A Hybrid Dictionary Model for Ethical Analysis

Abstract

With the adoption of social media and web services, people have become more likely to share opinions on the web about their daily activities. Thus, social networks end up being seen as an opportunity to bend the rules, making things inadmissible in society. This work aimed to design a dictionary template for sentiment analysis applied to unethical behaviors. It also analyses how prepared the machine is for human dialogue, and proposes a hybrid approach combining existing work for dictionary creation and standard conversation recognition in the Internet. Additionally, it also analyzes current policies to remove inappropriate content and proposes some steps to be considered to reduce spread of inappropriate content in the web.