Proceedings ArticleDOI
Role of different factors in predicting movie success
Anand Bhave,Himanshu Kulkarni,Vinay Biramane,Pranali Kosamkar +3 more
- pp 1-4
TLDR
This paper suggests that the integration of both the classical and the social factors (anticipation and user feedback) and the study of interrelation among the classical factors will lead to more accuracy.Abstract:
Due to rapid digitization and emergence of social media the movie industry is growing by leaps and bounds. The average number of movies produced per year is greater than 1000. So to make the movie profitable, it becomes a matter of concern that the movie succeeds. Given the low success rate, models and mechanisms to predict reliably the ranking and or box office collections of a movie can help de-risk the business significantly and increase average returns. The current predictive models available are based on various factors for assessment of the movie. These include the classical factors such as cast, producer, director etc. or the social factors in form of response of the society on various online platforms. This methodology lacks to harvest the required accuracy level. Our paper suggests that the integration of both the classical and the social factors (anticipation and user feedback) and the study of interrelation among the classical factors will lead to more accuracy.read more
Citations
More filters
Journal ArticleDOI
Box-office forecasting based on sentiments of movie reviews and Independent subspace method
TL;DR: New box-office forecasting models are presented to enhance the forecasting accuracy by utilizing review sentiments and employing non-linear machine learning algorithms, and an independent subspace method (ISM) is applied.
Journal ArticleDOI
Twitter Mining for Discovery, Prediction and Causality: Applications and Methodologies
TL;DR: A number of the applications that employ Twitter Mining are reviewed, investigating Twitter information for prediction, discovery and as an informational basis of causation.
Proceedings ArticleDOI
Using Crowd-Source Based Features from Social Media and Conventional Features to Predict the Movies Popularity
TL;DR: Experiments in predictive analysis using machine learning algorithms on both conventional features, collected from movies databases on Web as well as social media features demonstrate that the sentiments harnessed from social media and othersocial media features can predict the success with more accuracy than that of using conventional features.
Journal ArticleDOI
Understanding videos at scale: How to extract insights for business research
TL;DR: This article provides a consolidated tool to efficiently extract 109 video-based variables, requiring no programming knowledge, that include structural video characteristics such as colorfulness as well as advanced content-related features such as scene cuts or human face detection.
Journal ArticleDOI
An inside look into the complexity of box-office revenue prediction in China:
TL;DR: It is proposed that relativity analysis is more reasonable than precise revenue prediction, and it is proved that watching counts of 1 week before releasing on Youku is the barometer of market performance, especially the first week revenues.
References
More filters
Dissertation
Using sentiment and social network analyses to predict opening-movie box-office success
TL;DR: In this paper, the authors explore notions of collective intelligence in the form of web metrics, social network analysis and sentiment analysis to predict the box-office income of movies and explore several modeling approaches to predict performance on the Hollywood Stock Exchange prediction market as well as overall gross income.
MooVis -- A Visual Analytics Tool for the Prediction of Movie Viewer Ratings and Boxoffice
Mennatallah el Assady,Daniel Hafner,Michael Hund,Alexander Jäger,Wolfgang Jentner,Christian Rohrdantz,Fabian Fischer,Svenja Simon,Tobias Schreck,Daniel A. Keim +9 more
TL;DR: Konstanz Information Miner is a open-source tool, developed at the University of Konstanz, containing different Data Mining techniques and the possibility to extract trained models in the PMML (Predictive Model Markup Language) format in order to import them into other applications.