소셜 빅데이터와 Google 검색트렌드를 활용한 한국과 미국의 사이버불링 검색에 영향을 미치는 요인 분석

송태민,송주영,천미경,Song, Tae-Min,Song, Juyoung,Cheon, Mi-Kyung 한국빅데이터학회 2016 한국빅데이터학회 학회지 Vol.1 No.1

본 연구의 목적은 소셜 빅데이터와 Google 검색 트렌드를 활용하여 한국과 미국의 사이버불링 검색에 영향을 미치는 요인을 분석하는 것이다. 한국의 사이버불링 요인 분석은 2011년 1월 1일부터 2013년 3월 31일까지 총 227개 소셜미디어에서 수집된 검색통계를 활용하였고, 미국은 2004년 1월 1일부터 2013년 12월 22일까지 구글 검색트렌드에서 검색된 검색량을 분석대상으로 하였다. 첫째 위계적 회귀분석결과 스트레스가 사이버불링에 미치는 영향은 한국이 미국보다 많은 것으로 나타났다. 둘째 다중집단 구조모형 분석결과 한국과 미국 모두 스트레스에서 운동, 음주, 사이버불링으로 가는 경로가 정적(+)으로 유의한 영향을 미치는 것으로 나타났다. 셋째, 한국과 미국은 모든 경로에서 집단 간 유의미한 차이를 보이고 있으며, '스트레스 ${\rightarrow}$ 운동', '스트레스 ${\rightarrow}$ 음주', '음주 ${\rightarrow}$ 사이버불링', '스트레스 ${\rightarrow}$ 사이버불링' 경로가 한국이 미국보다 더 유의하게 강하게 나타났다. 한국의 청소년과 성인은 사이버불링과 관련한 담론을 주고받으며, 이러한 언급이 실제적인 사이버불링과 관련된 심리적 행동적 특성으로 노출이 될 수 있기 때문에 SNS상에 사이버불링 행위에 대한 위험징후가 예측되면 실시간으로 개입할 수 있는 온라인 애플리케이션이 개발되어야 할 것이다. The study analyzed big data extracted from Google and social media to identify factors related to searches on cyber bullying in Korea and America. Korea's cyber bullying analysis was conducted social big data collected from online news sites, blogs, $caf{\acute{e}}s$, social network services and message for between January 1, 2011 and March 31, 2013. Google search trends for the search words of stress, exercise, drinking, and cyber bullying were obtained for January 1, 2004 and December 22, 2013. The main results of this study were as follows: first, the significant factors stress were cyber bullying that Korea more than America. Secondly, a positive relationship was found between stress and drinking, exercise and cyber bullying both Korea and America. Thirdly, significant differences were found all path both Korea and America. The study shows that both adults and teenagers are influenced in Korea. We need to develop online application that if cyber bullying behavior was predicted can intervene in real time because these actual cyber bullying-related exposure to psychological and behavioral characteristic.

