Quantitative insights from online qualitative data: An example from the health care sector. Issue 12 (6th November 2018)

• Record Type: Journal Article
• Authors: Pitt, Christine; Mulvey, Michael; Kietzmann, Jan
• Is Part Of: Psychology & marketing. Volume 35:Issue 12(2018)
• Page Start: 1010
• Page End: 1017
• Publication Date: 2018-11-06
• Subjects: artificial intelligence -- credence goods -- health care -- latent class (LC) cluster modeling -- sentiment analysis; Marketing -- Psychological aspects -- Periodicals; Motivation research (Marketing) -- Periodicals; Marketing -- Aspect psychologique -- Périodiques; Motivation, Études de (Marketing) -- Périodiques; 658.80019
• DOI: 10.1002/mar.21152
• Languages: English
• ISSNs: 0742-6046

Abstract

Abstract: Among the deluge of online data generated by users in the form of text on social media sites, health care reviews are among the most common, and potentially, the most insightful. Patients review and comment on the experiences with procedures as varied as hysterectomies, colonoscopies, and chemotherapy. In their attempts to reduce the uncertainty associated with medical treatments, many patients nowadays also turn to social media, where they rely on the experiences articulated by other patients. In this study, IBM Watson is used to examine how knee replacement patients talk about their emotions and express sentiment through their comments online. Then, a latent class cluster modeling procedure is used to segment these patients into distinct groups, according to their emotions (anger, disgust, fear, happiness, sadness, and surprise), sentiment, and their overall satisfaction with knee replacement surgery. The findings show how qualitative online data can be transformed into quantitative insights regarding underlying market segments, which could then be targeted through different strategies by both marketers and health care practitioners.