논문 해외 국제전문학술지(SCI급) BOX OFFICE FORECASTING CONSIDERING COMPETITIVE ENVIRONMENT AND WORD-OF-MOUTH IN SOCIAL NETWORKS: A CASE STUDY OF KOREAN FILM MARKET
- 학술지 구분 국제전문학술지(SCI급)
- 게재년월 2017-07
- 저자명 KIM, T (KIM, TAEGU)공동(제1),KANG, P (KANG, PILSUNG),HONG, J (HONG, JUNGSIK)
- 학술지명 COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE
- 발행처명 HINDAWI LTD
- 발행국가 해외
- 논문언어 외국어
- 전체저자수 3
홈페이지논문 초록 (Abstract)
Accurate box office forecasting models are developed by considering competition and word-of-mouth (WOM) effects in addition to screening-related information. Nationality, genre, ratings, and distributors of motion pictures running concurrently with the target motion picture are used to describe the competition, whereas the numbers of informative, positive, and negative mentions posted on social network services (SNS) are used to gauge the atmosphere spread by WOM. Among these candidate variables, only significant variables are selected by genetic algorithm (GA), based on which machine learning algorithms are trained to build forecasting models. The forecasts are combined to improve forecasting performance. Experimental results on the Korean film market show that the forecasting accuracy in early screening periods can be significantly improved by considering competition. In addition, WOM has a stronger influence on total box office forecasting. Considering both competition and WOM improves forecasting performance to a larger extent than when only one of them is considered.