DISMON

Introduction

Nonfatal workplace injuries and illnesses among private industry employers in 2008 occurred at a rate of 3.9 cases per 100 equivalent full-time workers (U.S. Bureau of Labor Statistics, 2009). Due to these sick leaves the companies are forced to hire new workers in order to fill the temporary vacancies, often employing the new members of the staff in short time-frames. Thus, it drives the company to carry out a quick selection process which entails a bad performance of this task and finally it can conclude with a no proper decision. In addition in most of the cases the incorporation of the new employees comprises an in-service training period or/and an adaptation period, therefore an efficiency loss. On the other, hand if the company does not hire new workers, it presents a worse scenario. Hence all these issues can imply loss of money by the company; unsatisfied clients; loss of partners; and unhappy stakeholders.

This paper proposes an automatic system for monitoring and helping to foresee the diseases using the social web and semantic technologies, giving useful information to the company and its employees in order to increase the efficiency by means of the prevention of injuries and illnesses, resulting in a safety environment for the workers. The system by means of analyzing the different information exchanged in the social web, will detect the diseases that are suffering the employees of a given company in a particular time. Furthermore the system will inform to the company about the spreading of the different illnesses and the recognized patterns. The aim of DISMON is to prevent massive infections and by means of the recognized patterns inferring which environmental conditions of the working place could have been the cause of a given disease, for instance temperature of the offices, contaminated air or water. In addition the system will report to each employee how probably is for them to be infected, based on the profile of the user, as age, location, previous illnesses or allergies in order to compare them with the characteristics of the previous infected workers, obtaining a percentage of the possibilities of the workers to get an illness.