Dataset Information

Whether the weather will help us weather the COVID-19 pandemic: Using machine learning to measure twitter users' perceptions.

ABSTRACT: OBJECTIVE:The potential ability for weather to affect SARS-CoV-2 transmission has been an area of controversial discussion during the COVID-19 pandemic. Individuals' perceptions of the impact of weather can inform their adherence to public health guidelines; however, there is no measure of their perceptions. We quantified Twitter users' perceptions of the effect of weather and analyzed how they evolved with respect to real-world events and time. MATERIALS AND METHODS:We collected 166,005 English tweets posted between January 23 and June 22, 2020 and employed machine learning/natural language processing techniques to filter for relevant tweets, classify them by the type of effect they claimed, and identify topics of discussion. RESULTS:We identified 28,555 relevant tweets and estimate that 40.4 % indicate uncertainty about weather's impact, 33.5 % indicate no effect, and 26.1 % indicate some effect. We tracked changes in these proportions over time. Topic modeling revealed major latent areas of discussion. DISCUSSION:There is no consensus among the public for weather's potential impact. Earlier months were characterized by tweets that were uncertain of weather's effect or claimed no effect; later, the portion of tweets claiming some effect of weather increased. Tweets claiming no effect of weather comprised the largest class by June. Major topics of discussion included comparisons to influenza's seasonality, President Trump's comments on weather's effect, and social distancing. CONCLUSION:We exhibit a research approach that is effective in measuring population perceptions and identifying misconceptions, which can inform public health communications.

SUBMITTER: Gupta M

PROVIDER: S-EPMC7654388 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Whether the weather will help us weather the COVID-19 pandemic: Using machine learning to measure twitter users' perceptions.

Gupta Marichi M Bansal Aditya A Jain Bhav B Rochelle Jillian J Oak Atharv A Jalali Mohammad S MS

International journal of medical informatics 20201110

<h4>Objective</h4>The potential ability for weather to affect SARS-CoV-2 transmission has been an area of controversial discussion during the COVID-19 pandemic. Individuals' perceptions of the impact of weather can inform their adherence to public health guidelines; however, there is no measure of their perceptions. We quantified Twitter users' perceptions of the effect of weather and analyzed how they evolved with respect to real-world events and time.<h4>Materials and methods</h4>We collected ...[more]

PMID: 33242762

Similar Datasets

Project description:BackgroundIt is important to measure the public response to the COVID-19 pandemic. Twitter is an important data source for infodemiology studies involving public response monitoring.ObjectiveThe objective of this study is to examine COVID-19-related discussions, concerns, and sentiments using tweets posted by Twitter users.MethodsWe analyzed 4 million Twitter messages related to the COVID-19 pandemic using a list of 20 hashtags (eg, "coronavirus," "COVID-19," "quarantine") from March 7 to April 21, 2020. We used a machine learning approach, Latent Dirichlet Allocation (LDA), to identify popular unigrams and bigrams, salient topics and themes, and sentiments in the collected tweets.ResultsPopular unigrams included "virus," "lockdown," and "quarantine." Popular bigrams included "COVID-19," "stay home," "corona virus," "social distancing," and "new cases." We identified 13 discussion topics and categorized them into 5 different themes: (1) public health measures to slow the spread of COVID-19, (2) social stigma associated with COVID-19, (3) COVID-19 news, cases, and deaths, (4) COVID-19 in the United States, and (5) COVID-19 in the rest of the world. Across all identified topics, the dominant sentiments for the spread of COVID-19 were anticipation that measures can be taken, followed by mixed feelings of trust, anger, and fear related to different topics. The public tweets revealed a significant feeling of fear when people discussed new COVID-19 cases and deaths compared to other topics.ConclusionsThis study showed that Twitter data and machine learning approaches can be leveraged for an infodemiology study, enabling research into evolving public discussions and sentiments during the COVID-19 pandemic. As the situation rapidly evolves, several topics are consistently dominant on Twitter, such as confirmed cases and death rates, preventive measures, health authorities and government policies, COVID-19 stigma, and negative psychological reactions (eg, fear). Real-time monitoring and assessment of Twitter discussions and concerns could provide useful data for public health emergency responses and planning. Pandemic-related fear, stigma, and mental health concerns are already evident and may continue to influence public trust when a second wave of COVID-19 occurs or there is a new surge of the current pandemic.

