Depression in South Korean Adolescents Captured by Text and Opinion Mining of Social Big Data.

Depression in adolescence is recognized as an important social and public health issue that interferes with continued physical growth and increases the likelihood of other mental disorders. The goal of this study was to examine online documents posted by South Korean adolescents for 3 years through the text and opinion mining of collectable documents in order to capture their depression. The sample for this study was online text-based individual documents that contained depression-related words among adolescents, and these were collected from 215 social media websites in South Korea from 1 January 2012 to 31 December 2014. A sentiment lexicon was developed for adolescent depressive symptoms, and such sentiments were analyzed through opinion mining. The depressive symptoms in the present study were classified into nine categories as suggested by the Diagnostic and Statistical Manual for Mental Disorders, 5th Edition (DSM-5). The association analysis and decision tree analysis of data mining were used to build an efficient prediction model of adolescent depression. Opinion mining indicated that 15.5% were emotionally stable, 58.6% moderately stressed, and 25.9% highly distressed. Data mining revealed that the presence of depressed mood most of the day or nearly every day had the greatest effect on adolescents' depression. Social big data analysis may serve as a viable option for developing a timely response system for emotionally susceptible adolescents. The present study represents one of the first attempts to investigate depression in South Korean adolescents using text and opinion mining from three years of online documents that originally amounted to approximately 3.1 billion documents.

Exploring Future Signals of COVID-19 and Response to Information Diffusion Using Social Media Big Data.

COVID-19 is a respiratory infectious disease that first reported in Wuhan, China, in December 2019. With COVID-19 spreading to patients worldwide, the WHO declared it a pandemic on 11 March 2020. This study collected 1,746,347 tweets from the Korean-language version of Twitter between February and May 2020 to explore future signals of COVID-19 and present response strategies for information diffusion. To explore future signals, we analyzed the term frequency and document frequency of key factors occurring in the tweets, analyzing the degree of visibility and degree of diffusion. Depression, digestive symptoms, inspection, diagnosis kits, and stay home obesity had high frequencies. The increase in the degree of visibility was higher than the median value, indicating that the signal became stronger with time. The degree of visibility of the mean word frequency was high for disinfectant, healthcare, and mask. However, the increase in the degree of visibility was lower than the median value, indicating that the signal grew weaker with time. Infodemic had a higher degree of diffusion mean word frequency. However, the mean degree of diffusion increase rate was lower than the median value, indicating that the signal grew weaker over time. As the general flow of signal progression is latent signal → weak signal → strong signal → strong signal with lower increase rate, it is necessary to obtain active response strategies for stay home, inspection, obesity, digestive symptoms, online shopping, and asymptomatic.

Correction: A Determinants-of-Fertility Ontology for Detecting Future Signals of Fertility Issues From Social Media Data: Development of an Ontology.

[This corrects the article DOI: 10.2196/25028.].

A Determinants-of-Fertility Ontology for Detecting Future Signals of Fertility Issues From Social Media Data: Development of an Ontology.

BACKGROUND: South Korea has the lowest fertility rate in the world despite considerable governmental efforts to boost it. Increasing the fertility rate and achieving the desired outcomes of any implemented policies requires reliable data on the ongoing trends in fertility and preparations for the future based on these trends. OBJECTIVE: The aims of this study were to (1) develop a determinants-of-fertility ontology with terminology for collecting and analyzing social media data; (2) determine the description logics, content coverage, and structural and representational layers of the ontology; and (3) use the ontology to detect future signals of fertility issues. METHODS: An ontology was developed using the Ontology Development 101 methodology. The domain and scope of the ontology were defined by compiling a list of competency questions. The terms were collected from Korean government reports, Korea's Basic Plan for Low Fertility and Aging Society, a national survey about marriage and childbirth, and social media postings on fertility issues. The classes and their hierarchy were defined using a top-down approach based on an ecological model. The internal structure of classes was defined using the entity-attribute-value model. The description logics of the ontology were evaluated using Protégé (version 5.5.0), and the content coverage was evaluated by comparing concepts extracted from social media posts with the list of ontology classes. The structural and representational layers of the ontology were evaluated by experts. Social media data were collected from 183 online channels between January 1, 2011, and June 30, 2015. To detect future signals of fertility issues, 2 classes of the ontology, the socioeconomic and cultural environment, and public policy, were identified as keywords. A keyword issue map was constructed, and the defined keywords were mapped to identify future signals. R software (version 3.5.2) was used to mine for future signals. RESULTS: A determinants-of-fertility ontology comprised 236 classes and terminology comprised 1464 synonyms of the 236 classes. Concept classes in the ontology were found to be coherently and consistently defined. The ontology included more than 90% of the concepts that appeared in social media posts on fertility policies. Average scores for all of the criteria for structural and representations layers exceeded 4 on a 5-point scale. Violence and abuse (socioeconomic and cultural factor) and flexible working arrangement (fertility policy) were weak signals, suggesting that they could increase rapidly in the future. CONCLUSIONS: The determinants-of-fertility ontology developed in this study can be used as a framework for collecting and analyzing social media data on fertility issues and detecting future signals of fertility issues. The future signals identified in this study will be useful for policy makers who are developing policy responses to low fertility.

