Abstract: Systems and methods for document classification by confidentiality levels. An example method comprises: receiving an electronic document comprising a natural language text; obtaining document metadata associated with the electronic document; extracting, from the natural language text, a plurality of information objects represented by the natural language text; computing a confidentiality level associated with the electronic document, by applying, to the extracted information objects and the document metadata, a set of classification rules; and associating the electronic document with a metadata item reflecting the computed confidentiality level.