Monitoring Information-Seeking Patterns and Obesity Prevalence in Africa With Internet Search Data: Observational Study

BackgroundThe prevalence of chronic conditions such as obesity, hypertension, and diabetes is increasing in African countries. Many chronic diseases have been linked to risk factors such as poor diet and physical inactivity. Data for these behavioral risk factors are usually obtained from surveys, which can be delayed by years. Behavioral data from digital sources, including social media and search engines, could be used for timely monitoring of behavioral risk factors.ObjectiveThe objective of our study was to propose the use of digital data from internet sources for monitoring changes in behavioral risk factors in Africa.MethodsWe obtained the adjusted volume of search queries submitted to Google for 108 terms related to diet, exercise, and disease from 2010 to 2016. We also obtained the obesity and overweight prevalence for 52 African countries from the World Health Organization (WHO) for the same period. Machine learning algorithms (ie, random forest, support vector machine, Bayes generalized linear model, gradient boosting, and an ensemble of the individual methods) were used to identify search terms and patterns that correlate with changes in obesity and overweight prevalence across Africa. Out-of-sample predictions were used to assess and validate the model performance.ResultsThe study included 52 African countries. In 2016, the WHO reported an overweight prevalence ranging from 20.9% (95% credible interval [CI] 17.1%-25.0%) to 66.8% (95% CI 62.4%-71.0%) and an obesity prevalence ranging from 4.5% (95% CI 2.9%-6.5%) to 32.5% (95% CI 27.2%-38.1%) in Africa. The highest obesity and overweight prevalence were noted in the northern and southern regions. Google searches for diet-, exercise-, and obesity-related terms explained 97.3% (root-mean-square error [RMSE] 1.15) of the variation in obesity prevalence across all 52 countries. Similarly, the search data explained 96.6% (RMSE 2.26) of the variation in the overweight prevalence. The search terms yoga, exercise, and gym were most correlated with changes in obesity and overweight prevalence in countries with the highest prevalence.ConclusionsInformation-seeking patterns for diet- and exercise-related terms could indicate changes in attitudes toward and engagement in risk factors or healthy behaviors. These trends could capture population changes in risk factor prevalence, inform digital and physical interventions, and supplement official data from surveys.     

The Digital Distribution of Public Health News Surrounding the Human Papillomavirus Vaccination: A Longitudinal Infodemiology Study

Background

New media changes the dissemination of public health information and misinformation. During a guest appearance on the Today Show, US Representative Michele Bachmann claimed that human papillomavirus (HPV) vaccines could cause “mental retardation”.

Objective

The purpose of this study is to explore how new media influences the type of public health information users access, as well as the impact to these platforms after a major controversy. Specifically, this study aims to examine the similarities and differences in the dissemination of news articles related to the HPV vaccination between Google News and Twitter, as well as how the content of news changed after Michele Bachmann’s controversial comment.

Methods

This study used a purposive sampling to draw the first 100 news articles that appeared on Google News and the first 100 articles that appeared on Twitter from August 1-October 31, 2011. Article tone, source, topics, concerns, references, publication date, and interactive features were coded. The intercoder reliability had a total agreement of .90.

Results

Results indicate that 44.0% of the articles (88/200) about the HPV vaccination had a positive tone, 32.5% (65/200) maintained a neutral tone, while 23.5% (47/200) presented a negative tone. Protection against diseases 82.0% (164/200), vaccine eligibility for females 75.5% (151/200), and side effects 59.0% (118/200) were the top three topics covered by these articles. Google News and Twitter articles significantly differed in article tone, source, topics, concerns covered, types of sources referenced in the article, and uses of interactive features. Most notably, topic focus changed from public health information towards political conversation after Bachmann’s comment. Before the comment, the HPV vaccine news talked more often about vaccine dosing (P<.001), duration (P=.005), vaccine eligibility for females (P=.03), and protection against diseases (P=.04) than did the later pieces. After the controversy, the news topic shifted towards politics (P=.01) and talked more about HPV vaccine eligibility for males (P=.01).

Conclusions

This longitudinal infodemiology study suggests that new media influences public health communication, knowledge transaction, and poses potential problems in the amount of misinformation disseminated during public health campaigns. In addition, the study calls for more research to adopt an infodemiology approach to explore relationships between online information supply and public health decisions.     