DEA 모형을 이용한 의료기관의 정보화 효율성 측정에 관한 연구

송태민,김우식,Song, Tae-Min,Kim, U-Sik 한국정보처리학회 2001 정보처리학회논문지D Vol.8 No.6

의료기관의 정보화 평가와 관련된 연구로는 주로 정보화 성과를 측정하기 위한 요소를 찾아내는 연구가 대부분으로 연구자 각자의 주관적인 척도를 사용함으로써 그 결과를 계량화·객관화하기가 적합하지 못하였다. 본 연구는 다수의 동질적 기관의 다수투입·다수산출의 효율성을 상대적으로 평가하기 위한 방법인 DEA(Data Envelopment Analysis; 자료포괄분석) 모형을 적용하여 의료기관의 정보화 효율성을 객관적으로 측정할 수 있는 가능성을 제시하였다. 이에 대한 사례적용으로 DEA모형을 이용하여 국내 3차 의료기관의 정보자원 활용정도에 대한 상대적인 효율성 평가와 분석을 실시하였다. 그 결과 효율성이 1.0인 의료기관은 다수투입수준에 비해 다수산출수준이 높은 기관으로 정보자원 활용정도가 양호한 기관으로 평가될 수 있고, 반면에 효율성이 1.0 미만인 의료기관들은 다수투입수준에 비해 다수산출수준이 대체로 낮은 기관으로서 정보자원의 활용정도가 상대적으로 낮은 기관으로 평가할 수 있으며, 다수 정보자원 활용의 효율성 제고를 위한 계량적 개선조치가 필요한 것으로 분석되었다. Since most of studies for information efficiency measurement of healthcare organizations have mainly focused on searching a measuring standard used for performance of informatization and each researchers subjective standard having been used, they can not be easily measured and objective. This study showed a possibility that efficiency measurement of healthcare organization can be performed by solving a problem related to objectiveness, which may occur in measuring many organization with many measuring items, with DEA (data envelopment analysis). For proving this possibility, efficiency evaluation and analysis for information resources utilization of domestic tertiary healthcare organizations have been performed by using DEA model. As a result, DMU (decision making unit) having efficiency rate of 1 will be evaluated that output is higher than input and information resources are being used efficiently, but on the other hand, DMU having efficiency rate of below 1 will be evaluated that output is lower than input and information resources are being used inefficiently, which is required to be improved.

소셜 빅데이터를 활용한 담배 위험 예측

송태민,송주영,천미경,Song, Tae Min,Song, Juyoung,Cheon, Mi Kyung 한국데이터정보과학회 2015 한국데이터정보과학회지 Vol.26 No.5

본 연구는 국내의 블로그, 카페, SNS 등 인터넷을 통해 수집된 소셜 빅데이터를 데이터마이닝 분석 기법을 적용하여 우리나라 국민의 담배에 대한 위험요인을 예측하고자 하였다. 주요분석 결과는 다음과 같다. 첫째, 온라인상에 '담뱃값인상'이 언급될 경우 담배에 대한 일반군 (negative)이 58.6%에서 74.8%로 증가하며, '폐암'이 언급될 경우 73.1%로 증가하는 것으로 나타났다. 둘째, 담뱃값인상 이후 담배에 대한 위험군 (positive)은 5.6% 감소하고, 일반군은 6.1% 증가한 것으로 나타났다. 셋째, 'FCTC, 담뱃값인상, 금연관련법, 흡연규제, 금연광고, 금연사업'과 관련된 정책이 온라인상에 많이 언급될수록 담배에 대한 위험군이 감소하는 것으로 나타났다. 마지막으로 '금연약, 금연패치, 금연껌'이 온라인 상에 언급될수록 담배에 대한 위험군이 감소하나, '전자담배와 보조제'가 온라인상에 언급될수록 담배에 대한 위험군을 증가시키는 것으로 나타났다. This study will predict risk factors associated with cigarettes in Korea by analyzing the social big data collected from the internet such as blogs, cafes, and SNSes in Korea, using data mining techniques. The key analysis results are as follows. First, when "raising cigarette price"is mentioned online, the negative group (i.e., the proportion of people holding negative views about smoking) increased from 58.6% to 74.8%, and when "lung cancer" is mentioned, it increased to 73.1%. Second, with regard to cigarettes in general, the positive group (i.e., the proportion of people holding positive views about smoking) decreased by 5.6% after the raising of cigarette prices, while the negative group increased by 6.1%. Third, when policies related to "FCTC, raising cigarette price, non-smoking laws, smoking regulations, non-smoking ads, and nonsmoking business" are more frequently mentioned online, the positive group tended to decrease. Finally, when "non-smoking drugs, non-smoking patches, and non-smoking gums" are more frequently mentioned online, the positive group tended to decrease. However, when "electronic cigarettes and supplements" are more frequently mentioned online, the positive group increased.

