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

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

Fingerprint

Social Support
Social Networks
Forecasting
Motion pictures
Motion Pictures
Screening
Motion
Social Work
Atmosphere
Ethnic Groups
Learning algorithms
Gages
Learning systems
Forecast
Market
Learning Algorithm
Gauge
Machine Learning
Genetic algorithms
Genetic Algorithm

ASJC Scopus subject areas

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

Cite this

@article{ed636123966643ed9e5ab4e9de70f507,
title = "Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks: A Case Study of Korean Film Market",
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.",
author = "Taegu Kim and Jungsik Hong and Pilsung Kang",
year = "2017",
month = "1",
day = "1",
doi = "10.1155/2017/4315419",
language = "English",
volume = "2017",
journal = "Computational Intelligence and Neuroscience",
issn = "1687-5265",
publisher = "Hindawi Publishing Corporation",

}

TY - JOUR

T1 - Box Office Forecasting considering Competitive Environment and Word-of-Mouth in Social Networks

T2 - A Case Study of Korean Film Market

AU - Kim, Taegu

AU - Hong, Jungsik

AU - Kang, Pilsung

PY - 2017/1/1

Y1 - 2017/1/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85027249965&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027249965&partnerID=8YFLogxK

U2 - 10.1155/2017/4315419

DO - 10.1155/2017/4315419

M3 - Article

C2 - 28819355

AN - SCOPUS:85027249965

VL - 2017

JO - Computational Intelligence and Neuroscience

JF - Computational Intelligence and Neuroscience

SN - 1687-5265

M1 - 4315419

ER -