Improving productivity in Hollywood with data science: Using emotional arcs of movies to drive product and service innovation in entertainment industries

Abstract Improving productivity in the entertainment industry is a very challenging task as it heavily depends on generating attractive content for the consumers. The consumer-centric design (putting the consumers at the centre of the content development and production) focuses on ways in which businesses can design customized services and products which accurately reflect consumer preferences. We propose a new framework which allows to use data science to optimize content-generation in entertainment and test this framework for the motion picture industry. We use the natural language processing methodology combined with econometric analysis to explore whether and to what extent emotions shape consumer preferences for media and entertainment content, which, in turn, affect revenue streams. By analyzing 6,174 movie scripts, we generate the emotional trajectory of each motion picture. We then combine the obtained mappings into clusters which represent groupings of consumer emotional journeys. These clusters are then plugged into an econometric model to predict overall success parameters of the movies including box office revenues, viewer satisfaction levels (captured by IMDb ratings), awards, as well as the number of viewers’ and critics’ reviews. We find that emotional arcs in movies can be partitioned into 6 basic shapes. The highest box offices are associated with the Man in a Hole shape which is characterized by an emotional fall followed by an emotional rise. This U-shaped emotional arc results in financially successful movies irrespective of genre and production budget. Implications of this analysis for generating on-demand content and improving productivity in entertainment industries are discussed.

[1]  L. C. Harris.  Film distribution as policy: current standards and alternatives , 2018 .

[2]  Seong-Yoon Shin,et al.  An Improved Text Classification Method for Sentiment Classification , 2019 .

[3]  Alan D. Smith.  Shrinking-release window movie releases: potential impacts on best business practices , 2011 .

[4]  Seonyeong Park.  FORECASTING AUDIENCE OF MOTION PICTURES CONSIDERING COMPETITIVE ENVIRONMENT , 2017 .

[5]  Sukki Yoon,et al.  The effects of eWOM volume and valence on product sales – an empirical examination of the movie industry , 2018, International Journal of Advertising.

[6]  Meri Prasetyawati,et al.  Development Strategy Of Competitive Health Of The Beginning Industry Through Management Of Value Added And Non Value Added Activity , 2018 .

[7]  Irene C. L. Ng.  Creating new markets in the digital economy : a theory oflatent demand , 2014 .

[8]  J. McMahon.  Is Hollywood a Risky Business? A Political Economic Analysis of Risk and Creativity , 2018 .

[9]  Jong Hyup Lee,et al.  The role of entropy of review text sentiments on online WOM and movie box office sales , 2017, Electron. Commer. Res. Appl..

[10]  John Sedgwick,et al.  Managing uncertainty in creative industries: Film sequels and Hollywood’s profitability, 1988–2015 , 2018, Competition & Change.

[11]  Jianping Chai,et al.  An effective daily box office prediction model based on deep neural networks , 2018, Cognitive Systems Research.

[12]  Hee-Dong Yang,et al.  Electronic word-of-mouth, box office revenue and social media , 2017, Electron. Commer. Res. Appl..

[13]  E. Grubert,et al.  Villainous or valiant? Depictions of oil and coal in American fiction and nonfiction narratives , 2017 .

[14]  Yang Wang,et al.  Hot streaks in artistic, cultural, and scientific careers , 2017, Nature.

[15]  Ruben Xing,et al.  Research on Movie Box Office Prediction Model With Conjoint Analysis , 2019, Int. J. Inf. Syst. Supply Chain Manag..

[16]  Yunian Ru,et al.  Time series clustering based on sparse subspace clustering algorithm and its application to daily box-office data analysis , 2018, Neural Computing and Applications.

[17]  Chieh Lee,et al.  Using Online User-Generated Reviews to Predict Offline Box-Office Sales and Online DVD Store Sales in the O2O Era , 2019, J. Theor. Appl. Electron. Commer. Res..