The Causality Inference of Public Interest in Restaurants and Bars on Daily COVID-19 Cases in the United States: Google Trends Analysis

BackgroundThe COVID-19 pandemic has affected virtually every region in the world. At the time of this study, the number of daily new cases in the United States was greater than that in any other country, and the trend was increasing in most states. Google Trends provides data regarding public interest in various topics during different periods. Analyzing these trends using data mining methods may provide useful insights and observations regarding the COVID-19 outbreak.ObjectiveThe objective of this study is to consider the predictive ability of different search terms not directly related to COVID-19 with regard to the increase of daily cases in the United States. In particular, we are concerned with searches related to dine-in restaurants and bars. Data were obtained from the Google Trends application programming interface and the COVID-19 Tracking Project.MethodsTo test the causation of one time series on another, we used the Granger causality test. We considered the causation of two different search query trends related to dine-in restaurants and bars on daily positive cases in the US states and territories with the 10 highest and 10 lowest numbers of daily new cases of COVID-19. In addition, we used Pearson correlations to measure the linear relationships between different trends.ResultsOur results showed that for states and territories with higher numbers of daily cases, the historical trends in search queries related to bars and restaurants, which mainly occurred after reopening, significantly affected the number of daily new cases on average. California, for example, showed the most searches for restaurants on June 7, 2020; this affected the number of new cases within two weeks after the peak, with a P value of .004 for the Granger causality test.ConclusionsAlthough a limited number of search queries were considered, Google search trends for restaurants and bars showed a significant effect on daily new cases in US states and territories with higher numbers of daily new cases. We showed that these influential search trends can be used to provide additional information for prediction tasks regarding new cases in each region. These predictions can help health care leaders manage and control the impact of the COVID-19 outbreak on society and prepare for its outcomes.     

Predicting the Number of Suicides in Japan Using Internet Search Queries: Vector Autoregression Time Series Model

BackgroundThe number of suicides in Japan increased during the COVID-19 pandemic. Predicting the number of suicides is important to take timely preventive measures.ObjectiveThis study aims to clarify whether the number of suicides can be predicted by suicide-related search queries used before searching for the keyword “suicide.”MethodsThis study uses the infoveillance approach for suicide in Japan by search trends in search engines. The monthly number of suicides by gender, collected and published by the National Police Agency, was used as an outcome variable. The number of searches by gender with queries associated with “suicide” on “Yahoo! JAPAN Search” from January 2016 to December 2020 was used as a predictive variable. The following five phrases highly relevant to suicide were used as search terms before searching for the keyword “suicide” and extracted and used for analyses: “abuse”; “work, don’t want to go”; “company, want to quit”; “divorce”; and “no money.” The augmented Dickey-Fuller and Johansen tests were performed for the original series and to verify the existence of unit roots and cointegration for each variable, respectively. The vector autoregression model was applied to predict the number of suicides. The Breusch-Godfrey Lagrangian multiplier (BG-LM) test, autoregressive conditional heteroskedasticity Lagrangian multiplier (ARCH-LM) test, and Jarque-Bera (JB) test were used to confirm model convergence. In addition, a Granger causality test was performed for each predictive variable.ResultsIn the original series, unit roots were found in the trend model, whereas in the first-order difference series, both men (minimum tau 3: −9.24; max tau 3: −5.38) and women (minimum tau 3: −9.24; max tau 3: −5.38) had no unit roots for all variables. In the Johansen test, a cointegration relationship was observed among several variables. The queries used in the converged models were “divorce” for men (BG-LM test: P=.55; ARCH-LM test: P=.63; JB test: P=.66) and “no money” for women (BG-LM test: P=.17; ARCH-LM test: P=.15; JB test: P=.10). In the Granger causality test for each variable, “divorce” was significant for both men (F₁₀₄=3.29; P=.04) and women (F₁₀₄=3.23; P=.04).ConclusionsThe number of suicides can be predicted by search queries related to the keyword “suicide.” Previous studies have reported that financial poverty and divorce are associated with suicide. The results of this study, in which search queries on “no money” and “divorce” predicted suicide, support the findings of previous studies. Further research on the economic poverty of women and those with complex problems is necessary.     

