Classification-based Content Sensitivity Analysis

With the availability of user-generated content in the Web, malicious users have access to huge repositories of private (and often sensitive) information regarding a large part of the world’s population. In this paper, we propose a way to evaluate the harmfulness of text content by defining a new data mining task called content sensitivity analysis. According to our definition, a score can be assigned to any text sample according to its degree of sensitivity. Even though the task is similar to sentiment analysis, we show that it has its own peculiarities and may lead to a new branch of research. Thanks to some preliminary experiments, we show that content sensitivity analysis can not be addressed as a simple binary classification task.