• Journal of Korea Entertainment Industry Association
• /
• v.13 no.5
• /
• pp.1-13
• /
• 2019

This study examines the impact of factors that affect Hollywood movies' box office performance, using a sample of 149 movies that were ranked number 1 on the first week of release between 2014 and 2018. Such factors as production budget, the number of opening screens, the valence and volume of both critics and netizens, rating, distributor's power, remake, high season, genre are introduced to analyze box office performance. The result shows that the determinants of the US box office and the total box office are different. Considering the difference in budget by genre, the number of opening screens is not influential in the US box office performance of all genres with production budget of less than $100 million. The result suggests the need to refine more elaborated models for future research on box office performance.

• The Journal of the Korea Contents Association
• /
• v.13 no.6
• /
• pp.108-115
• /
• 2013

This study focused on whether the existence and type of originals have any effects on box-office performance of the movie. Cultural products have characteristics of experience goods of which consumers hardly know the value of the products before they actually experience the products. To reduce the uncertainty, movie producers may want to use existing contents already made for other type of cultural products, which is generally called of One Source Multi Use. Using 381 Korean box-office data during January 2010 and September 2012, this study found that, first, the existence of original affects positively the movie's box office performance, second, the fiction based original has a positive effect on the movie's box office performance while cartoon and movie/TV based originals do not, and third, the movie type(commercial movie) positively moderates the relationship between fiction based original and movie performance. This study showed that box-office performance is not only affected by the characteristics of the movie itself, but also affected by other conditions including the use of existing originals created for other purposes.

• The Journal of the Korea Contents Association
• /
• v.20 no.12
• /
• pp.221-229
• /
• 2020

This study aims to find out predictors of a movie's eventual box office, focusing on a movie's box office rank on an opening day. For an empirical analysis, I use data of 794 commercial movies released in the Korean theatrical exhibition market during the recent five years(2013~2017). The regression analysis shows that being box office number one on an opening day has statistically significant impact on a movie's final box office. A movie's quality, measured by audience's review, does not give significant impact on top1 movie's final success. Indexes such as increase of showing number on Sunday are strongly related to a movie's economic success. The additional analysis on box office number one movie on an opening day, totally 158 movies, finds that box office growth rate on a second week is strongly related to a movie's final success. Lastly, correlation coefficient of a movie's opening day box office and final box office does not show consistent growth when the coefficient is compared yearly. This study might have meaning in that it proposes new box office predictors and shows the relation of the indexes and a movie's final performance empirically.

• Design Convergence Study
• /
• v.14 no.4
• /
• pp.1-16
• /
• 2015

This study aims to understand distribution of the sentimental words on each genre and find relationship between box office performance and sentimental words in movie review using 673 movies that have more than 1,000 reviews. For the analysis, crawling movie reviews and made data was composed movie genre, movie name, sales, attendance, screen, normal attendance, 7 sentimental words. For analysis results, we used correlation analysis and Parallel coordinates. As a results, First, the highest box office value of the genre is comedy and the lowest box office value of the genre is horror through analyze box office on each genre. Secondly, Movie genre of fantasy feel a lot of boring emotion and Movie genre of SF feel a lot of anger emotion even if 'Happy' and 'Surprise' have highest sentiment value on every genre. Third, We found 'Anger' increase sentimental value when 'Disgust' increase sentimental value and 'Surprise' decrease sentimental value when 'Happy' increase sentimental value through analyze correlation relationship between sentimental words using total data. Fourth, We found 'Happy' have linear relationship between box office and 'Fear' have non-linear relationship between box office through analyze sentimental words according to box office performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.9
• /
• pp.437-444
• /
• 2017

Although many studies tried to predict movie revenues in the last decade, the main focus is still to learn an efficient forecast model to fit the box-office revenues. However, the previous works lack the analysis about why the prediction errors occur, and no method is proposed to reduce the errors. In this paper, we consider the prediction error comes from the competition between the movies that are released in the same period. Our purpose is to analyze the competition value for a movie and to predict how much it will be affected by other competitors so as to improve the performance of movie box-office prediction. In order to predict the competition value, firstly, we classify its sign (positive/negative) and compute the probability of positive sign and the probability of negative sign. Secondly, we forecast the competition value by regression under the condition that its sign is positive and negative respectively. And finally, we calculate the expectation of competition value based on the probabilities and values. With the predicted competition, we can adjust the primal predicted box-office. Our experimental results show that predictive competition can help improve the performance of the forecast.

• The Journal of the Korea Contents Association
• /
• v.18 no.5
• /
• pp.357-366
• /
• 2018

This study analyzed the factors affecting box office performance of 200 movies released at the Chinese theater in 2015. The results showed that main actor power, online rating, production power, and Chinese film were sighificant factors which influenced box office, while the distribution power, genre, IP utilization and integration of production and distribution were insignificant. These results mean that online marketing factors such as the popularity index of the main actors evaluated on the internet and the online rating are affecting box office performances in Chinese theaters.

• Cartoon and Animation Studies
• /
• s.16
• /
• pp.21-32
• /
• 2009

This study provides an empirical analysis of box office performance for animation movies released in Korea between 2003 and 2008. Two dependent variables are both the number of audiences in the whole country and the number of audiences in Seoul. Such independent variables are employed : power of distributors, the number of screens, release time, sequel/remake, awards, film ratings, nationality, online reviews, and critics' reviews. For the total number of audiences in the whole country, significant variables are the number of screens, the power of USA distributors, Summer release, and online reviews. Since there is no analysis for box office performance for animation movies released in Korean theaters, this study will be considered to be meaningful.

• The Journal of Society for e-Business Studies
• /
• v.26 no.2
• /
• pp.19-43
• /
• 2021

The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

• The Journal of the Korea Contents Association
• /
• v.17 no.6
• /
• pp.296-310
• /
• 2017

The present study analyzed the factors affecting the box office performance of movies in the Chinese market in 2010~2014. A total of 499 movies were selected for the final analyses. Based on the previous studies, genre, actor/actress power, director power, sequel, remake, release period, award, online evaluation, distributor power, and production area were chosen as independent variables. Regression analyses showed that most of the independent variables except for distributor power were found to affect box office performance of the movies.

• Communications for Statistical Applications and Methods
• /
• v.20 no.4
• /
• pp.301-309
• /
• 2013

This paper predicts gross box office revenue for domestic films using the Korean film data from 2008-2011. We use three regression methods, Linear Regression, Random Forest and Gradient Boosting to predict the gross box office revenue. We only consider domestic films with a revenue size of at least KRW 500 million; relevant explanatory variables are chosen by data visualization and variable selection techniques. The key idea of analyzing this data is to construct the meaningful explanatory variables from the data sources available to the public. Some variables must be categorized to conduct more effective analysis and clustering methods are applied to achieve this task. We choose the best model based on performance in the test set and important explanatory variables are discussed.