Early Prediction of Movie Box Office Success based on Wikipedia Activity Big Data

Abstract

Use of socially generated "big data" to access information about collective states of the minds in human societies has become a new paradigm in the emerging field of computational social science. A natural application of this would be the prediction of the society's reaction to a new product in the sense of popularity and adoption rate. However, bridging the gap between "real time monitoring" and "early predicting" remains a big challenge. Here we report on an endeavor to build a minimalistic predictive model for the financial success of movies based on collective activity data of online users. We show that the popularity of a movie can be predicted much before its release by measuring and analyzing the activity level of editors and viewers of the corresponding entry to the movie in Wikipedia, the well-known online encyclopedia.

13 pages, Including Supporting Information, 7 Figures, Download the dataset from: http://wwm.phy.bme.hu/SupplementaryDataS1.zip

References in corpus (5)

• "I Wanted to Predict Elections with Twitter and all I got was this Lousy Paper" -- A Balanced Survey on Election Prediction using Twitter Data
• Opinions, Conflicts and Consensus: Modeling Social Dynamics in a Collaborative Environment
• The statistical laws of popularity: Universal properties of the box office dynamics of motion pictures
• Quantitative analysis of the evolution of novelty in cinema through crowdsourced keywords
• Value production in a collaborative environment

Cited by in corpus (31)

• Quantifying the Effect of Sentiment on Information Diffusion in Social Media
• Global disease monitoring and forecasting with Wikipedia
• Early Predictions of Movie Success: the Who, What, and When of Profitability
• The distorted mirror of Wikipedia: a quantitative analysis of Wikipedia coverage of academics
• The production of information in the attention economy
• Manipulation and abuse on social media
• Using four different online media sources to forecast the crude oil price
• Quantifying and predicting success in show business
• Twitter-based analysis of the dynamics of collective attention to political parties
• Quantitative analysis of the evolution of novelty in cinema through crowdsourced keywords
• Value production in a collaborative environment
• Style in the Age of Instagram: Predicting Success within the Fashion Industry using Social Media
• Wikipedia traffic data and electoral prediction: towards theoretically informed models
• Can electoral popularity be predicted using socially generated big data?
• Understanding Editing Behaviors in Multilingual Wikipedia
• Identifying long-term periodic cycles and memories of collective emotion in online social media
• Self-organization on social media: endo-exo bursts and baseline fluctuations
• Evolving Collaboration, Dependencies, and Use in the Rust Open Source Software Ecosystem
• Dynamics and Biases of Online Attention: The Case of Aircraft Crashes
• Inspiration, Captivation, and Misdirection: Emergent Properties in Networks of Online Navigation
• TwitterPaul: Extracting and Aggregating Twitter Predictions
• A Graph-structured Dataset for Wikipedia Research
• The quantitative measure and statistical distribution of fame
• Memory Remains: Understanding Collective Memory in the Digital Age
• Terrorist attacks sharpen the binary perception of "Us" vs. "Them"
• On the Dynamics of Social Media Popularity: A YouTube Case Study
• Detecting and Gauging Impact on Wikipedia Page Views
• Hybrid Machine Learning Approach to Popularity Prediction of Newly Released Contents for Online Video Streaming Service
• Upscaling human activity data: an ecological perspective
• Social media self-branding and success: Quantitative evidence from a model competition
• Collective Attention towards Scientists and Research Topics