Method of automatically constructing content for web sites

A machine readable storage medium storing executable program instructions which when executed cause a data processing system to perform a method for automatically generating content from a plurality of web sites into original content, comprising the steps of:

• searching a plurality of web sites on the internet using a predetermined key word to create a subset of said plurality of web sites having web content related to said predetermined keyword;
• creating a corpus by separating said web content into a plurality of sentences, each of said plurality of sentences having a plurality of words;
• filtering said plurality of sentences from said corpus for suitability of use in automatically generating said generated content by an analysis of at least one of (1) sentence grammar, (2) sentence form, (3) sentence punctuation, (4) sentence length, and (5) said plurality of words;
• determining a topic, separately for each of said plurality of sentences using a topic model creating a plurality of topics;
• ranking each of said plurality of topics based upon a determination of uniqueness keeping a portion of said plurality of sentences with said topic having a relatively higher ranking and discarding those of said plurality of sentences with said topic having a relatively lower ranking;
• instantiating a new sentence by taking a first portion of a first one of said plurality of topics combined with a second portion of a second one of said plurality of topics;
• and
• repeating said instantiating step taking a different portion of a different one of said plurality of topics combined with another portion of said still another one of said plurality of topics until a number of new sentences are formed.