Development and Evaluation of an Obesity Ontology for Social Big Data Analysis

Abstract

ObjectivesThe aim of this study was to develop and evaluate an obesity ontology as a framework for collecting and analyzing unstructured obesity-related social media posts.MethodsThe obesity ontology was developed according to the ‘Ontology Development 101’. The coverage rate of the developed ontology was examined by mapping concepts and terms of the ontology with concepts and terms extracted from obesity-related Twitter postings. The structure and representative ability of the ontology was evaluated by nurse experts. We applied the ontology to the density analysis of keywords related to obesity types and management strategies and to the sentiment analysis of obesity and diet using social big data.ResultsThe developed obesity ontology was represented by 8 superclasses and 124 subordinate classes. The superclasses comprised ‘risk factors,’ ‘types,’ ‘symptoms,’ ‘complications,’ ‘assessment,’ ‘diagnosis,’ ‘management strategies,’ and ‘settings.’ The coverage rate of the ontology was 100% for the concepts and 87.8% for the terms. The evaluation scores for representative ability were higher than 4.0 out of 5.0 for all of the evaluation items. The density analysis of keywords revealed that the top-two posted types of obesity were abdomen and thigh, and the top-three posted management strategies were diet, exercise, and dietary supplements or drug therapy. Positive expressions of obesity-related postings has increased annually in the sentiment analysis.ConclusionsIt was found that the developed obesity ontology was useful to identify the most frequently used terms on obesity and opinions and emotions toward obesity posted by the geneal population on social media.

Identifying and prioritizing critical factors for promoting the implementation and usage of big data in healthcare

“…We selected four sub-factors including establishing data standardization, opening data between inter-and intra-organizations, securing data quality, and enhancing data privacy and security. These factors were selected from research done by Kim et al (2013), Heitmueller et al (2014), Kshetri (2014), Kuo et al (2014), Raghupathi and Raghupathi (2014), Vithiatharan (2014), and Song and Ryu (2015).…”

“…The infrastructure and IT capabilities for big data exist sufficiently in terms of advanced medical equipment supply, hospital operation systems based on IT, and bio and public care data storage. However, there are the challenges for the implementation and use of big data in the Korean healthcare sector, such as government support (Lee et al, 2014), fostering experts (Kim et al, 2013; Back, 2014; Lee et al, 2015), data privacy and security (Paik, 2014; Ko and Lim, 2014), technology development (Kim et al, 2013; Paik, 2014), and the application of data analytics (Lee et al, 2014).…”

“…Other studies have focused on the capabilities and policies for big data success in healthcare (e.g., Kim et al, 2013; Heitmueller et al, 2014, Wang et al, 2015b). Kim et al (2013) presented the directions of public policies including system development, utilization, and data infrastructure aspects. Heitmueller et al (2014) suggested data sharing, evidence data building, demand creating, capability securing, trust networks building, and legislating as policies in the United Kingdom.…”

“…Some studies have dealt with the potential benefits of big data in healthcare to national health systems or medical organizations (e.g., Groves et al, 2013; Darrel et al, 2014; Raghupathi and Raghupathi, 2014). Other studies have investigated the technological aspects (e.g., Kuo et al, 2014; Vithiatharan, 2014; Braunstein, 2015; Huang et al, 2015), the required capabilities (e.g., Wang et al, 2015b), and government policies (e.g., Kim et al, 2013; Heitmueller et al, 2014).…”

Sentiment Analysis of Social Media on Childhood Vaccination: Development of an Ontology

“…However, these methods are not sufficient for understanding the semantics of terms [21,22]. An ontology defining the meanings and inherent attributes of concepts, capturing relationships between them, and containing terms covering thesaurus, is required for social data analysis to solve this issue [21,23-25]. An ontology can help researchers understand the semantics of and the relationships between concepts when contextual knowledge is lacking.…”