Dynamic box office forecasting based on microblog data

Abstract

Movies, as one of the most rapidly developing industries´outcomes, have gained much attention these years. Especially in China, the world´s second largest film market with a rapid growing speed, many film companies intend to foresee the future box office in advance to better arrange their income and expenditure. Unlike some traditional forecasting model based on several movie-related features, this paper comprehensively utilizes the real-time social media, microblog, to realize a more accurate weekly box office forecasting model. The features weekly extracted from microblogs can be divided into count based features and context based features, along with the existing box office and the screen arrangements, to predict the box office in next week. For count based features, not only the total volume of related microblogs and the diffusion effect considers the number of followers, several unnoticed features like authentication users, gender ratio and mobile-users ratio are also introduced into the original predicting model. For content based features, a duplicate semantic analysis method is proposed. The number of tweets which can indeed influence others´purchase decision, along with the number of tweets with positive and negative influence is the results of the analysis system. On this basis, guided effect for each influential tweets are identified by the praise, comment and retweet times. Some machine learning models are then adopted after using genetic algorithm (GA) for feature selection. The empirical study shows that our research can dynamic forecast box office with a sustainable good performance.

The making of box-office collection: qualitative insights from Bollywood

“…average and volume of ratings, ratio and sum of positive, negative and neutral opinions) and the environment (e.g. screen ratio, seasonality) (Chen et al, 2016;De Vany and Walls, 2004;Palia et al, 2008). The stardom effect or the impact of using stars has also been documented (Elberse, 2007;Fetscherin, 2010).…”

“…The literature has shed light on the factors that affect a film's box-office performance. Most studies employ one or more success criteria in their scrutiny of box-office earnings such as critical appraisals, financial performance and film awards (Simonton, 2009), and more often than not, film performance is examined using various denominators such as film viewers (movie goers) (Hur et al, 2016), revenue (ticket sales) (Chen et al, 2016) and ratings (reviews) (Khopkar and Nikolaev, 2017). First-week box-office receipts have also been employed as a predictor as early box-office success has been found to produce a significant impact on the film's overall sales (Liu et al, 2016).…”

“…First-week box-office receipts have also been employed as a predictor as early box-office success has been found to produce a significant impact on the film's overall sales (Liu et al, 2016). Other studies have also used weekly (Chen et al, 2016) and overall box-office receipts (Ghiassi et al, 2015;Sharda and Delen, 2006), among others.…”

“…Most studies employ one or more success criteria in their scrutiny of box-office earnings such as critical appraisals, financial performance and film awards (Simonton, 2009), and more often than not, film performance is examined using various denominators such as film viewers (movie goers) (Hur et al. , 2016), revenue (ticket sales) (Chen et al. , 2016) and ratings (reviews) (Khopkar and Nikolaev, 2017).…”

“…, 2016). Other studies have also used weekly (Chen et al. , 2016) and overall box-office receipts (Ghiassi et al.…”