Using Machine Learning to Compare Provaccine and Antivaccine Discourse Among the Public on Social Media: Algorithm Development Study

BackgroundDespite numerous counteracting efforts, antivaccine content linked to delays and refusals to vaccinate has grown persistently on social media, while only a few provaccine campaigns have succeeded in engaging with or persuading the public to accept immunization. Many prior studies have associated the diversity of topics discussed by antivaccine advocates with the public’s higher engagement with such content. Nonetheless, a comprehensive comparison of discursive topics in pro- and antivaccine content in the engagement-persuasion spectrum remains unexplored.ObjectiveWe aimed to compare discursive topics chosen by pro- and antivaccine advocates in their attempts to influence the public to accept or reject immunization in the engagement-persuasion spectrum. Our overall objective was pursued through three specific aims as follows: (1) we classified vaccine-related tweets into provaccine, antivaccine, and neutral categories; (2) we extracted and visualized discursive topics from these tweets to explain disparities in engagement between pro- and antivaccine content; and (3) we identified how those topics frame vaccines using Entman’s four framing dimensions.MethodsWe adopted a multimethod approach to analyze discursive topics in the vaccine debate on public social media sites. Our approach combined (1) large-scale balanced data collection from a public social media site (ie, 39,962 tweets from Twitter); (2) the development of a supervised classification algorithm for categorizing tweets into provaccine, antivaccine, and neutral groups; (3) the application of an unsupervised clustering algorithm for identifying prominent topics discussed on both sides; and (4) a multistep qualitative content analysis for identifying the prominent discursive topics and how vaccines are framed in these topics. In so doing, we alleviated methodological challenges that have hindered previous analyses of pro- and antivaccine discursive topics.ResultsOur results indicated that antivaccine topics have greater intertopic distinctiveness (ie, the degree to which discursive topics are distinct from one another) than their provaccine counterparts (t₁₂₂=2.30, P=.02). In addition, while antivaccine advocates use all four message frames known to make narratives persuasive and influential, provaccine advocates have neglected having a clear problem statement.ConclusionsBased on our results, we attribute higher engagement among antivaccine advocates to the distinctiveness of the topics they discuss, and we ascribe the influence of the vaccine debate on uptake rates to the comprehensiveness of the message frames. These results show the urgency of developing clear problem statements for provaccine content to counteract the negative impact of antivaccine content on uptake rates.     

The Reliability of Tweets as a Supplementary Method of Seasonal Influenza Surveillance

Background

Existing influenza surveillance in the United States is focused on the collection of data from sentinel physicians and hospitals; however, the compilation and distribution of reports are usually delayed by up to 2 weeks. With the popularity of social media growing, the Internet is a source for syndromic surveillance due to the availability of large amounts of data. In this study, tweets, or posts of 140 characters or less, from the website Twitter were collected and analyzed for their potential as surveillance for seasonal influenza.

Objective

There were three aims: (1) to improve the correlation of tweets to sentinel-provided influenza-like illness (ILI) rates by city through filtering and a machine-learning classifier, (2) to observe correlations of tweets for emergency department ILI rates by city, and (3) to explore correlations for tweets to laboratory-confirmed influenza cases in San Diego.

Methods

Tweets containing the keyword “flu” were collected within a 17-mile radius from 11 US cities selected for population and availability of ILI data. At the end of the collection period, 159,802 tweets were used for correlation analyses with sentinel-provided ILI and emergency department ILI rates as reported by the corresponding city or county health department. Two separate methods were used to observe correlations between tweets and ILI rates: filtering the tweets by type (non-retweets, retweets, tweets with a URL, tweets without a URL), and the use of a machine-learning classifier that determined whether a tweet was “valid”, or from a user who was likely ill with the flu.

Results

Correlations varied by city but general trends were observed. Non-retweets and tweets without a URL had higher and more significant (P<.05) correlations than retweets and tweets with a URL. Correlations of tweets to emergency department ILI rates were higher than the correlations observed for sentinel-provided ILI for most of the cities. The machine-learning classifier yielded the highest correlations for many of the cities when using the sentinel-provided or emergency department ILI as well as the number of laboratory-confirmed influenza cases in San Diego. High correlation values (r=.93) with significance at P<.001 were observed for laboratory-confirmed influenza cases for most categories and tweets determined to be valid by the classifier.

