Semi-automated Content Zoning of Spam Emails

CoZo+ - A Content Zoning Engine for textual documents

“…We have presented a engine for the zoning of content as it was initially introduced in [1]. The engine consists of several modules that process incoming texts by firstly removing any formats, resolving pronouns to his corresponding actor, and finally outputs the texts including the zones.…”

“…Cozo+ is a zoning engine and an extension to Cozo ( [1]). Cozo+ consists of two main modules, which is a preprocessing module and a text-stream processing module (see Figure 1).…”

“…A zone can be described as a set of sentences or paragraphs describing the same topic owning a zone name to reflect the topic. In a first approach to content zoning ( [1]), this has been applied to the analysis of spam emails -as means to separate spam from non-spam electronic mails. An important aspect in the zoning of texts is its structuring in itself -that has to be learned.…”