Why watching movie tweets won't tell the whole story?

Abstract

Data from Online Social Networks (OSNs) are providing analysts with an unprecedented access to public opinion on elections, news, movies etc. However, caution must be taken to determine whether and how much of the opinion extracted from OSN user data is indeed reflective of the opinion of the larger online population. In this work we study this issue in the context of movie reviews on Twitter and compare the opinion of Twitter users with that of the online population of IMDb and Rotten Tomatoes. We introduce new metrics to show that the Twitter users can be characteristically different from general users, both in their rating and their relative preference for Oscar-nominated and non-nominated movies. Additionally, we investigate whether such data can truly predict a movie's box-office success.

Does Twitter matter? The impact of microblogging word of mouth on consumers’ adoption of new movies

“…However, they do not control for other important variables that influence movie success, such as advertising spending. Wong, Sen, and Chiang (2012) link Twitter valence metrics to the total box office revenues of 34 movies, but they include only positive tweets in their analysis. They find that these tweets do "not necessarily translate into predictable box office" (p. 6) results.…”

Influence of social media on performance of movies

“…Tweets about movies suffer inconsistent hype-approval factor which cannot be necessarily correlated with the financial performance of movies at box-office [7]. We also improve in terms of the accuracy of classification of movies.…”

“…Going with the trend, many other studies have tried to capture popularity variable through movie and star buzz through tweets or pre release hype created on the Internet through advertising and marketing. On one hand, a few studies [8] advocate that social media buzz have positive impact on box office returns, some others [7] advocate that buzz in the form of tweets do not necessarily relate to box office revenue. Star Power has been one amongst the features on which recent researches have focused much on.…”

Classifying Short Text in Social Media: Twitter as Case Study

“…For example, movie makers attempt to measure people's opinions via Twitter users. Wong et al investigate the ability to predict whether there is a relation between users' opinions and Oscar nominations for films [68]. First, Wong et al determine if a tweet is relevant to a movie.…”