Predicting motion picture box office performance using temporal tweet patterns
作者机构:Department of Computer Science and Information SystemsUniversity of Wisconsin–River FallsRiver FallsWisconsinUSA Department of Management and MarketingUniversity of Wisconsin–River FallsRiver FallsWisconsinUSA
出 版 物:《International Journal of Intelligent Computing and Cybernetics》 (智能计算与控制论国际期刊(英文))
年 卷 期:2018年第11卷第1期
页 面:64-80页
核心收录:
学科分类:0810[工学-信息与通信工程] 0808[工学-电气工程] 08[工学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
主 题:Forecasting Social media Natural language processing Sentiment analysis Machine learning Box office
摘 要:Purpose–The purpose of this paper is to investigate temporal tweet patterns and their effectiveness in predicting the financial performance of a ***,how tweet patterns are formed prior to and after a movie’s release and their usefulness in predicting a movie’s success is ***/methodology/approach–Volume was measured and sentiment analysis was performed on a sampleof Tweetsposted fourdays beforeand afterthe releaseof 86 *** patternof tweeting for financially successful movies was compared with those that were financial *** temporal tweet patterns,a number of machine learning models were developed and their predictive performance was ***–Results show that the temporal patterns of tweet volume,length and sentiment differ between“hitsand“bustsin the days surrounding their *** with“buststhe tweet pattern for“hitsreveal higher volume,shorter length,and more favourable *** patterns in social media features occur days in advance of a movie’s release and can be used to develop models for predicting a movie’s ***/value–Analysis of temporal tweet patterns and their usefulness in predicting box office returns is the main contribution of this *** of this research could lead to development of analyticaltools allowingmotionpicture studiosto accurately predictand possiblyinfluencethe opening night box-office receipts prior to the release of the ***,the specific temporal tweet patterns presented by this work may be applied to problems in other areas of research.