Predicting a box office gross in the film industry is an important goal. Many works have analyzed the elements of a film making. Previous studies have suggested several methods for predicting box office such as a model for distinguishing people's reactions by using a sentiment analysis, a study on the period of influence of word-of-mouth effect through SNS. These works discover that a word of mouth (WOM) effect through SNS influences customers’ choice of movies. Therefore, this study analyzes correlations between a box office gross and a ratio of people reaction to a certain movie by extracting their feedback on the film from before and after of the film opening. In this work, people’s reactions to the movie are categorized into positive, neutral, and negative opinions by employing sentiment analysis. In order to proceed the research analyses in this work, North American tweets are collected between March 2011 and August 2012. There is no correlation for each analysis that has been conducted in this work, hereby rate of tweets before and after opening of movies does not have relationship between a box office gross.

Abstract
 1. 서 론
 2. 사전 연구
  2.1 박스 오피스 예측 (Box office prediction)
  2.2 감성 분석 (sentiment analysis)을 이용한 박스 오피스 예측
  2.3 SNS 구전 효과가 영화에 영향을 미치는 기간
 3. 연구 방법 (Methodology)
  3.1 데이터 전처리
  3.2. 사전 데이터베이스 구축
  3.3. 감성분석 (Sentiment analysis)
  3.4 상관 분석 (Correlation analysis)
 4. 실험
  4.1 실험 절차
  4.2 가설 검정
 5. 결 론
 6. Reference

• 박지윤(인하대학교 산업공학과) | Ji-Yun Park
• 유인혁(인하대학교 산업공학과) | In-Hyeok Yoo
• 강성우(인하대학교 산업공학과) | Sung-Woo Kang Corresponding Author