[18]  Christopher M. Danforth,et al.  The emotional arcs of stories are dominated by six basic shapes , 2016, EPJ Data Science.

[19]  H. Lee.  The political economy of ‘creative industries’ , 2017 .

[20]  Stein Kristiansen,et al.  Economic reasoning and creative industries progress , 2018 .

[21]  Neil Lee,et al.  The Creative Industries and Urban Economic Growth in the UK , 2014 .

[22]  G. Feng.  A comparative study of the online film ratings of US and Chinese audiences: An analytical approach based on big data , 2019 .

[23]  OhChong,et al.  Beyond likes and tweets , 2017 .

[24]  Dmitri G. Markovitch,et al.  Exploring the small movie profitability puzzle , 2015 .

[25]  Kang Zhao,et al.  Early Predictions of Movie Success: The Who, What, and When of Profitability , 2015, J. Manag. Inf. Syst..

[26]  Muhammad Tanvir Afzal,et al.  Pre-production box-office success quotient forecasting , 2019, Soft Comput..

[27]  W. D. Walls,et al.  Black swan models for the entertainment industry with an application to the movie business , 2019, Empirical Economics.

[28]  Sierdjan Koster,et al.  Creative Industries and Regional Productivity Growth in the Developing Economy: Evidence from Indonesia , 2017 .

[29]  A. Leaver.  A different take: Hollywood's unresolved business model , 2010 .

[30]  Luciano da Fontoura Costa,et al.  Mesoscopic representation of texts as complex networks , 2016, ArXiv.

[31]  Irene C. L. Ng,et al.  Value & worth: Creating new markets in the digital economy , 2012, Journal of Revenue and Pricing Management.

[32]  Zoë Wallin.  "Pictures Seem to Run in Cycles": Industry Discourse and the Economics of Film Cycles in Classical Hollywood , 2019, Film History.

[33]  Luciano da Fontoura Costa,et al.  Representation of texts as complex networks: a mesoscopic approach , 2016, J. Complex Networks.

[34]  Enrico Santarelli,et al.  Creative industries, new business formation, and regional economic growth , 2009 .

[35]  Vishal Gupta,et al.  Investigating the Effect of eWOM in Movie Box Office Success Through an Aspect-Based Approach , 2018 .

[36]  D. Marburger.  Optimal ticket pricing for performance goods , 1997 .

[37]  Hyun-Seok Hwang,et al.  Does Social Opinion Influence Movie Ticket Revenues?: A Case Study , 2017 .

[38]  Douglas Steinley,et al.  K-means clustering: a half-century synthesis. , 2006, The British journal of mathematical and statistical psychology.

[39]  Youngmee Hwang,et al.  Analyzing Box-Office Hit Factors Using Big Data: Focusing on Korean Films for the Last 5 Years , 2017, J. Inform. and Commun. Convergence Engineering.

[40]  Jonghyuk Kim,et al.  A Text Mining Approach for Sustainable Performance in the Film Industry , 2019, Sustainability.

[41]  Marina Lommerse,et al.  Designing Futures: A Model for Innovation, Growth and Sustainability of the Craft and Design Industry , 2011 .

[42]  Lauren Carroll Harris.  Film distribution as policy: current standards and alternatives , 2018 .

[43]  Anna-Katharina Hornidge.  ‘Creative industries’: Economic programme and boundary concept , 2011, Journal of Southeast Asian Studies.

[44]  Peter Meer,et al.  Semi-Supervised Kernel Mean Shift Clustering , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[45]  Han-fen Hu,et al.  Beyond likes and tweets: Consumer engagement behavior and movie box office in social media , 2017, Inf. Manag..

[46]  John J. Oliver.  Exploring industry level capabilities in the U.K. creative industries , 2017 .

[47]  Tin Cheuk Leung,et al.  Strategic Decision-Making in Hollywood Release Gaps , 2013 .

[48]  Xinlei Chen,et al.  Learning about movies: the impact of movie release types on the nationwide box office , 2013 .