Project description:BackgroundCOVID-19 is one of the greatest threats to human beings in terms of health care, economy, and society in recent history. Up to this moment, there have been no signs of remission, and there is no proven effective cure. Vaccination is the primary biomedical preventive measure against the novel coronavirus. However, public bias or sentiments, as reflected on social media, may have a significant impact on the progression toward achieving herd immunity.ObjectiveThis study aimed to use machine learning methods to extract topics and sentiments relating to COVID-19 vaccination on Twitter.MethodsWe collected 31,100 English tweets containing COVID-19 vaccine-related keywords between January and October 2020 from Australian Twitter users. Specifically, we analyzed tweets by visualizing high-frequency word clouds and correlations between word tokens. We built a latent Dirichlet allocation (LDA) topic model to identify commonly discussed topics in a large sample of tweets. We also performed sentiment analysis to understand the overall sentiments and emotions related to COVID-19 vaccination in Australia.ResultsOur analysis identified 3 LDA topics: (1) attitudes toward COVID-19 and its vaccination, (2) advocating infection control measures against COVID-19, and (3) misconceptions and complaints about COVID-19 control. Nearly two-thirds of the sentiments of all tweets expressed a positive public opinion about the COVID-19 vaccine; around one-third were negative. Among the 8 basic emotions, trust and anticipation were the two prominent positive emotions observed in the tweets, while fear was the top negative emotion.ConclusionsOur findings indicate that some Twitter users in Australia supported infection control measures against COVID-19 and refuted misinformation. However, those who underestimated the risks and severity of COVID-19 may have rationalized their position on COVID-19 vaccination with conspiracy theories. We also noticed that the level of positive sentiment among the public may not be sufficient to increase vaccination coverage to a level high enough to achieve vaccination-induced herd immunity. Governments should explore public opinion and sentiments toward COVID-19 and COVID-19 vaccination, and implement an effective vaccination promotion scheme in addition to supporting the development and clinical administration of COVID-19 vaccines.

Project description:BackgroundMenthol cigarettes are used disproportionately by African American, female, and adolescent smokers. Twitter is also used disproportionately by minority and younger populations, providing a unique window into conversations reflecting social norms, behavioral intentions, and sentiment toward menthol cigarettes.ObjectiveOur purpose was to identify the content and frequency of conversations about menthol cigarettes, including themes, populations, user smoking status, other tobacco or substances, tweet characteristics, and sentiment. We also examined differences in menthol cigarette sentiment by prevalent categories, which allowed us to assess potential perceptions, misperceptions, and social norms about menthol cigarettes on Twitter. This approach can inform communication about these products, particularly to subgroups who are at risk for menthol cigarette use.MethodsThrough a combination of human and machine classification, we identified 94,627 menthol cigarette-relevant tweets from February 1, 2012 to January 31, 2013 (1 year) from over 47 million tobacco-related messages gathered prospectively from the Twitter Firehose of all public tweets and metadata. Then, 4 human coders evaluated a random sample of 7000 tweets for categories, including sentiment toward menthol cigarettes.ResultsWe found that 47.98% (3194/6657) of tweets expressed positive sentiment, while 40.26% (2680/6657) were negative toward menthol cigarettes. The majority of tweets by likely smokers (2653/4038, 65.70%) expressed positive sentiment, while 91.2% (320/351) of nonsmokers and 71.7% (91/127) of former smokers indicated negative views. Positive views toward menthol cigarettes were predominant in tweets that discussed addiction or craving, marijuana, smoking, taste or sensation, song lyrics, and tobacco industry or marketing or tweets that were commercial in nature. Negative views toward menthol were more common in tweets about smoking cessation, health, African Americans, women, and children and adolescents-largely due to expression of negative stereotypes associated with these groups' use of menthol cigarettes.ConclusionsExaminations of public opinions toward menthol cigarettes through social media can help to inform the framing of public communication about menthol cigarettes, particularly in light of potential regulation by the European Union, US Food and Drug Administration, other jurisdictions, and localities.

