Abstract

In 2014, Patrizia and his colleague published an interesting paper about the validated mobile smartphone application for body position measurement in rehabilitation [1]. The conclusion in that paper, they found 12 apps with promising features. Nowadays, this number has been increased to over 300 thanks to the booming of the smart phone and internet [2]. Normally a user community (rehabilitation ecosystem) can be also created to serve as the major feedback method, in which people can put comments on the rehabilitation plan, application itself, or any latest news. For the owner of this application, one may be interested about finding the most engaged user, and deliver customized plan with good quality. That wish can be fulfilled by data mining those comments. On the other hand, Yelp is a multi-dimension recommendation and review system, consisting several aspects of the data: users, business, and reviews. The purpose of this work is to use Yelp dataset to mimic the scenario in the rehabilitation ecosystem and answer following key question: Can insightful advertisement (the customized plan) be generated and deliver to those most engaged user? The insight of an advertisement means that advertisement should contain the key features of a particular domain of business belongs; here it’s physical rehabilitation for certain category of patient. These key features should reflect the users’ potential needs. And they could already exist in the toplevel business model in the domain, or the general rehabilitation plan for certain type of patient in our case, and be pursued by the application owner. The engaged user means those members who may show great interesting to your business (your customized rehabilitation plan). And they show great need to get the service of good quality.