[49]  Kumar Rajaram,et al.  Distribution Planning to Optimize Profits in the Motion Picture Industry , 2010 .

[50]  Yong Xu,et al.  Decision Model for Market of Performing Arts with Factorization Machine , 2018 .

[51]  Wei Chong Choo,et al.  Forecasting movie demand using total and split exponential smoothing , 2018 .

[52]  Ya-Han Hu,et al.  Considering online consumer reviews to predict movie box-office performance between the years 2009 and 2014 in the US , 2018, Electron. Libr..

[53]  Evgeny A. Antipov,et al.  Are box office revenues equally unpredictable for all movies? Evidence from a Random forest-based model , 2017 .

[54]  Aristotle,et al.  The Poetics of Aristotle , 1988 .

[55]  Imran Ihsan,et al.  Using Academy Awards to Predict Success of Bollywood Movies using Machine Learning Algorithms , 2019, International Journal of Advanced Computer Science and Applications.

[56]  J. Černevičiūtė,et al.  Teamwork management in Creative industries: factors influencing productivity , 2018, Entrepreneurship and Sustainability Issues.

[57]  Björn W. Schuller,et al.  Real-life voice activity detection with LSTM Recurrent Neural Networks and an application to Hollywood movies , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[58]  Lisa Purse.  Digital Heroes in Contemporary Hollywood: Exertion, Identification, and the Virtual Action Body , 2007 .

[59]  Hugh Robert Macdonald,et al.  Palm Sunday , 1968 .

[60]  Yao Liu,et al.  Sales Prediction by Integrating the Heat and Sentiments of Product Dimensions , 2018, Sustainability.

[61]  Maya Irjayanti,et al.  Implementing Technology in Creative Industry (Benchmarking Study in Developed Countries) , 2017 .

[62]  Amit M. Joshi.  Movie Stars and the Volatility of Movie Revenues , 2015 .

[63]  Hossein Najafi,et al.  Predicting motion picture box office performance using temporal tweet patterns , 2018, Int. J. Intell. Comput. Cybern..

[64]  Sungzoon Cho,et al.  Box-office forecasting based on sentiments of movie reviews and Independent subspace method , 2016, Inf. Sci..

[65]  B. Goff,et al.  Movies, Mass Consumers, and Critics: Economics and Politics of a Two‐Sided Market , 2017 .

[66]  Li-Chen Cheng,et al.  Exploring contextual factors from consumer reviews affecting movie sales: an opinion mining approach , 2020, Electron. Commer. Res..

[67]  M. Holbrook,et al.  Is movie success a judgment device? When more is not better , 2018, Psychology & Marketing.

[68]  Kirsten Grorud-Colvert,et al.  Uniting science and stories: Perspectives on the value of storytelling for communicating science , 2018, FACETS.

[69]  Harold L. Vogel.  Entertainment Industry Economics , 2020 .

[70]  Yi-Cheng Zhang,et al.  How Network Topologies Impact Project Alliance Performance: Evidence from the Movie Industry , 2019, Entropy.

[71]  Giwoong Bae,et al.  The impact of movie titles on box office success , 2019, Journal of Business Research.

[72]  Zheng-Hua Tan,et al.  Implementing a Commercial-Strength Parallel Hybrid Movie Recommendation Engine , 2014, IEEE Intelligent Systems.

[73]  Oliver Budzinski,et al.  Conquering the Box Office: Factors Influencing Success of International Movies in Russia , 2018, Review of Network Economics.

[74]  J. Eliashberg,et al.  The Motion Picture Industry: Critical Issues in Practice, Current Research, and New Research Directions , 2006 .

[75]  Brent A. Scott,et al.  Age, Gender, and Compensation , 2014 .

[76]  Louis R. Nemzer,et al.  How words matter: machine learning & movie success , 2020 .