Conclusions

Compared to tweet analyses in the previous influenza season, this study demonstrated increased accuracy in using Twitter as a supplementary surveillance tool for influenza as better filtering and classification methods yielded higher correlations for the 2013-2014 influenza season than those found for tweets in the previous influenza season, where emergency department ILI rates were better correlated to tweets than sentinel-provided ILI rates. Further investigations in the field would require expansion with regard to the location that the tweets are collected from, as well as the availability of more ILI data.     

The Impact of Public Health Events on COVID-19 Vaccine Hesitancy on Chinese Social Media: National Infoveillance Study

BackgroundThe ongoing COVID-19 pandemic has brought unprecedented challenges to every country worldwide. A call for global vaccination for COVID-19 plays a pivotal role in the fight against this virus. With the development of COVID-19 vaccines, public willingness to get vaccinated has become an important public health concern, considering the vaccine hesitancy observed worldwide. Social media is powerful in monitoring public attitudes and assess the dissemination, which would provide valuable information for policy makers.ObjectiveThis study aimed to investigate the responses of vaccine positivity on social media when major public events (major outbreaks) or major adverse events related to vaccination (COVID-19 or other similar vaccines) were reported.MethodsA total of 340,783 vaccine-related posts were captured with the poster’s information on Weibo, the largest social platform in China. After data cleaning, 156,223 posts were included in the subsequent analysis. Using pandas and SnowNLP Python libraries, posts were classified into 2 categories, positive and negative. After model training and sentiment analysis, the proportion of positive posts was computed to measure the public positivity toward the COVID-19 vaccine.ResultsThe positivity toward COVID-19 vaccines in China tends to fluctuate over time in the range of 45.7% to 77.0% and is intuitively correlated with public health events. In terms of gender, males were more positive (70.0% of the time) than females. In terms of region, when regional epidemics arose, not only the region with the epidemic and surrounding regions but also the whole country showed more positive attitudes to varying degrees. When the epidemic subsided temporarily, positivity decreased with varying degrees in each region.ConclusionsIn China, public positivity toward COVID-19 vaccines fluctuates over time and a regional epidemic or news on social media may cause significant variations in willingness to accept a vaccine. Furthermore, public attitudes toward COVID-19 vaccination vary from gender and region. It is crucial for policy makers to adjust their policies through the use of positive incentives with prompt responses to pandemic-related news to promote vaccination acceptance.     

Finding the Patient’s Voice Using Big Data: Analysis of Users’ Health-Related Concerns in the ChaCha Question-and-Answer Service (2009–2012)

BackgroundThe development of effective health care and public health interventions requires a comprehensive understanding of the perceptions, concerns, and stated needs of health care consumers and the public at large. Big datasets from social media and question-and-answer services provide insight into the public’s health concerns and priorities without the financial, temporal, and spatial encumbrances of more traditional community-engagement methods and may prove a useful starting point for public-engagement health research (infodemiology).ObjectiveThe objective of our study was to describe user characteristics and health-related queries of the ChaCha question-and-answer platform, and discuss how these data may be used to better understand the perceptions, concerns, and stated needs of health care consumers and the public at large.MethodsWe conducted a retrospective automated textual analysis of anonymous user-generated queries submitted to ChaCha between January 2009 and November 2012. A total of 2.004 billion queries were read, of which 3.50% (70,083,796/2,004,243,249) were missing 1 or more data fields, leaving 1.934 billion complete lines of data for these analyses.ResultsMales and females submitted roughly equal numbers of health queries, but content differed by sex. Questions from females predominantly focused on pregnancy, menstruation, and vaginal health. Questions from males predominantly focused on body image, drug use, and sexuality. Adolescents aged 12–19 years submitted more queries than any other age group. Their queries were largely centered on sexual and reproductive health, and pregnancy in particular.ConclusionsThe private nature of the ChaCha service provided a perfect environment for maximum frankness among users, especially among adolescents posing sensitive health questions. Adolescents’ sexual health queries reveal knowledge gaps with serious, lifelong consequences. The nature of questions to the service provides opportunities for rapid understanding of health concerns and may lead to development of more effective tailored interventions.