Participatory sensing is a crowd-sourcing technique that relies on participants' active contribution. By aggregating data sets from each participant, we can collect statistical information of the environment or phenomenona in the cloud. To promote use of participatory sensing in healthcare, research, and other useful applications, the protection of privacy is important to consider. The invasion of privacy in participatory sensing would have dire consequences because mobile phone used by these applications have sensitive data about users daily life. In this paper, we suggest a privacy-preserving participatory sensing scheme for real-world data sets with large numbers of categories by using Limited Negative Surveys. By using our method described in this paper, the server can reconstruct the probability distributions of the original distributions of sensed values without knowing the personal information of citizens. Furthermore, our research has the capablity to change, according to the features of data, especially the number of categories. We evaluate how this scheme of aggregate information can be still useful while protecting the privacy of users' original data.