Fad or Here to Stay: Predicting Product Market Adoption and Longevity Using Large Scale, Social Media Data

Abstract

The authors of this work propose a Knowledge Discovery in Databases (KDD) model for predicting product market adoption and longevity using large scale, social media data. Social media data, available through sites such as Twitter® and Facebook®, have been shown to be leading indicators and predictors of events ranging from influenza spread, financial stock market prices, and movie revenues. Being ubiquitous and colloquial in nature allows users to honestly express their opinions in a unified, dynamic manner. This makes social media a relatively new data gathering source that can potentially appeal to designers and enterprise decision makers aiming to understand consumers response to their upcoming/newly launched products. Existing design methodologies for leveraging large scale data have traditionally relied on product reviews available on the internet to mine product information. However, such web reviews often come from disparate sources, making the aggregation and knowledge discovery process quite cumbersome, especially reviews for poorly received products. Furthermore, such web reviews have not been shown to be strong indicators of new product market adoption. In this paper, the authors demonstrate how social media can be used to predict and mine information relating to product features, product competition and market adoption. In particular, the authors analyze the sentiment in tweets and use the results to predict product sales. The authors present a mathematical model that can quantify the correlations between social media sentiment and product market adoption in an effort to compute the ability to stay in the market of individual products. The proposed technique involves computing the Subjectivity, Polarity, and Favorability of the product. Finally, the authors utilize Information Retrieval techniques to mine users’ opinions about strong, weak, and controversial features of a given product model. The authors evaluate their approaches using the real-world smartphone data, which are obtained from www.statista.com and www.gsmarena.com.