The growing number of publicly available information sources makes it impossible for individuals to keep track of all the various opinions on one topic. The goal of our Fuzzy Believer system presented in this paper is to extract and analyze statements of opinion from newspaper articles. Beliefs are modeled using fuzzy set theory, applied after NLP-based information extraction. The Fuzzy Believer models a human agent, deciding what statements to believe or reject based on a range of configurable strategies.