It's been more than 90 days since you changed your password. Please change your password to protect your privacy
When you visit DBpia through the library, login to SNS is restricted.
If you visit through the library, the URL will be different and you will not be able to log in to SNS due to kakao/google/naver policy. If you want to use your SNS account, please visit DBpia directly and log in.
This study is about developing an ontology for personal debt and its application to social big data. For developing an ontology, we identified major concepts/classes in the area of personal debt, arranged the concepts in a hierarchy, and described properties of the concept (Noy and McGuinness, 2001). This study is based on 1) the review of the literature related to personal debt and 2) the exploration of social big data, that in this study refers to approximately 4 million debt-related online documents for 5 years from 2014 to 2018 collected through a variety of publicly available online sources. The concepts related to personal debt were categorized as 4 classes-sociodemographic characteristics, associated factors, properties of debt, and consequences of debt. Notable properties of each class with a high frequency in online documents were as follows: Sociodemographic characteristics include employees, self-employees, and families; Associated factors include interest rate, housing, and fraud; Properties of debt include subprime loans, prime loans, mobile loans, and mortgage; Consequences of debt include repayment, personal bankruptcy, and arrear. Sentiments frequently shown include both positive ones (e.g., practicality, efforts) and negative ones (e.g., hopelessness, agony, worry). This study is, to our knowledge, the first that presents an ontology of personal debt, and it provides a useful guideline for analysis of big data that future research in this area can build on.
이 연구의 목표는 소셜 빅데이터 분석을 위한 가계부채 관련 온톨로지를 개발하는 것이다. 이를 위해 가계부채 관련 주제의 분류 및 용어체계를 개발하였고, 그를 소셜 빅데이터에 적용하여 적합성을 살펴보았다. 온톨로지의 개발은 Noy and McGuinness(2001)가 제시한 방법론에 기반하였고, 기존문헌과 280개 온라인 채널에서 수집된 약 4백만 건의 온라인 문서를 활용하였다. 연구진은 문헌검토를 바탕으로 인구사회경제적 특성, 위험요인, 채무 특성, 채무 결과 총 네 가지 최상위 도메인을 도출하였고, 각 도메인별로 소분류 및 핵심용어를 제시하였다. 소셜 빅데이터를 탐색한 결과 인구사회경제적 특성에서는 소득, 직장인, 가족, 자영업 등이, 위험요인에서는 금리, 부동산, 사기, 재테크 등의 빈도가 높았다. 채무 특성에서는 비우량, 우량, 억대, 모바일대출 등이, 채무 결과에서는 채무상환, 개인회생, 개인파산, 연체 등이 많았다. 감정 관련하여 긍정적 용어로 긍정, 실용성, 노력, 보장 등이, 부정적 용어로 무력감, 불호, 고통, 고민 등이 많았다. 이 연구는 가계부채 관련 온톨로지를 처음으로 제시하고, 소셜 빅데이터의 활용을 위한 사회복지 분야 연구방법의 영역을 확장하였다는데 큰 의의가 있다.
You have been reported one after another from other members for writing reviews that contain advertisements, busive language, personal attacks, or disparaging expressions. As a result, you cannot write a review.