Project description:BackgroundThe COVID-19 pandemic has presented new challenges surrounding end-of-life planning and has been associated with increased online discussion about life support.Research questionHow has online communication about advance care planning (ACP) and specific life-sustaining interventions (LSIs) changed during the pandemic?Study design and methodsConversations on Twitter containing references to LSIs (eg, "ECMO") or ACP (eg, "DNR/DNI") were collected between January 2019 and May 2021. User account metadata were used to predict user demographic information and to classify users as organizations, individuals, clinicians, or influencers. The number of impressions was compared across these user categories and the content of tweets analyzed by using natural language processing models to identify topics of discussion and associated emotional sentiment.ResultsThere were 202,585 unique tweets about LSIs and 67,162 unique tweets about ACP. Users who were younger, male, or influencers were more likely to discuss LSIs online. Tweets about LSIs were associated with more positive emotional sentiment scores than tweets about ACP (LSIs, 0.3; ACP, -0.2; P < .001). Among tweets about ACP, most contained personal experiences related to the death of loved ones (27%) or discussed discrimination through do-not-resuscitate orders directed at the elderly and disabled (19%). Personal experiences had the greatest retweet-to-tweet-ratio (4.7), indicating high levels of user engagement. Tweets about discrimination contained the most negative net sentiment score (-0.5).InterpretationThe observed increase in tweets regarding LSIs and ACP suggests that Twitter was consistently used to discuss treatment modalities and preferences related to intensive care during the pandemic. Future interventions to increase online engagement with ACP may consider leveraging influencers and personal stories. Finally, we identified do-not-resuscitate-related discrimination as a commonly held public fear, which should be further explored as a barrier to ACP completion and can be proactively addressed by clinicians during bedside goals-of-care discussions.

Project description:BackgroundTwitter presents a valuable and relevant social media platform to study the prevalence of information and sentiment on vaping that may be useful for public health surveillance. Machine learning classifiers that identify vaping-relevant tweets and characterize sentiments in them can underpin a Twitter-based vaping surveillance system. Compared with traditional machine learning classifiers that are reliant on annotations that are expensive to obtain, deep learning classifiers offer the advantage of requiring fewer annotated tweets by leveraging the large numbers of readily available unannotated tweets.ObjectiveThis study aims to derive and evaluate traditional and deep learning classifiers that can identify tweets relevant to vaping, tweets of a commercial nature, and tweets with provape sentiments.MethodsWe continuously collected tweets that matched vaping-related keywords over 2 months from August 2018 to October 2018. From this data set of tweets, a set of 4000 tweets was selected, and each tweet was manually annotated for relevance (vape relevant or not), commercial nature (commercial or not), and sentiment (provape or not). Using the annotated data, we derived traditional classifiers that included logistic regression, random forest, linear support vector machine, and multinomial naive Bayes. In addition, using the annotated data set and a larger unannotated data set of tweets, we derived deep learning classifiers that included a convolutional neural network (CNN), long short-term memory (LSTM) network, LSTM-CNN network, and bidirectional LSTM (BiLSTM) network. The unannotated tweet data were used to derive word vectors that deep learning classifiers can leverage to improve performance.ResultsLSTM-CNN performed the best with the highest area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.93-0.98) for relevance, all deep learning classifiers including LSTM-CNN performed better than the traditional classifiers with an AUC of 0.99 (95% CI 0.98-0.99) for distinguishing commercial from noncommercial tweets, and BiLSTM performed the best with an AUC of 0.83 (95% CI 0.78-0.89) for provape sentiment. Overall, LSTM-CNN performed the best across all 3 classification tasks.ConclusionsWe derived and evaluated traditional machine learning and deep learning classifiers to identify vaping-related relevant, commercial, and provape tweets. Overall, deep learning classifiers such as LSTM-CNN had superior performance and had the added advantage of requiring no preprocessing. The performance of these classifiers supports the development of a vaping surveillance system.