소셜 빅데이터 기반 저출산 정책 수요분석

송태민(Tae Min Song) 통계청 통계개발원 2016 통계연구 Vol.- No.특별호

인터넷과 모바일 금연교육프로그램의 효과 비교분석

송태민(Tae-Min Song),최지혜(Ji-Hye Choi),김혜경(Hye-Kyeong Kim) 한국보건교육건강증진학회 2004 보건교육건강증진학회지 Vol.21 No.3

The potential contribution of the internet and mobile phone to smoking cessation seems huge, given that a majority of Koreans now use internet and have mobile phones. The Korean Ministry of Health and Welfare developed and has been offering an internet-based smoking cessation program from the January, 2002 and a mobile-based program from the April, 2004. Despite the anticipated effectiveness of internet and mobile-based smoking cessation programs, there is little empirical evidence regarding the efficacy of both types of programs. Therefore, this study intended to evaluate the effectiveness of an internet and a mobile-based smoking cessation program and to provide the basic database for the development of effective smoking cessation strategies for the health promotion for the whole nation. Cessation and satisfaction data were obtained from the 434 participants in both programs. The data were analysed for the comparison of quit-smoking rate and the degree of satisfaction between an internet smoking cessation program and a mobile smoking cessation program. The main results of this study were as follows: 1. For the internet program participants, there were statistically significant differences in cessation rate by gender(P<0.05) and age(P<0.01). In contrast, none of general characteristics provided statistically significant differences in cessation rate for the mobile program participants. 2. For the internet program participants, smoking related characteristics(average smoking amount and the reasons for smoking) didn't have an effect on smoking cessation. But, for mobile program participants, there was a statistically significant difference in cessation rate by the reasons for smoking(P<0.05). 3. The cessation rate was 31.9%(abstinence for the previous 30 days) for internet program participants and 17.8% for mobile program participants.

소셜 빅 데이터를 활용한 자살검색 요인 다변량 분석

송태민(Tae Min Song),송주영(Juyoung Song),안지영(An Ji-Young),진달래(Jin Dallae) 한국보건교육건강증진학회 2013 보건교육건강증진학회지 Vol.30 No.3

Objectives: The study is aimed at examining the individual reasons and regional/environmental factors of online search on suicide using social big data to predict practical behaviors related to suicide and to develop an online suicide prevention system on the governmental level. Methods: The study was conducted using suicide-related social big data collected from online news sites, blogs, cafes, social network services and message boards between January 1 and December 31, 2011 (321,506 buzzes from users assumed as adults and 67,742 buzzes from those assumed as teenagers). Technical analysis and development of the suicide search prediction model were done using SPSS 20.0, and the structural model, nd multi-group analysis was made using AMOS 20.0. Also, HLM 7.0 was applied for the multilevel model analysis of the determinants of search on suicide by teenagers. Results: A summary of the results of multivariate analysis is as follows. First, search on suicide by adults appeared to increase on days when there were higher number of suicide incidents, higher number of search on drinking, higher divorce rate, lower birth rate and higher average humidity. Second, search on suicide by teenagers rose on days when there were higher number of teenage suicide incidents, higher number of search on stress or drinking and less fine dust particles. Third, the comparison of the results of the structural equation model analysis of search on suicide by adults and teenagers showed that teenagers were more likely to proceed from search on stress to search on sports, drinking and suicide, while adults significantly tended to move from search on drinking to search on suicide. Fourth, the result of the multilevel model analysis of determinants of search on suicide by teenagers showed that monthly teenagers suicide rate and average humidity had positive effect on the amount of search on suicide. Conclusions: The study shows that both adults and teenagers are influenced by various reasons to experience stress and search on suicide on the Internet. Therefore, we need to develop diverse school-level programs that can help relieve teenagers of stress and workplace-level programs to get rid of the work-related stress of adults.

