An online feedback systemfor anonymous and credible feedback identification

This paper focuses on designing an online feedback management system that collects data in the form of suggestions, ratings and comments, and applies machine learning capabilities to automatically extract relevant summaries of the suggestions posted in this automated suggestion system. We have analyzed two key requirements, anonymous feedback and credible feedback, to gain insight on the submitted "suggestions" as for how to improve an organization, a course, or any decision involving evolutionary system. These two highly desirable requirements are kind of contradictory since it is perhaps a rather obvious point that unless we know the person how will we know the credibility of his/her feedback - simultaneously addressing both of these requirements is the key research contribution of this paper. The proposed system will help in ensuring the anonymity as well as credibility of the feedback and automatic identification of relevant summaries of suggestions with minimal human endeavor during training phase.