Forecasting the box offices of movies coming soon using social media analysis: A method based on improved Bass models

作者：

Highlights：

• Use Naive Bayes algorithm to calculate the sentiment values of Chinese microblog texts.

• Calculate three feature variables: sentiment value, consumers’ RFM value and the degree of moviegoers’ attention.

• Construct two improved Bass models to forecast the box offices of the movies.

• The proposed method has higher forecasting accuracy and lower error.

摘要

•Use Naive Bayes algorithm to calculate the sentiment values of Chinese microblog texts.•Calculate three feature variables: sentiment value, consumers’ RFM value and the degree of moviegoers’ attention.•Construct two improved Bass models to forecast the box offices of the movies.•The proposed method has higher forecasting accuracy and lower error.

论文关键词：Forecasting,Social media analysis,RFM analysis,The degree of moviegoers’ attention,The improved Bass model

论文评审过程：Received 7 July 2020, Revised 3 August 2021, Accepted 14 November 2021, Available online 24 November 2021, Version of Record 12 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116241