Human social sensing is an untapped resource for computational social science

Galešić, Mirta; Bruin, Wändi Bruine de; Dalege, Jonas; Feld, Scott L.; Kreuter, Frauke; Olsson, Henrik; Prelec, Dražen; Stein, D. L.; Does, Tamara van der

doi:10.1038/s41586-021-03649-2

Cited by 63 publications

(43 citation statements)

References 209 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, in a high-level view, the interactions between human, thing, and environment are naturally existing (i.e., human-environment and human-robot interactions), and in practice the IoT sensing tasks are oftentimes not separated [74]. In detail, though health and social sensing paradigms might overlap in common participants (e.g., specific groups of people), technologies (e.g., IoT wearables), and/or objectives (e.g., well-being), health sensing focuses on improving individual medical care and population health outcomes [278], whereas social sensing aims at describing and understanding social trends, dynamics, and interests [73].…”

Section: Discussionmentioning

confidence: 99%

Graph Neural Networks in IoT: A Survey

Dong¹,

Tang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

The Internet of Things (IoT) boom has revolutionized almost every corner of people's daily lives: healthcare, home, transportation, manufacturing, supply chain, and so on. With the recent development of sensor and communication technologies, IoT devices including smart wearables, cameras, smartwatches, and autonomous vehicles can accurately measure and perceive their surrounding environment. Continuous sensing generates massive amounts of data and presents challenges for machine learning. Deep learning models (e.g., convolution neural networks and recurrent neural networks) have been extensively employed in solving IoT tasks by learning patterns from multi-modal sensory data. Graph Neural Networks (GNNs), an emerging and fast-growing family of neural network models, can capture complex interactions within sensor topology and have been demonstrated to achieve state-of-the-art results in numerous IoT learning tasks. In this survey, we present a comprehensive review of recent advances in the application of GNNs to the IoT field, including a deep dive analysis of GNN design in various IoT sensing environments, an overarching list of public data and source code from the collected publications, and future research directions. To keep track of newly published works, we collect representative papers and their open-source implementations and create a Github repository at GNN4IoT. CCS Concepts: • Human-centered computing → Ubiquitous and mobile computing systems and tools; • Computing methodologies → Neural networks.

show abstract

Section: Discussionmentioning

confidence: 99%

Graph Neural Networks in IoT: A Survey

Dong¹,

Tang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Second, the neighborhood-aggregated measures of visits to FF outlets may be capturing an indicator of social behaviors of a larger group. Because eating is strongly influenced by social and cultural factors 24 , the 'social signal' 25 captured by the aggregated measure may be additionally predictive of disease risk. Third, the indicators may be picking up other neighborhood-level risk factors for these diseases.…”

Section: Discussionmentioning

confidence: 99%

Investigating mobility-based fast food outlet visits as indicators of dietary intake and diet-related disease