Project description:BackgroundTelehealth use has increased considerably in the last years and evidence suggests an overall positive sentiment towards telehealth. Twitter has a wide userbase and can enrich our understanding of telehealth use by users expressing their personal opinions in an unprompted way. This study aimed to explore Twitter users' experiences, perceptions and expectations about telehealth over the last 5 years.MethodsMixed-methods study with sequential complementary quantitative and qualitative phases was used for analysis stages comprising (1) a quantitative semiautomated analysis and (2) a qualitative research-led thematic analysis. A machine learning model was used to establish the data set with relevant English language tweets from 1 September 2017 to 1 September 2022 relating to telehealth using predefined search words. Results were integrated at the end.ResultsFrom the initial 237,671 downloaded tweets, 6469 had a relevancy score above 0.8 and were input into Leximancer and 595 were manually analysed. Experiences, perceptions and expectations were categorised into three domains: experience with telehealth consultation, telehealth changes over time and the purpose of the appointment. The most tweeted experience was expectations for telehealth consultation in comparison to in-person consultations. Users mostly mentioned the hope that waiting times for the consultations to start to be less than in-person, more telehealth appointments to be available and telehealth to be cheaper. Perceptions around the use of telehealth in relation to healthcare delivery changes brought about by the COVID-19 pandemic were also expressed. General practitioners were mentioned six times more than other healthcare professionals.Conclusion/implicationsThis study found that Twitter users expect telehealth services to be better, more affordable and more available than in-person consultations. Users acknowledged the convenience of not having to travel for appointments and the challenges to adapt to telehealth.Patient or public contributionAn open data set with 237,671 tweets expressing users' opinions in an unprompted way was used as a source for telehealth service users, caregivers and members of the public experiences, perceptions and expectations of telehealth.

Project description:BackgroundDuring the COVID-19 pandemic, residential lockdowns were implemented in numerous cities in China to contain the rapid spread of the disease. Although these stringent regulations effectively slowed the spread of COVID-19, they may have posed challenges to the well-being of residents.ObjectiveThis study aims to explore the effects of residential lockdown on the subjective well-being (SWB) of individuals in China during the COVID-19 pandemic.MethodsThe sample consisted of 1790 Sina Weibo users who were residents of cities that imposed residential lockdowns, of which 1310 users (73.18%) were female, and 3580 users who were residents of cities that were not locked down (gender-matched with the 1790 lockdown residents). In both the lockdown and nonlockdown groups, we calculated SWB indicators during the 2 weeks before and after the enforcement date of the residential lockdown using individuals' original posts on Sina Weibo. SWB was calculated via online ecological recognition, which is based on established machine learning predictive models.ResultsThe interactions of time (before the residential lockdown or after the residential lockdown) × area (lockdown or nonlockdown) in the integral analysis (N=5370) showed that after the residential lockdown, compared with the nonlockdown group, the lockdown group scored lower in some negative SWB indicators, including somatization (F1,5368=13.593, P<.001) and paranoid ideation (F1,5368=14.333, P<.001). The interactions of time (before the residential lockdown or after the residential lockdown) × area (developed or underdeveloped) in the comparison of residential lockdown areas with different levels of economic development (N=1790) indicated that the SWB of residents in underdeveloped areas showed no significant change after the residential lockdown (P>.05), while that of residents in developed areas changed.ConclusionsThese findings increase our understanding of the psychological impact and cost of residential lockdown during an epidemic. The more negative changes in the SWB of residents in developed areas imply a greater need for psychological intervention under residential lockdown in such areas.

Dataset Information

Whether the weather will help us weather the COVID-19 pandemic: Using machine learning to measure twitter users' perceptions.

Publications

Whether the weather will help us weather the COVID-19 pandemic: Using machine learning to measure twitter users' perceptions.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets