VADER sentiment analysis sentiment scores of user timelines were initially high and stable, but decreased significantly, and continuously, by late March.Discussion & ConclusionOur findings underscore the negative effects of the pandemic on overall population sentiment. Increased usage rates suggest that, for some, social media may be a coping mechanism to combat feelings of isolation related to long-term social distancing. However, in light of the documented negative effect of heavy social media usage on mental health, for many social media may further exacerbate negative feelings in the long-term. Thus, considering the overburdened US mental healthcare structure, these findings have important implications for ongoing mitigation efforts.

show abstract

“…In health education research to date, topic modeling has primarily been used to analyze social media data. For example, recent studies have used social media data to examine health concerns expressed online (Paul & Dredze, 2014), syndromic surveillance of the influenza virus on Twitter (Chen et al, 2016), digital branding strategies of major alcohol brands (Barry et al, 2018), and mental well-being during the COVID-19 pandemic . While social media represents a large, and freely available, source of text data for analysis, there are other potential uses for topic modeling in health-related research.…”

Section: Applications In Health-related Fieldsmentioning

confidence: 99%

On Mining Words: The Utility of Topic Models in Health Education Research and Practice

Valdez

Picket

Young

et al. 2021

Health Promotion Practice

Self Cite

View full text Add to dashboard Cite

Written language is the primary means by which scientific research findings are disseminated. Yet in the era of information overload, dissemination of a field of research may require additional efforts given the sheer volume of material available on any specific topic. Topic models are unsupervised natural language processing methods that analyze nonnumeric data (i.e., text data) in abundance. These tools aggregate, and make sense of, those data making them interpretable to interested audiences. In this perspective piece, we briefly describe topic models, including their purpose, function, and applicability for health education researchers and practitioners. We note how topic models can be applied in several contexts, including social media–based analyses, and mapping trends in scientific literature over time. As a tool for studying words, and patterns of words, topic models stand to improve our understanding of events prior and those occurring in the moment and help us look ahead into the future.

show abstract

Alcohol Advertising on Twitter—A Topic Model

Cited by 27 publications

References 34 publications

Social Media Insights Into US Mental Health During the COVID-19 Pandemic: Longitudinal Analysis of Twitter Data

Social Media Insights Into US Mental Health During the COVID-19 Pandemic: Longitudinal Analysis of Twitter Data

Social Media Insights Into US Mental Health Amid the COVID-19 Pandemic. A Longitudinal Twitter Analysis (JANUARY-APRIL 2020)

On Mining Words: The Utility of Topic Models in Health Education Research and Practice

Contact Info

Product

Resources

About