Using Social Media Data to Understand Consumers' Information Needs and Emotions Regarding Cancer: Ontology-Based Data Analysis Study.

BACKGROUND: Analysis of posts on social media is effective in investigating health information needs for disease management and identifying people's emotional status related to disease. An ontology is needed for semantic analysis of social media data. OBJECTIVE: This study was performed to develop a cancer ontology with terminology containing consumer terms and to analyze social media data to identify health information needs and emotions related to cancer. METHODS: A cancer ontology was developed using social media data, collected with a crawler, from online communities and blogs between January 1, 2014 and June 30, 2017 in South Korea. The relative frequencies of posts containing ontology concepts were counted and compared by cancer type. RESULTS: The ontology had 9 superclasses, 213 class concepts, and 4061 synonyms. Ontology-driven natural language processing was performed on the text from 754,744 cancer-related posts. Colon, breast, stomach, cervical, lung, liver, pancreatic, and prostate cancer; brain tumors; and leukemia appeared most in these posts. At the superclass level, risk factor was the most frequent, followed by emotions, symptoms, treatments, and dealing with cancer. CONCLUSIONS: Information needs and emotions differed according to cancer type. The observations of this study could be used to provide tailored information to consumers according to cancer type and care process. Attention should be paid to provision of cancer-related information to not only patients but also their families and the general public seeking information on cancer.

Social Big-Data Analysis of Particulate Matter, Health, and Society.

The study collected particulate matter (PM)-related documents in Korea and classified main keywords related to particulate matter, health, and social problems using text and opinion mining. The study attempted to present a prediction model for important causes related to particulate matter by using social big-data analysis. Topics related to particulate matter were collected from online (online news sites, blogs, cafés, social network services, and bulletin boards) from 1 January 2015, to 31 May 2016, and 226,977 text documents were included in the analysis. The present study applied machine-learning analysis technique to forecast the risk of particulate matter. Emotions related to particulate matter were found to be 65.4% negative, 7.7% neutral, and 27.0% positive. Intelligent services that can detect early and prevent unknown crisis situations of particulate matter may be possible if risk factors of particulate matter are predicted through the linkage of the machine-learning prediction model.

Application of Social Big Data to Identify Trends of School Bullying Forms in South Korea.

As the contemporary phenomenon of school bullying has become more widespread, diverse, and frequent among adolescents in Korea, social big data may offer a new methodological paradigm for understanding the trends of school bullying in the digital era. This study identified Term Frequency-Inverse Document Frequency (TF-IDF) and Future Signals of 177 school bullying forms to understand the current and future bullying experiences of adolescents from 436,508 web documents collected between 1 January 2013, and 31 December 2017. In social big data, sexual bullying rapidly increased, and physical and cyber bullying had high frequency with a high rate of growth. School bullying forms, such as "group assault" and "sexual harassment", appeared as Weak Signals, and "cyber bullying" was a Strong Signal. Findings considering five school bullying forms (verbal, physical, relational, sexual, and cyber bullying) are valuable for developing insights into the burgeoning phenomenon of school bullying.

