Predicting the Future with Social Media

By Sitaram Asur, Bernardo A. Huberman. 2010

2,354 citations recorded by the source corpus.

In recent years, social media has become ubiquitous and important for social networking and content sharing. And yet, the content that is generated from these websites remains largely untapped. In this paper, we demonstrate how social media content can be used to predict real-world outcomes. In particular, we use the chatter from Twitter.com to forecast box-office revenues for movies. We show that a simple model built from the rate at which tweets are created about particular topics can outperform market-based predictors. We further demonstrate how sentiments extracted from Twitter can be utilized to improve the forecasting power of social media.

Subfields: Economics and Econometrics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Economics and Econometrics

Citations in the corpus

Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries (2019, background): “Much research rests upon the assumption that online social traces reﬂect in some quantiﬁable way real-world phenomena (Asur and Huberman, 2010; Kıcıman and Richardson, 2015), an assumption that is key when assessing and interpreting results.”
Part-of-Speech Tagging for Twitter: Annotation, Features, and Experiments (2010, background): “com) is one particularly fruitful source of user-created content, and a flurry of recent research has aimed to understand and exploit these data (Ritter et al., 2010; Sharifi et al., 2010; Barbosa and Feng, 2010; Asur and Huberman, 2010; O’Connor et al., 2010a; Thelwall et al., 2011).”
Twitter mood predicts the stock market (2010, background): “Most recently, Asur and Huberman [1] provided a demonstration of how public sentiment related to movies, as expressed on Twitter, can actually predict box office receipts.”
Comparing Twitter and Traditional Media Using Topic Models (2011, background): “Several recent studies examined Twitter from different perspectives, including the topological characteristics of Twitter [1], tweets as social sensors of real-time events [2], the forecast of box-office revenues for movies [3], etc.”
Is Bigger Always Better? Potential Biases of Big Data Derived from Social Network Sites (2015, methodology): “), to the cultural (e.g., Asur and Huberman 2010), psychological (e.g., Wald, Khoshgoftaar, and Sumner 2012), and economic (e.g., Bollen, Mao, and zeng 2011). the unprecedented availability of such big data has led to much enthusiasm (e.g., Mayer-Schonberger and Cukier 2013), with some suggesting…”
Predicting the Political Alignment of Twitter Users (2011, background): “Social media data has proven valuable for predictions in various domains, including politics [18], [38], [39].”
Like It or Not (2016, methodology): “Additionally, sentiment analysis could be applied on a marketing domain to predict the success of a product or of movies [Asur and Huberman 2010].”
Predicting crime using Twitter and kernel density estimation (2014, background): “…researchers have attempted to use social media to predict or detect disease outbreaks [11], election results [12], macroeconomic processes (including crime) [13], box office performance of movies [14], natural phenomena such as earthquakes [15], product sales [16], and financial markets [17].”
From classification to quantification in tweet sentiment analysis (2016, background): “For instance, aggregate (rather than individual) results from tweet classiﬁcation are the real goal in Asur and Huberman (2010), which analyses Twitter data in order to predict box ofﬁce revenues for movies; in Olteanu et al. (2015), whose authors try to determine the percentage of tweets that are…”
Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks (2015, background): “There have been many works on using online users’ sentiments to predict box-ofﬁce revenues for movies (Asur and Huberman 2010), political elections (O’Connor et al. 2010; Tumasjan et al. 2010) and economic indicators (Bollen, Mao, and Zeng 2011; Zhang, Fuehres, and Gloor 2011).”
On Unravelling Opinions of Issue Specific-Silent Users in Social Media (2016, background): “Social media such as Twitter and Facebook has been a popular conduit for opinion mining and data science research (Pak and Paroubek 2010; Tumasjan et al. 2010; Chung and Mustafaraj 2011; Skoric et al. 2012; Barbosa and Feng 2010; Kouloumpis, Wilson, and Moore 2011).”
Can Tweets Predict Citations? Metrics of Social Impact Based on Twitter and Correlation with Traditional Metrics of Scientific Impact (2011, background): “area of science with applications in public health [17,18] and a wide range of other areas [19]—it has, for example, been shown that search engine queries predict influenza [20,21], that tweets during the H1N1 pandemic correlated with incidence rates [22], and that tweets about a movie accurately pr”
On Using Twitter to Monitor Political Sentiment and Predict Election Results (2011, methodology): “Asur and Huberman (Asur and Huberman, 2010) used Twitter volume and sentiment to predict box office takings for”