발간년도 : [2020]
| 논문정보 |
|
| 논문명(한글) |
[Vol.15, No.1] A Hybrid Approach Using Python and Excel for Extracting Valid C ases in Content Analysis |
|
| 논문투고자 |
Dong-Sung Kim, Hyung-Suk Kim |
|
| 논문내용 |
Recent big data gives scientists the opportunity to collect and analyze more quantity of data and more variety of data more quickly than they could ever do. 3Vs(Volume, Variety, Velocity), the basic characteristics of big data, can solve social science research’s key problems of generalization with research results, accessibility to necessary data, and excessive manpower or time. So, big data is attracting attention as a research method for social scientists. However, many researchers are blind and improperly applying big data without worrying and solving the representativeness and validity of the sample. Therefore, this study proposes a hybrid research method that can maximize the merits of both quantitative and qualitative research methods: generalization and validity. To do this, we researched the trend of fairness-oriented issues related to domestic large companies over a year and crawled 21,900 articles of Naver ranking news with Python using the BeautifulSoup library. And 1,876 final valid data for content analysis were extracted by using the FIND function of Excel. Consequently, we propose an alternative by modeling the process and method for content analysis: crawling news articles by python and filtering valid cases by Excel FIND function. After this research, it is expected that various collaborations will be carried out to create synergy between big data technologies and social science fields. |
|
| 첨부논문 |
|
|
|
|
|
자료실 > 논문지 