다층모형을 통한 금연성공에 영향을 미치는 요인 분석

송태민(Tae Min Song),이주열(Ju Yul Lee) 한국보건교육건강증진학회 2013 보건교육건강증진학회지 Vol.30 No.1

Objectives: In this study, a multilevel analysis model has been designed to investigate the effect of personal characteristics associated with smoking cessation on anti-smoking determinants with a goal of finding out the factors which have influence on smoking cessation among the entrants of smoking cessation clinic in a public health center. Methods: A total of 253,136 male smokers who received smoking cessation services for more than six(6) months in a smoking cessation clinic of public health center from July 16, 2007 to July 15, 2008 were examined. For technical analysis, SPSS Version 2.0 has been used. For multilevel analysis on smoking cessation determinants, in addition, HLM 7.0 has been adopted. Results: According to the unconditional model of multilevel analysis, the success rates of smoking cessation among the entrants of a smoking cessation clinic were 47.3%. In an unconditional slope model test to which regional variables were added, a negative effect was observed in average smoking amount, total smoking period, nicotine dependence and services while a positive effect was found in age, stress and type of social security in terms of the log of the odds of smoking cessation. In a conditional model test, a positive effect was observed in Non-Smoking Campaigns (NSC) and Frequency of Counseling (FC) in terms of the log of the odds of smoking cessation in regional variables. Conclusions: It is important to approach smokers individually and, at the same time, build healthy environment for a local community to increase smoking cessation rates among the entrants of smoking cessation clinic in a public health center.

보건소 금연클리닉 신규등록자와 재등록자의 금연 성공요인 분석

송태민(Tae Min Song),이주열(Ju Yul Lee),조경숙(Kyung Sook Cho) 한국보건교육건강증진학회 2008 보건교육건강증진학회지 Vol.25 No.2

This study has comparatively analyzed the primary success factors in smoking cessation among new enrollees and re-enrollees of a smoking cessation clinic in order to find out how to efficiently operate smoking cessation clinics at public health centers. The study was conducted with 262,837 smokers aged 19 or over who were provided with smoking cessation services for more than 6 months after being registered with the smoking cessation clinic at public health centers (250 clinics nationwide) from July 16, 2006 to July 15, 2007. After dividing smokers into re-enrollees and new enrollees of the smoking cessation clinic, the success rate of and success factors for smoking cessation over 6 months have been investigated. The success factors in smoking cessation have been compared between new enrollees and re-enrollees of smoking cessation clinics. The results can be summarized as follows: First, the success rate of smoking cessation for 6 months at smoking cessation clinics of public health centers was higher in new enrollees (46.3%) than in re-enrollees (41.1%). Second, the common factors that had an influence on the success of smoking cessation of both new enrollees and re-enrollees of the smoking cessation clinic included age, social security, service, frequency of counseling, number of cigarettes per day, and alcoholic problems. Third, compared to new enrollees, re-enrollees had a higher success rate of smoking cessation as they got older. In terms of the success rate of health insurance, on the contrary, new enrollees were better than re-enrollees. Fourth, the study showed a higher success rate in smoking cessation in both new and re-enrollees if they had no alcoholic problems. In particular, a higher success rate was observed in re-enrollees when there were no alcoholic problems. To efficiently operate smoking cessation clinics at public health centers, this study confirmed that counseling should be tailored depending on the types of enrollees in the program.

