Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market

Taegu Kim, Jungsik Hong, Pilsung Kang

Research output: Contribution to journalArticle

1 Citation (Scopus)

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.

Original languageEnglish
Article number4315419
JournalComputational Intelligence and Neuroscience
Volume2017
DOIs
Publication statusPublished - 2017 Jan 1

ASJC Scopus subject areas

  • Computer Science(all)
  • Neuroscience(all)
  • Mathematics(all)

Fingerprint Dive into the research topics of 'Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market'. Together they form a unique fingerprint.

  • Cite this