53 Pages Posted: 31 Jan 2017
Date Written: January 31, 2017
User generated content in the form of customer reviews, blogs or tweets is an emerging and rich source of data for marketers. Topic models have been successfully applied to such data, demonstrating that empirical text analysis benefits greatly from a latent variable approach which summarizes high-level interactions among words. We propose a new topic model that allows for serial dependency of topics in text. That is, topics may carry over from word to word in a document, violating the bag-of-words assumption in traditional topic models. In our model, topic carry-over is informed by sentence conjunctions and punctuation. Typically, such observed information is eliminated prior to analyzing text data (i.e., “pre-processing”) because words such as “and” and “but” do not differentiate topics. We find that these elements of grammar contain information relevant to topic changes. We examine the performance of our model using multiple data sets and estab- lish boundary conditions for when our model leads to improved inference about customer evaluations. Implications and opportunities for future research are discussed.
Keywords: LDA, autocorrelated topics, user-generated content, Bayesian analysis
JEL Classification: M31, C11
Suggested Citation: Suggested Citation
Bueschken, Joachim and Allenby, Greg M., Improving Text Analysis Using Sentence Conjunctions and Punctuation (January 31, 2017). Available at SSRN: https://ssrn.com/abstract=2908915