User-generated data in blogs and social networks has recently become a valuable resource for sentiment analysis in the financial domain since it has been shown to be extremely significant to marketing research companies and public opinion organizations. In this paper a fine-grained approach is proposed to predict a real-valued sentiment score. We use several feature sets consisting of lexical features, semantic features and combination of lexical and semantic features. To evaluate our approach a microblog messages dataset is used. Since our dataset includes confidence scores of real numbers within the [0-1] range, we compare the performance of two learning methods: Random Forest and SVR. We test the results of the training model boosted by semantics against classification results obtained by n-grams. Our results indicate that our approach succeeds in performing the accuracy level of more than 72% in some cases.