The predictive power of online chatter

By Daniel F. Gruhl, Ramanathan V. Guha, Ravi Kumar, Jasmine Novak, Andrew Tomkins. Knowledge Discovery and Data Mining, 2005

449 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/bfd56c1f57bf54d49db7dc67d355ecb49eac9583

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

Predicting the Future with Social Media (2010, background): “Gruhl and others [9] showed how to generate automated queries for mining blogs in order to predict spikes in book sales.”
From Predictive to Prescriptive Analytics (2014, methodology): “most notably in [13] and [19], and to predict movements in the stock market in [14]. Online chatter on blogs and social media have been shown to predict movie earnings in [2] and Amazon book sales in [22] using IBM’s WebFountain [21]. An important question, especially from a business’s point of view”
Bibliometrics to webometrics (2008, background): “A good example of a research initiative to harness consumer generated media (CGM) is an attempt to predict sales patterns for books based upon the volume of blog discussions of them [98].”
Patterns of temporal variation in online media (2011, background): “Popularity of various pieces of content on the Web, like news articles [30], blog posts [21, 27], Videos [10], posts in online discussion forums [4] and product reviews [13], vary on very different temporal scales.”
Towards detecting influenza epidemics by analyzing Twitter messages (2010, methodology): “[10] use hand-crafted keywords applied to Web documents to predict product sales.”
Predicting Movie Sales from Blogger Sentiment (2006, background): “In particular, a recent study showed that peaks in references to books in weblogs are likely to be followed by peaks in their sales (Gruhl et al., 2005).”
How Does the Data Sampling Strategy Impact the Discovery of Information Diffusion in Social Media? (2010, background): “…in the context of this work: • Information content: Today’s online social media feature extensive activity that is dependent on the information content being shared (i.e. the topic) as well as have been historically observed to exhibit correlation with external events (Gruhl et al. 2005).”
The impact of social and conventional media on firm equity value: A sentiment analysis approach (2013, background): “[18] show how to predict spikes in book sales via analyzing the correlation between blog and review mentions and performance.”
Designing novel review ranking systems: predicting the usefulness and impact of reviews (2007, background): “[10] analyzed the correlation between online mentions of a product and sales of that product.”
Modeling Public Mood and Emotion: Twitter Sentiment and Socio-Economic Phenomena (2009, background): “Personal websites such as blogs and online journals are often awash with emotive information and have been extensively used to deduct everyday happiness [12], explore trends and seasonality [1], forecast mood [13], and predict sales of books [7] and movies [14].”
A review of unsupervised feature learning and deep learning for time-series modeling (2014, background): “As an example, it has been shown that predicted stock prices can be improved if further information is extracted from online social media, such as Twitter feeds [14] and online chat activity [43].”
Predicting consumer behavior with Web search (2010, background): “A people increasingly turn to the Internet for news, information, and research purposes, it is tempting to view online activity at any moment in time as a snapshot of the collective consciousness, reflecting the instantaneous interests, concerns, and intentions of the global population (1, 2).”
A probabilistic approach to spatiotemporal theme pattern mining on weblogs (2006, background): “Gruhl and others [11] proposed a model for information propagation and categorized diffusing topics into chatter and spikes; they followed up to prove these temporal patterns of topics are useful to predict spike patterns in sales ranks [10].”
Manipulation of online reviews: An analysis of ratings, readability, and sentiments (2012, background): “[16] showed that volume of blog postings could be used to predict spikes in actual consumer purchase decisions at the online retailer Amazon.”