Horn

Bell

Bueno

et al. 2021

Preprint

View full text Add to dashboard Cite

ImportanceExcessive consumption of fast food (FF) is associated with chronic disease. Population-level research on FF outlet visits is now possible with mobility data, however its usefulness as an indicator of FF intake and diet-related disease must be established.ObjectiveInvestigate whether FF outlet visits from mobility data are indicators of self-reported FF intake, obesity, and diabetes, and compared with self-reported intake, equivalent or better indicators of obesity and diabetes.Design, Setting, and ParticipantsA secondary analysis of data from a representative sample of 8,036 adult residents of Los Angeles County (LAC) from the 2011 Los Angeles County Health Survey (LACHS), and mobility data representing all geolocations between October 2016 - March 2017 of 243,644 anonymous and opted-in smartphone users in LAC.Main Outcomes and MeasuresMain outcomes were self-reported FF intake frequency (never, infrequent, moderate, frequent), obesity, and diabetes from LACHS. FF outlet visits were computed as the temporal frequency of FF visits (FF visits/time) and the ratio of visits to FF over all food outlets (FF visits/food), summarized over smartphone users in a neighborhood, scaled from 0-10, and linked to LACHS respondents by census tract.ResultsThe analytic sample included 5,447 LACHS respondents and 234,995 smartphone users with 14,498,850 visits to food outlets. FF outlet visits were significantly associated with self-reported FF intake (reference: never) for both FF visits/time (infrequent: odds ratio [OR], 1.13; 95% CI, 1.06-1.20; frequent: OR, 1.35; 95% CI, 1.28-1.42) and FF visits/food (infrequent: OR, 1.12; 95% CI, 1.06-1.17; frequent: OR, 1.28; 95% CI, 1.22-1.33). FF outlet visits were significantly associated with obesity (FF visits/time: adjusted OR [AOR], 1.16; 95% CI, 1.12-1.21; FF visits/food: AOR, 1.13; 95% CI, 1.10-1.17) and diabetes (FF visits/time: AOR, 1.15; 95% CI, 1.09-1.21; FF visits/food: AOR, 1.11; 95% CI, 1.07-1.16), adjusted for sociodemographic factors. Models of the association between FF outlet visits and obesity or diabetes had better fits than between self-reported FF intake and obesity or diabetes.Conclusions and relevanceThis study illustrates that population-scale mobility data provide useful, passively-collected indicators of FF intake and diet-related disease within large, diverse urban populations that may be better than self-report intake.Key PointsQuestionDo visits to fast food outlets observed in mobility data provide meaningful measures of fast food intake, and when compared with self-reported intake, equivalent or better indicators of diet-related disease?FindingsIn this cross-sectional Los Angeles County study from a survey of 8,036 adults and mobility data from 243,644 smartphone users with 14.5 million food outlet visits, neighborhood-level features representing visits to fast food outlets were significantly associated with self-reported fast food intake, significantly associated with obesity and diabetes, and were a better predictor of these diseases than self-reported fast food intake.MeaningMeasures of food behaviors observed in population-scale mobility data can provide meaningful indicators of food intake and diet-related diseases, and could complement existing dietary surveillance methods.

show abstract

“…With the advance of information and communication technologies (ICT) and the widespread use of mobile devices in recent years, new types of data are being generated, and the emergence of multi-source urban location data based on 'social sensing' (Galesic et al, 2021) provides a solid basis for fine-grained descriptions of the functional as well as spatial form of cities, which enables precise planning responses to various urban problems .…”

Section: Data Sourcementioning

confidence: 99%

Mobility and Beyond: Explore the Spatial and Functional Effect of Cycling ban on Huangpu District, Shanghai through crowd-sourcing data

Zhang¹,

Hong²

2021

Proceedings of the 57th ISOCARP World Planning Congress

View full text Add to dashboard Cite

Cycling is regarded as one of the most sustainable transportation methods in cities. However, under the need to improve motor traffic conditions in dense street space, the importance of cycling accessibility is often overlooked. This research takes Huangpu District, the cradle of modern-day Shanghai but is currently also the most restricted street segments for cycling activities, in order to explode the effect of cycling curb on urban space. Through emerging crowd-sourcing data that precisely reflects users' activities, this article aims to explore the mobility as well as functionality aspects of the cycling curb policy influence. It is found that current policy didn't provide enough cycling accessibility and route choice to an area with various cycling purpose, even though the streets with restrictions for non-motorized vehicles don't significantly deprive cyclists of their connectivity with urban vitality. Moreover, metro stations function as a key role in local cycling activities. Finally, authors provide a revision framework for the policy and planning making process in Huangpu District under the view of 'cycling-first' agenda.

show abstract

Human social sensing is an untapped resource for computational social science

Cited by 63 publications

References 209 publications

Graph Neural Networks in IoT: A Survey

Graph Neural Networks in IoT: A Survey

Investigating mobility-based fast food outlet visits as indicators of dietary intake and diet-related disease

Mobility and Beyond: Explore the Spatial and Functional Effect of Cycling ban on Huangpu District, Shanghai through crowd-sourcing data

Contact Info

Product

Resources

About