Automated Discovery of Product Feature Inferences Within Large-Scale Implicit Social Media Data

Recently, social media has emerged as an alternative, viabl e source to extract large-scale, heterogeneous product feat ur s in a time and cost efficient manner. One of the challenges of utilizing social media data to inform product design decisi ons is the existence of implicit data such as sarcasm, which accounts for 22.75% of social media data, and can potentially create bias in the predictive models that learn from such dat a sources. For example, if a customer says “I just love waiting all day while this song downloads”, an automated product feature extraction model may incorrectly associate a posit ive sentiment of “love” to the cell phone’s ability to download. While traditional text mining techniques are designed to ha ndle well-formed text where product features are explicitly inferred from the combination of words, these tools would fail to process these social messages that include implicit prod uct feature information. In this paper, we propose a method that enables designers to utilize implicit social media data by t ranslating each implicit message into its equivalent explicit f orm, using the word concurrence network. A case study of Twitter messages that discuss smartphone features is used to valida te the proposed method. The results from the experiment not onl y show that the proposed method improves the interpretabilit y of implicit messages, but also sheds light on potential appl ications in the design domains where this work could be extended.