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

BACKGROUND: Although vaccination rates are above the threshold for herd immunity in South Korea, a growing number of parents have expressed concerns about the safety of vaccines. It is important to understand these concerns so that we can maintain high vaccination rates. OBJECTIVE: The aim of this study was to develop a childhood vaccination ontology to serve as a framework for collecting and analyzing social data on childhood vaccination and to use this ontology for identifying concerns about and sentiments toward childhood vaccination from social data. METHODS: The domain and scope of the ontology were determined by developing competency questions. We checked if existing ontologies and conceptual frameworks related to vaccination can be reused for the childhood vaccination ontology. Terms were collected from clinical practice guidelines, research papers, and posts on social media platforms. Class concepts were extracted from these terms. A class hierarchy was developed using a top-down approach. The ontology was evaluated in terms of description logics, face and content validity, and coverage. In total, 40,359 Korean posts on childhood vaccination were collected from 27 social media channels between January and December 2015. Vaccination issues were identified and classified using the second-level class concepts of the ontology. The sentiments were classified in 3 ways: positive, negative or neutral. Posts were analyzed using frequency, trend, logistic regression, and association rules. RESULTS: Our childhood vaccination ontology comprised 9 superclasses with 137 subclasses and 431 synonyms for class, attribute, and value concepts. Parent's health belief appeared in 53.21% (15,709/29,521) of posts and positive sentiments appeared in 64.08% (17,454/27,236) of posts. Trends in sentiments toward vaccination were affected by news about vaccinations. Posts with parents' health belief, vaccination availability, and vaccination policy were associated with positive sentiments, whereas posts with experience of vaccine adverse events were associated with negative sentiments. CONCLUSIONS: The childhood vaccination ontology developed in this study was useful for collecting and analyzing social data on childhood vaccination. We expect that practitioners and researchers in the field of childhood vaccination could use our ontology to identify concerns about and sentiments toward childhood vaccination from social data.

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

[This corrects the article on p. 159 in vol. 23, PMID: 28875050.].

Longitudinal Trajectory of the Relationship Between Self-Esteem and Substance Use From Adolescence to Young Adulthood.

BACKGROUND: We examined the longitudinal trajectory of substance use (binge drinking, marijuana use, and cocaine use) in relation to self-esteem from adolescence to young adulthood. METHODS: Generalized estimating equation models were fit using SAS to investigate changes in the relation between self-esteem and each substance use (binge drinking, marijuana use, and cocaine use) from adolescence to young adulthood. Data were drawn from the 3 waves of the National Longitudinal Study of Adolescent Health, a nationally representative sample of middle and high school students in the United States (N = 6504). RESULTS: Self-esteem was a significant predictor for the use of all 3 substances at 15 years of age (ps < .001). However, at age 21, self-esteem no longer predicted binge drinking and marijuana use in the controlled model. CONCLUSIONS: It appears that self-esteem loses its protective role against substance use except cocaine use as adolescents transition to young adulthood.

Analysis of the Factors Affecting Consumer Acceptance of Accredited Online Health Information.

With the increasing use of the internet and the spread of smartphones, health information seekers obtain considerable information through the internet. As the amount of online health information increases, the need for quality management of health information has been emphasized. The purpose of this study was to investigate the factors affecting the intention of using accredited online health information by applying the extended technology acceptance model (Extended-TAM). An online survey was conducted from September 15, 2016 to October 3, 2016, on 500 men and women aged 19-69 years. The results showed that the greatest factor influencing the acceptance of the accredited health information was perceived usefulness, and the expectation for the quality of the accreditation system was the most important mediator variable. In order to establish the health information accreditation system as a means to provide easy and useful information to the consumers, it is necessary to carry out quality management and promote the system through the continuous monitoring of the accreditation system.

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

OBJECTIVES: The 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. METHODS: The 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. RESULTS: The 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. CONCLUSIONS: It 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.

Ontology-Based Approach to Social Data Sentiment Analysis: Detection of Adolescent Depression Signals.