[77]  Deb Roy,et al.  Audio-Visual Sentiment Analysis for Learning Emotional Arcs in Movies , 2017, 2017 IEEE International Conference on Data Mining (ICDM).

[78]  Antonio Pedro Batarda Fernandes.  The Entrapment of Art: Rock-Art, Order, Subversion, Creativity, Meaning, and the Appeal of Illusive Imagery , 2018 .

[79]  Mark Skilton,et al.  The 4th Industrial Revolution: Responding to the Impact of Artificial Intelligence on Business , 2017 .

[80]  Neeraj Bharadwaj,et al.  Predicting Innovation Success in the Motion Picture Industry: The Influence of Multiple Quality Signals , 2017 .

[81]  Seung Ryul Jeong,et al.  Text Mining and Sentiment Analysis for Predicting Box Office Success , 2018, KSII Trans. Internet Inf. Syst..

[82]  G. Celeux,et al.  Variable Selection for Clustering with Gaussian Mixture Models , 2009, Biometrics.

[83]  Dingtao Zhao,et al.  Creative industries agglomeration, regional innovation and productivity growth in China , 2014, Chinese Geographical Science.

[84]  Prashant Rajput,et al.  Box Office Revenue Prediction Using Dual Sentiment Analysis , 2017 .

[85]  P. Garcia‐del‐Barrio,et al.  Do movie contents influence box-office revenues? , 2017 .

[86]  Aleksandar Ignjatovic,et al.  Rating through Voting: An Iterative Method for Robust Rating , 2012, ArXiv.

[87]  Sven Jockel,et al.  The Event Movie: Marketing Filmed Entertainment for Transnational Media Corporations , 2006 .

[88]  Helton Saulo,et al.  Log‐symmetric regression models: information criteria and application to movie business and industry data with economic implications , 2019, Applied Stochastic Models in Business and Industry.

[89]  François A. Carrillat,et al.  Debates and assumptions about motion picture performance: a meta-analysis , 2018 .

[90]  Zhang Yi,et al.  Predicting movie box-office revenues using deep neural networks , 2019, Neural Computing and Applications.

[91]  Charles R. Plott,et al.  Two information aggregation mechanisms for predicting the opening weekend box office revenues of films: Boxoffice Prophecy and Guess of Guesses , 2015 .

[92]  W. D. Walls,et al.  Screen wars, star wars, and sequels , 2009 .

[93]  Iljoo Kim,et al.  Predicting movie success with machine learning techniques: ways to improve accuracy , 2018, Inf. Syst. Frontiers.

[94]  W. Walls,et al.  Does Hollywood Make Too Many R-Rated Movies?: Risk, Stochastic Dominance, and the Illusion of Expectation , 2000 .

[95]  Young-Seo Park,et al.  Spatial analysis of various multiplex cinema types , 2016 .

[96]  Athman Bouguettaya,et al.  Efficient agglomerative hierarchical clustering , 2015, Expert Syst. Appl..

[97]  Chun-Yu Ho,et al.  Agglomeration economies in creative industries , 2019, Regional Science and Urban Economics.

[98]  Haoxiang Ma,et al.  Analyzing dynamic review manipulation and its impact on movie box office revenue , 2019, Electron. Commer. Res. Appl..

[99]  Sarit Chakraborty,et al.  An Improved Text Sentiment Classification Model Using TF-IDF and Next Word Negation , 2018, ArXiv.

[100]  Aleksandar Ignjatovic,et al.  An Iterative Method for Calculating Robust Rating Scores , 2015, IEEE Transactions on Parallel and Distributed Systems.

[101]  Shanzhi Chen,et al.  An inside look into the complexity of box-office revenue prediction in China , 2017, Int. J. Distributed Sens. Networks.

[102]  Yong Jin,et al.  The power of the "like" button: The impact of social media on box office , 2017, Decis. Support Syst..

[103]  Lida Xu,et al.  A local-density based spatial clustering algorithm with noise , 2007, Inf. Syst..