패널자료를 활용한 종단적 금연 성공요인 분석

송태민(Tae Min Song),이주열(Ju Yul Lee) 한국보건교육건강증진학회 2009 보건교육건강증진학회지 Vol.26 No.3

Objectives: This study has longitudinally analyzed male smokers in order to find out the trend rate of re-smoking after smoking cessation. Methods: The study was conducted with 800 male smokers who were provided with smoking cessation services for 3 years at public health centers from July 16, 2005 to July 15, 2008. Results: The results can be summarized as follows: First, the success rate of smoking cessation for at least 6 months during 3-year period was 54.4%. The failure rate of smoking cessation at the second year was 47.5% and the third 27.2%, which indicates that the failure rate diminishes as the period of smoking cessation extends. Second, the success rate of smoking cessation at the first trial was 35.0%, the second 24.3%, and the third 16.4%. The success rate diminished as the number of trial increased. Third, the continuation rate of smoking cessation for a year was 18.3%, for 2 years 13.4%. For the success group, the continuation rate of smoking cessation for a year was 52.5%, for 2 years 38.2%. For the failure group, the rate for a year was 21.5%. Fourth, in this longitudinal analysis, the most crucial variables that affect the success rate of smoking cessation are total number of consultation and the past experience of successful smoking cessation. Conclusion: This study shows that success of smoking cessation and the continuance of smoking cessation are both difficult, and that the past experience of smoking cessation plays an important role determining the present success of smoking cessation and continuance of smoking cessation. Thus, it is necessary to divide people into success group and failure group based on the results of the past experience of smoking cessation when they consult at smoking cessation clinics at public health centers. Further, in order to increase the continuation rate of smoking cessation, this study suggests that we need to consider ways to take care of those who successfully abstained from smoking for 6 months.

앤더슨 행동모형을 이용한 노년기 외래의료서비스 이용에 대한 스트레스 취약요인의 매개효과 분석

송태민 ( Song Tae Min ) 한국보건사회연구원 2013 保健社會硏究 Vol.33 No.1

본 연구는 앤더슨의 의료서비스 이용모델을 바탕으로 기존 연구에서 검증된 주요 결정요인인 선행요인, 가능요인, 욕구요인이 스트레스 취약요인을 매개하여 외래의료서비스 이용에 영향을 미치는 요인에 대한 검증을 실시하였다. 분석자료는 2009년 한국의 료패널의 본 조사와 부가조사에서 응답한 60세 이상 노인 3,696명을 대상으로 하였으며, 구조모형과 매개효과 분석은 구조방정식모형을 사용하였고, 개인요인과 지역요인의 영향에 대한 검증은 다층모형을 사용하였다. 주요분석 결과 개인요인인 문제음주, 스트레스, 소득수준, 장애유무가 노인의 외래의료서비스 이용에 유의한 영향을 주며, 스트레스나 우울이 있을 때 외래의료서비스 이용에 영향을 더 많이 주는 것으로 나타났다. 스트레스 취약요인의 매개효과 검증에서 전기노인은 우울을 매개하였고 후기노인은 스트레스를 매개하여 외래의료서비스 이용에 영향을 주는 것으로 나타났다. 그리고, 지역 요인인 병의원 수나 노인장기요양시설 수가 많을수록 외래의료서비스 이용이 증가하는 것으로 나타났다. 따라서 노인의 신체적 질병, 배우자의 죽음, 경제상태의 악화, 사회와 가족으로부터의 고립, 일상생활에 대한 자기통제 불가능 등으로 인한 스트레스를 해소 할 수 있는 국가차원의 상담프로그램의 도입과 보건의료 접근성이 취약한 노인계층을 위하여 의료시설의 지역간 균형적인 공급이 필요할 것으로 본다. This study has verified the factors affecting the use of outpatient medical services by the elderly, using the main determinants of Andersen, which are predisposing factors, enabling factors, need factors and stress-vulnerability factors. For data analysis, a total of 3,696 aged people (60 or older) who participated in the main and additional surveys of Korea Health Panel 2009 were examined. In addition, Structural Equation Modeling(SEM) has been used to analyze structure model and mediator effects. To verify the effect of regional factors, Hierarchical Linear Model(HLM) has been used. The findings of this study are as follows: Stress or depression has a significant effect on the use of outpatient medical services by the elderly. The mediating factors of stress-vulnerability is significantly related the use of outpatient medical service by two different mediating factors within two groups; Elderly who are between 60 and 74 mediates stress and elderly who are over 75 mediates stress. The frequency of the use of outpatient medical services increased as the number of local medical clinics and long-term care service facilities increased. Therefore, it is necessary to come up with a government-led stress consultation program which can handle elderly stress caused by physical disease, spouse`s death, unfavorable economic conditions, isolation from society and family and inability to control daily routine activities and to provide community-based medical facilities for the aged who have poor accessibility to medical services.