Please use this identifier to cite or link to this item:
Title: Anticipating movie success through crowdsourced social media videos
Authors: Singh J
Goyal G.
Keywords: Dlib-ml
Emotive response
Social media
Machine learning
Movie trailer release
Issue Date: 2019
Publisher: Elsevier Ltd
Abstract: Business houses and marketers have been relying on social media to affect consumer opinions and purchasing behavior. In this paper a framework has been proposed to identify and quantify the emotive value of any movie trailer. The proposed framework made use of Dlib-ml (a machine learning toolkit) and a Genetic Algorithm inspired Support Vector Machine algorithm (GAiSVM) for parameter tuning and classification and emotive analysis of movie trailers. A case study comprising of 141 movies trailers released from Jan 1, 2017 till April 31, 2018 was done to investigate the relationship between emotive score of a movie trailer and financial returns associated with it. Results revealed a direct correlation between emotive score of a movie trailer and financial returns. Further, it was concluded that an emotionally intense movie trailer could result high financial returns in comparison to non-much emotionally intense trailers.
URI: 10.1016/j.chb.2018.08.050
Appears in Collections:Journals

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.