University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

A picture is worth a thousand words : investigating the value of Instagram posts and Twitter posts in predicting movie box office revenues.

Rouwenhorst, J.H.J. (2018) A picture is worth a thousand words : investigating the value of Instagram posts and Twitter posts in predicting movie box office revenues.

[img] PDF
2MB
Abstract:Purpose: Using Instagram and Twitter data for volume- and sentiment-related predictor variables, the purpose of this paper is to examine the predictive value of Instagram predictor variables compared to Twitter variables in predicting movie box office revenues in the same and the subsequent week. Design/methodology/approach: A total number of 40.000 posts, containing textual and visual data were collected from Instagram and Twitter. Besides counting post volumes and post views, the Instagram and Twitter posts were used for performing textual sentiment and visual sentiment analysis. Findings: The predictive value of Instagram predictor variables is on average higher than the predictive value of Twitter predictor variables in predicting movie box office revenues in the same and subsequent week. Originality/value: Results of this research demonstrate that Instagram predictor variables are on average better predictors of movie box office revenues. Compared to textual sentiment, visual sentiment was found to be a more relevant predictor of movie box office revenues. With regard to the visual sentiment-related variables, negative visual sentiment-related on Instagram is identified as a significant predictor for movies after the moment of movie release.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:54 computer science, 83 economics, 85 business administration, organizational science
Programme:Business Administration MSc (60644)
Link to this item:https://purl.utwente.nl/essays/75083
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page