Considering online consumer reviews to predict movie box-office performance between the years 2009 and 2014 in the US
| DOI | https://doi.org/10.1108/EL-02-2018-0040 |
| Pages | 1010-1026 |
| Published date | 10 December 2018 |
| Date | 10 December 2018 |
| Author | Ya-Han Hu,Wen-Ming Shiau,Sheng-Pao Shih,Cho-Ju Chen |
| Subject Matter | Information & knowledge management,Information & communications technology,Internet |
Considering online consumer
reviews to predict movie
box-office performance between
the years 2009 and 2014 in the US
Ya-Han Hu
Department of Information Management, National Chung Cheng University,
Chiayi, Taiwan and Center for Innovative Research on Aging Society,
National Chung Cheng University, Chiayi, Taiwan
Wen-Ming Shiau
Department of Information Management, National Chung Cheng University,
Chiayi, Taiwan
Sheng-Pao Shih
Department of Information Management, Tamkang University,
New Taipei City, Taiwan, and
Cho-Ju Chen
Department of Information Management, National Chung Cheng University,
Chiayi, Taiwan
Abstract
Purpose –The purpose of this paper is to combine basic movie information factors, external factors and
review factors, to predict box-office performance and identify the most crucial factor of influence for box-office
performance.
Design/methodology/approach –Five movie genres and first-week movie revie ws found on IMDb
were collected. The movie reviews were quantified using sentiment analysis tools SentiStrength and
Stanford CoreNLP, in which quantified data were combined with basic movie information and external
environment factors to predict movie box-office performance. A movie box-office performance prediction
model was then develope d using data mining (DM) technologies with M5 m odel trees (M5P), linea r
regression (LR) and support vector regression (SVR), after which movie box-office performance
predictionsweremade.
Findings –The results of this paper showed that theinclusion of movie reviews generated more accurate
prediction results. Concerningmovie review-related factors, the one that exhibited the greatest effecton box-
office performancewas the number of movie reviews made, whereas movie review content only displayedan
effect on box-officeperformance for specific movie genres.
Research limitations/implications –Because this paper collectedmovie data from the IMDb, the data
were limited andprimarily consisted of movies released in the USA;data pertaining to less popular movies or
those releasedoutside of the USA were, thus, insufficient.
Practical implications –This paper helps to verify whether the consideration of the features extracted
from moviereviews can improve the performance of movie box-office.
This research was supported in part by the Ministry of Science and Technology of the Republic of
China (grant number MOST 104-2410-H-194-070-MY3).
EL
36,6
1010
Received9 March 2018
Revised5 May 2018
Accepted7 May 2018
TheElectronic Library
Vol.36 No. 6, 2018
pp. 1010-1026
© Emerald Publishing Limited
0264-0473
DOI 10.1108/EL-02-2018-0040
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0264-0473.htm
Originality/value –Through variousDM technologies, this paper shows that movie reviews enhanced the
accuracy of box-office performancepredictions and the content of movie reviews has an effect on box-office
performance.
Keywords Online reviews,Machine learning, Box-officepredictions, IMDb, Onlineconsumer reviews
Paper type Research paper
1. Introduction
According to the movie box-office performance report released by Motion Picture Association
of America (MPAA) in 2016, the global film industry generated US$38.6bn worth of revenue
in 2016, making it a flagship industry featuring remarkable business opportunities and added
values (Shanklin, 2002). However, of the thousands of movies released globally every year,
many produce poor movie box-office performance despite a high production cost. Statistics
show that of the 80 per cent of profits made by the film and television industry, only 6 per cent
came from movies and that 78 per cent of movies generated a loss (Davenport and Harris,
2009). High production costs by no means guarantee strong box-office performance. Therefore,
findinga method to ensure anideal return on investment becomesmarkedly crucial.
Netflix, one of the largest online video service providers in the USA, collects various
online consumer behavior, includingactions (i.e. clicking, playing, pausing, fast forwarding
and rewinding) and behavior (i.e. viewing duration,number of views and viewing cycle). In
addition, each video is addeddifferent tags (e.g. director, actor, screenwriter, producer,genre
and plot), in which the data are analyzed to identify users’preference. Furthermore, user
surveys are conducted to discover potential customer groups. Such an effort was made
before introducing the political drama House of Cards, which allowed the show to produce
successful box-office performance. Therefore, analyzing factors of successfor movies before
their release is essentialto generating outstanding box-office revenue.
A number of studies related to box-office performance prediction have already been
conducted (Basuroy et al., 2003;Sharda and Delen, 2006;Zhang et al., 2009;Lipizzi et al.,
2016). Several factors influencingbox-office performance have been identified, includingthe
movie genre, director, actors and plot summary as well as marketing activities used to
promote the movies (Chintagunta et al., 2010;Delen et al.,2007;Ding et al., 2017;Hur et al.,
2016).
The emergence and developmentof the internet and Web 2.0 have allowed information to
be exchanged more quickly and conveniently (Wang et al.,2017). Consumers search for
product information online and share and exchangeideas and thoughts via platforms such
as forums, virtual communities, electronic bulletin boards and chat rooms (Pai et al.,2013).
They find messages and product reviews left by other users, forming the so called
“electronic word-of-mouth marketing”(eWOM marketing). These online platforms become
channels in which users exchange information with product suppliers and other users
(Cantallops and Salvi,2014;Zhou et al., 2017).
Today, many movie review websitescontain basic movie information as well as viewers’
reviews and thoughts aboutthe movies. Some studies found that the number of reviews and
the reviewers’scores are positively correlated with box-office performance, in which the
effect of negative reviews is strongerthan that of positive reviews (Chintagunta et al., 2010;
Duan et al., 2008). Although these studies considered the effect of movie reviews on box-
office performance, they failedto include a sufficient amount of factors and samples, which
may limit the generalizability of findings. Therefore, this study collected larger number of
movie data and considered most of the factorsused in previous studies to predict box-office
performance. Information from the IMDb website was used to build movie samples. The
Online
consumer
reviews
1011
Get this document and AI-powered insights with a free trial of vLex and Vincent AI
Get Started for FreeStart Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
Start Your Free Trial of vLex and Vincent AI, Your Precision-Engineered Legal Assistant
-
Access comprehensive legal content with no limitations across vLex's unparalleled global legal database
-
Build stronger arguments with verified citations and CERT citator that tracks case history and precedential strength
-
Transform your legal research from hours to minutes with Vincent AI's intelligent search and analysis capabilities
-
Elevate your practice by focusing your expertise where it matters most while Vincent handles the heavy lifting