BACKGROUND: Social networking services (SNSs) contain abundant information about the feelings, thoughts, interests, and patterns of behavior of adolescents that can be obtained by analyzing SNS postings. An ontology that expresses the shared concepts and their relationships in a specific field could be used as a semantic framework for social media data analytics. OBJECTIVE: The aim of this study was to refine an adolescent depression ontology and terminology as a framework for analyzing social media data and to evaluate description logics between classes and the applicability of this ontology to sentiment analysis. METHODS: The domain and scope of the ontology were defined using competency questions. The concepts constituting the ontology and terminology were collected from clinical practice guidelines, the literature, and social media postings on adolescent depression. Class concepts, their hierarchy, and the relationships among class concepts were defined. An internal structure of the ontology was designed using the entity-attribute-value (EAV) triplet data model, and superclasses of the ontology were aligned with the upper ontology. Description logics between classes were evaluated by mapping concepts extracted from the answers to frequently asked questions (FAQs) onto the ontology concepts derived from description logic queries. The applicability of the ontology was validated by examining the representability of 1358 sentiment phrases using the ontology EAV model and conducting sentiment analyses of social media data using ontology class concepts. RESULTS: We developed an adolescent depression ontology that comprised 443 classes and 60 relationships among the classes; the terminology comprised 1682 synonyms of the 443 classes. In the description logics test, no error in relationships between classes was found, and about 89% (55/62) of the concepts cited in the answers to FAQs mapped onto the ontology class. Regarding applicability, the EAV triplet models of the ontology class represented about 91.4% of the sentiment phrases included in the sentiment dictionary. In the sentiment analyses, "academic stresses" and "suicide" contributed negatively to the sentiment of adolescent depression. CONCLUSIONS: The ontology and terminology developed in this study provide a semantic foundation for analyzing social media data on adolescent depression. To be useful in social media data analysis, the ontology, especially the terminology, needs to be updated constantly to reflect rapidly changing terms used by adolescents in social media postings. In addition, more attributes and value sets reflecting depression-related sentiments should be added to the ontology.

Social Big Data Analysis of Information Spread and Perceived Infection Risk During the 2015 Middle East Respiratory Syndrome Outbreak in South Korea.

We investigated online diffusion of information, spread of fear, and perceived risk of infection to Middle East Respiratory Syndrome (MERS) as cases of MERS spread rapidly and dozens of fatalities occurred in South Korea in May-June of 2015. This study retrieved 8,671,695 MERS-related online documents from May 20 to June 18, 2015, from 171 Korean online channels and analyzed such documents by using multilevel models and data mining with Apriori algorithm association analysis. We used R software (version 3.2.1) for the association analysis data mining and visualization. Buzz with negative emotions (i.e., anxiety or fear) was more prevalent in online discussion boards, Twitter, and online cafes than news sites and blogs. News buzz (b = 0.21, p < 0.001), but not rumor buzz (b = 0.06, p = 0.308), was associated with positive MERS emotions (i.e., being calm or composed). The mention of eating immunity-boosting food in the news led to a 94 percent chance of a positive MERS emotion and that such a chance of showing a positive emotion was 4.75 times higher than that without such a mention (support of 0.001, confidence of 0.94, and lift of 4.75). Even with the same precautionary messages that were disseminated, they yielded the opposite emotional reactions to people depending on the channel through which the messages were communicated. In the face of a novel and highly contagious disease such as MERS, the government must deploy a response system that includes provision and dissemination of reliable information and inhibits online diffusion of false information.

Data Mining of Web-Based Documents on Social Networking Sites That Included Suicide-Related Words Among Korean Adolescents.

PURPOSE: To investigate online search activity of suicide-related words in South Korean adolescents through data mining of social media Web sites as the suicide rate in South Korea is one of the highest in the world. METHODS: Out of more than 2.35 billion posts for 2 years from January 1, 2011 to December 31, 2012 on 163 social media Web sites in South Korea, 99,693 suicide-related documents were retrieved by Crawler and analyzed using text mining and opinion mining. These data were further combined with monthly employment rate, monthly rental prices index, monthly youth suicide rate, and monthly number of reported bully victims to fit multilevel models as well as structural equation models. RESULTS: The link from grade pressure to suicide risk showed the largest standardized path coefficient (beta = .357, p < .001) in structural models and a significant random effect (p < .01) in multilevel models. Depression was a partial mediator between suicide risk and grade pressure, low body image, victims of bullying, and concerns about disease. The largest total effect was observed in the grade pressure to depression to suicide risk. The multilevel models indicate about 27% of the variance in the daily suicide-related word search activity is explained by month-to-month variations. A lower employment rate, a higher rental prices index, and more bullying were associated with an increased suicide-related word search activity. CONCLUSIONS: Academic pressure appears to be the biggest contributor to Korean adolescents' suicide risk. Real-time suicide-related word search activity monitoring and response system needs to be developed.

Development and Evaluation of an Adolescents' Depression Ontology for Analyzing Social Data.

