Dataset Information

Leveraging geotagged Twitter data to examine neighborhood happiness, diet, and physical activity.

ABSTRACT: Using publicly available, geotagged Twitter data, we created neighborhood indicators for happiness, food and physical activity for three large counties: Salt Lake, San Francisco and New York.We utilize 2.8 million tweets collected between February-August 2015 in our analysis. Geo-coordinates of where tweets were sent allow us to spatially join them to 2010 census tract locations. We implemented quality control checks and tested associations between Twitter-derived variables and sociodemographic characteristics.For a random subset of tweets, manually labeled tweets and algorithm labeled tweets had excellent levels of agreement: 73% for happiness; 83% for food, and 85% for physical activity. Happy tweets, healthy food references, and physical activity references were less frequent in census tracts with greater economic disadvantage and higher proportions of racial/ethnic minorities and youths.Social media can be leveraged to provide greater understanding of the well-being and health behaviors of communities-information that has been previously difficult and expensive to obtain consistently across geographies. More open access neighborhood data can enable better design of programs and policies addressing social determinants of health.

SUBMITTER: Nguyen QC

PROVIDER: S-EPMC5438210 | biostudies-literature | 2016 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Leveraging geotagged Twitter data to examine neighborhood happiness, diet, and physical activity.

Nguyen Quynh C QC Kath Suraj S Meng Hsien-Wen HW Li Dapeng D Smith Ken Robert KR VanDerslice James A JA Wen Ming M Li Feifei F

Applied geography (Sevenoaks, England) 20160701

<h4>Objectives</h4>Using publicly available, geotagged Twitter data, we created neighborhood indicators for happiness, food and physical activity for three large counties: Salt Lake, San Francisco and New York.<h4>Methods</h4>We utilize 2.8 million tweets collected between February-August 2015 in our analysis. Geo-coordinates of where tweets were sent allow us to spatially join them to 2010 census tract locations. We implemented quality control checks and tested associations between Twitter-deri ...[more]

PMID: 28533568

Similar Datasets

Project description:BackgroundSocial media technology such as Twitter allows users to share their thoughts, feelings, and opinions online. The growing body of social media data is becoming a central part of infodemiology research as these data can be combined with other public health datasets (eg, physical activity levels) to provide real-time monitoring of psychological and behavior outcomes that inform health behaviors. Currently, it is unclear whether Twitter data can be used to monitor physical activity levels.ObjectiveThe aim of this study was to establish the feasibility of using Twitter data to monitor physical activity levels by assessing whether the frequency and sentiment of physical activity-related tweets were associated with physical activity levels across the United States.MethodsTweets were collected from Twitter's application programming interface (API) between January 10, 2017 and January 2, 2018. We used Twitter's garden hose method of collecting tweets, which provided a random sample of approximately 1% of all tweets with location metadata falling within the United States. Geotagged tweets were filtered. A list of physical activity-related hashtags was collected and used to further classify these geolocated tweets. Twitter data were merged with physical activity data collected as part of the Behavioral Risk Factor Surveillance System. Multiple linear regression models were fit to assess the relationship between physical activity-related tweets and physical activity levels by county while controlling for population and socioeconomic status measures.ResultsDuring the study period, 442,959,789 unique tweets were collected, of which 64,005,336 (14.44%) were geotagged with latitude and longitude coordinates. Aggregated data were obtained for a total of 3138 counties in the United States. The mean county-level percentage of physically active individuals was 74.05% (SD 5.2) and 75.30% (SD 4.96) after adjusting for age. The model showed that the percentage of physical activity-related tweets was significantly associated with physical activity levels (beta=.11; SE 0.2; P<.001) and age-adjusted physical activity (beta=.10; SE 0.20; P<.001) on a county level while adjusting for both Gini index and education level. However, the overall explained variance of the model was low (R2=.11). The sentiment of the physical activity-related tweets was not a significant predictor of physical activity level and age-adjusted physical activity on a county level after including the Gini index and education level in the model (P>.05).ConclusionsSocial media data may be a valuable tool for public health organizations to monitor physical activity levels, as it can overcome the time lag in the reporting of physical activity epidemiology data faced by traditional research methods (eg, surveys and observational studies). Consequently, this tool may have the potential to help public health organizations better mobilize and target physical activity interventions.

