Opening Big in Box Office? Trailer Content Can Help

Methodology

Model Architecture

Possible Enhancements / Future Works

Weaknesses

To investigate the impact of audiovisual features extracted from the movie trailer content to be used as input along with the metadata to predict the movie's opening weekend gross. The author argues that the use of audiovisual features is expected to improve the prediction performance.

1- The audiovisual features from the trailers had to be extracted manually to be used as inputs. The choice of audiovisual features is such that they are related to certain metadata features
2- The author investigate the usefulness of the selected audiovisual features in explaining certain metadata features. Linear SVM was used to predict the category of genre and MPAA rating using audiovisuals. Then for continuous metadata features (budget, movie runtime, etc), linear regression was used. It was found that some metadata can be replaced with audiovisuals. For example, movie genre, it can be easily predicted from the movie trailer.
3- After investigating the usefulness of audiovisuals, the author proceeded to find the correlation between the extracted audiovisuals and the opening weekend gross of the movie. Results from this are in "Results of Study"

This model could be used in mining features from social media about to be released movies can be done.

This model can be modified to learn and extract the audiovisuals instead of extracting them manually

Inputs and Outputs of Model

Inputs (metadata)

  • Production budget
  • Genre
  • MPAA ratings
  • Release period
  • First week screens
  • Actor's experience)

Sample

Output

474 American movies released during 2010 and 2014

Predict the movie's initial success

Audiovisual features

Visuals

Audio

  • Intensity and color
  • Shots
  • Motion activity
  • Close up shots

Results of Study

The result suggests that the use of both metadata and audiovisuals together provide better results than using either individually. Trailer content can add information complementary to metadata

This model can be used to classify movies using the audiovisuals to predict the genre, MPAA ratings, budget and runtime of the movie