This study aims to develop and evaluate an ontology for adolescents' depression to be used for collecting and analyzing social data. The ontology was developed according to the 'ontology development 101' methodology. Concepts were extracted from clinical practice guidelines and related literatures. The ontology is composed of five sub-ontologies which represent risk factors, sign and symptoms, measurement, diagnostic result and management care. The ontology was evaluated in four different ways: First, we examined the frequency of ontology concept appeared in social data; Second, the content coverage of ontology was evaluated by comparing ontology concepts with concepts extracted from the youth depression counseling records; Third, the structural and representational layer of the ontology were evaluated by 5 ontology and psychiatric nursing experts; Fourth, the scope of the ontology was examined by answering 59 competency questions. The ontology was improved by adding new concepts and synonyms and revising the level of structure.

Development and Evaluation of a Low Fertility Ontology for Analyzing Social Data in Korea.

The purpose of this study is to develop a low fertility ontology for collecting and analyzing social data. A low fertility ontology was developed according to Ontology Development 101 and formally represented using Protégé. The content coverage of the ontology was evaluated using 1,387 narratives posted by the public and 63 narratives posted by public servants. Six super-classes of the ontology were developed based on Bronfenbrenner's ecological system theory with an individual in the center and environmental systems impacting their as surroundings. In total, 568 unique concepts were extracted from the narratives. Out of these concepts, 424(74.6%) concepts were lexically or semantically mapped, 67(11.8%) were either broadly or narrowly mapped to the ontology concepts. Remaining 77(13.6%) concepts were not mapped to any of the ontology concepts. This ontology can be used as a framework to understand low fertility problems using social data in Korea.

Stress, Depression, and Lifestyle Behaviors in Korean Adults: A Latent Means and Multi-Group Analysis on the Korea Health Panel Data.

It has been reported that stress can induce depression, with the patient's age and sex as moderating factors. Associations between depression and lifestyle in Korean adults have not been addressed. This study was designed to examine if the relationships among stress, problem drinking, exercise, and depression differ by age and sex. For this study, the Korea health panel data was utilized, and a structural equation model using AMOS was employed. The major findings were as follows: women were more likely to experience stress and depression than men. Individuals over 40 showed a higher tendency toward stress and depression than those under 40. Age- and sex-specific paths from stress to problem drinking, exercise, and depression were positively inter-correlated; the path from exercise to depression indicated an inverse association. These results indicate the need for evidence-based stress-management programs for the psychological well-being of Korean adults.

Development of an Adolescent Depression Ontology for Analyzing Social Data.

Depression in adolescence is associated with significant suicidality. Therefore, it is important to detect the risk for depression and provide timely care to adolescents. This study aims to develop an ontology for collecting and analyzing social media data about adolescent depression. This ontology was developed using the 'ontology development 101'. The important terms were extracted from several clinical practice guidelines and postings on Social Network Service. We extracted 777 terms, which were categorized into 'risk factors', 'sign and symptoms', 'screening', 'diagnosis', 'treatment', and 'prevention'. An ontology developed in this study can be used as a framework to understand adolescent depression using unstructured data from social media.

Big data analysis framework for healthcare and social sectors in Korea.

OBJECTIVES: We reviewed applications of big data analysis of healthcare and social services in developed countries, and subsequently devised a framework for such an analysis in Korea. METHODS: We reviewed the status of implementing big data analysis of health care and social services in developed countries, and strategies used by the Ministry of Health and Welfare of Korea (Government 3.0). We formulated a conceptual framework of big data in the healthcare and social service sectors at the national level. As a specific case, we designed a process and method of social big data analysis on suicide buzz. RESULTS: Developed countries (e.g., the United States, the UK, Singapore, Australia, and even OECD and EU) are emphasizing the potential of big data, and using it as a tool to solve their long-standing problems. Big data strategies for the healthcare and social service sectors were formulated based on an ICT-based policy of current government and the strategic goals of the Ministry of Health and Welfare. We suggest a framework of big data analysis in the healthcare and welfare service sectors separately and assigned them tentative names: 'health risk analysis center' and 'integrated social welfare service network'. A framework of social big data analysis is presented by applying it to the prevention and proactive detection of suicide in Korea. CONCLUSIONS: There are some concerns with the utilization of big data in the healthcare and social welfare sectors. Thus, research on these issues must be conducted so that sophisticated and practical solutions can be reached.