Project description:BackgroundLocal destinations have previously been shown to be associated with higher levels of both physical activity and walking, but little is known about how the distribution of destinations is related to activity. Kernel density estimation is a spatial analysis technique that accounts for the location of features relative to each other. Using kernel density estimation, this study sought to investigate whether individuals who live near destinations (shops and service facilities) that are more intensely distributed rather than dispersed: 1) have higher odds of being sufficiently active; 2) engage in more frequent walking for transport and recreation.MethodsThe sample consisted of 2349 residents of 50 urban areas in metropolitan Melbourne, Australia. Destinations within these areas were geocoded and kernel density estimates of destination intensity were created using kernels of 400m (meters), 800m and 1200m. Using multilevel logistic regression, the association between destination intensity (classified in quintiles Q1(least)-Q5(most)) and likelihood of: 1) being sufficiently active (compared to insufficiently active); 2) walking≥4/week (at least 4 times per week, compared to walking less), was estimated in models that were adjusted for potential confounders.ResultsFor all kernel distances, there was a significantly greater likelihood of walking≥4/week, among respondents living in areas of greatest destinations intensity compared to areas with least destination intensity: 400m (Q4 OR 1.41 95%CI 1.02-1.96; Q5 OR 1.49 95%CI 1.06-2.09), 800m (Q4 OR 1.55, 95%CI 1.09-2.21; Q5, OR 1.71, 95%CI 1.18-2.48) and 1200m (Q4, OR 1.7, 95%CI 1.18-2.45; Q5, OR 1.86 95%CI 1.28-2.71). There was also evidence of associations between destination intensity and sufficient physical activity, however these associations were markedly attenuated when walking was included in the models.ConclusionsThis study, conducted within urban Melbourne, found that those who lived in areas of greater destination intensity walked more frequently, and showed higher odds of being sufficiently physically active-an effect that was largely explained by levels of walking. The results suggest that increasing the intensity of destinations in areas where they are more dispersed; and or planning neighborhoods with greater destination intensity, may increase residents' likelihood of being sufficiently active for health.

Project description:BackgroundAs one of the serious public health issues, vaccination refusal has been attracting more and more attention, especially for newly approved human papillomavirus (HPV) vaccines. Understanding public opinion towards HPV vaccines, especially concerns on social media, is of significant importance for HPV vaccination promotion.MethodsIn this study, we leveraged a hierarchical machine learning based sentiment analysis system to extract public opinions towards HPV vaccines from Twitter. English tweets containing HPV vaccines-related keywords were collected from November 2, 2015 to March 28, 2016. Manual annotation was done to evaluate the performance of the system on the unannotated tweets corpus. Followed time series analysis was applied to this corpus to track the trends of machine-deduced sentiments and their associations with different days of the week.ResultsThe evaluation of the unannotated tweets corpus showed that the micro-averaging F scores have reached 0.786. The learning system deduced the sentiment labels for 184,214 tweets in the collected unannotated tweets corpus. Time series analysis identified a coincidence between mainstream outcome and Twitter contents. A weak trend was found for "Negative" tweets that decreased firstly and began to increase later; an opposite trend was identified for "Positive" tweets. Tweets that contain the worries on efficacy for HPV vaccines showed a relative significant decreasing trend. Strong associations were found between some sentiments ("Positive", "Negative", "Negative-Safety" and "Negative-Others") with different days of the week.ConclusionsOur efforts on sentiment analysis for newly approved HPV vaccines provide us an automatic and instant way to extract public opinion and understand the concerns on Twitter. Our approaches can provide a feedback to public health professionals to monitor online public response, examine the effectiveness of their HPV vaccination promotion strategies and adjust their promotion plans.

Dataset Information

Leveraging geotagged Twitter data to examine neighborhood happiness, diet, and physical activity.

Publications

Leveraging geotagged Twitter data to examine neighborhood happiness, diet, and physical activity.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets