System and method for rating a written document

A writing rating method implemented in a computer infrastructure having computer executable code tangibly embodied on a computer readable storage medium including programming instructions operable to rate a writing written in any language, comprising the steps of:

• providing a style score based on how a language style of the writing is different from at least one training document,
• wherein providing the style score includes constructing an n-gram list for the at least one training document and an n-gram list for the input document and comparing the n-gram list of the at least one training document to the n-gram list of the input document to provide the style score based on how the language style of the input document is different from the at least one training document;
• providing a punctuation score based on a comparison between the use of punctuation marks in the writing and the use of punctuation marks in the at least one training document,
• wherein providing the punctuation score includes comparing an average number of punctuation marks in the input document to an average number of punctuation marks in the at least one training document;
• providing a spelling score based on spelling accuracy of the writing;
• providing a quotation score based on a comparison between sentences from the writing and the sentences from the at least one training document;
• providing an enrichment score based on new and accurate vocabularies used in the writing;
• providing a syntax analysis score based on grammar mistakes in the writing;
• providing a focus score based on a topic of the essay and a focus of the writing on that topic;
• providing an idea and cohesion scores based on whether the writing provides a close or far away cohesive correct answer;
• and
• providing the rating of the writing based on the style score, the punctuation score, the spelling score, the quotation score, the enrichment score, the syntax analysis score, the focus score, the idea score and the cohesion score.

A computer program product comprising a non-transitory computer usable storage medium having readable program code embodied in the storage medium, the computer program product includes at least one component operable to:

• provide a style score based on how a language style of an input document is different from at least one training document,
• wherein providing the style score includes constructing an n-gram list for the at least one training document and an n-gram list for the input document and comparing the n-gram list of the at least one training document to the n-gram list of the input document to provide the style score based on how the language style of the input document is different from the at least one training document;
• provide a punctuation score based on a comparison between the use of punctuation marks in the input document and use of punctuation marks in the at least one training document,
• wherein providing the punctuation score includes comparing an average number of punctuation marks in the input document to an average number of punctuation marks in the at least one training document;
• provide a spelling score based on spelling accuracy of the input document;
• provide a quotation score based on a comparison between sentences from the input document and sentences from the at least one training document;
• provide an enrichment score based on new and accurate vocabularies used in the input document;
• provide a syntax analysis score based on grammar mistakes in the input document;
• provide a focus score based on a topic of the essay and a focus of the input document on that topic;
• provide an idea and a cohesion score based on whether the input document provides a close or far away cohesive correct answer;
• and
• provide a rating of the input document based on the style score, the punctuation score, the spelling score, the quotation score, the enrichment score, the syntax analysis score, the focus score, the idea score and the cohesion score.