패널오차수정모형을 이용한 온라인 구전이 영화 관객수에 미치는 영향 분석

In this article, we examine the effect of online or electronic word of mouth(e-WOM) on movie box office success by conducting a panel data analysis. We collected weekly panel data with the number of audiences, the number of audience’s reviews and the number of screens about 27 movies released in Korea in 2019. The number of audiences and the number of screens were collected from KOBIS(KOrea Box-office Information System)(kobis.or.kr), while online reviews were collected through web scraping on the movie site in NAVER(movie.naver.com). By applying a panel unit-root test and a panel cointegration test, we found that the three variables(the number of audiences, the number of audience’s reviews and the number of screens) are I(1) and cointegrated. Hence we applied a panel error correction model(ECM) to analyze the causal relationships in our movie panel data. The results of this study can be summarized as follows. It was found that, in the long run relationship, both of the number of audience’s reviews and the number of screens had significant positive effects on the number of audiences, while, in the short run relationship, only the difference of the number of screens had significant positive effect on the difference of the number of audiences.