Method and system for identifying web documents for advertisements

1. A computerized system for selecting advertisement spots for web documents, comprising:

a program store storing code

a database storing a dataset mapping between at least one of a plurality of writing patterns, at least one editorial feature, and at least one of a plurality of demographic segments, wherein each of said plurality of writing patterns comprises a frequency of occurrence of a member from a group consisting of an article, an auxiliary verb, a conjunction, a preposition, and a pronoun, wherein the at least one editorial feature is a feature that has an effect on the look and feel of an analyzed web document; and

a hardware processor coupled to a data interface connected to a network, said database, and said program store for implementing stored code, the code comprising:

code to identify, using said hardware processor, at least one writing pattern in each of a plurality of web documents, wherein said at least one writing pattern is selected from a plurality of writing patterns, and to identify at least one editorial feature in each of said plurality of web documents, wherein said at least one writing pattern maps to at least one of said plurality of demographic segments, said mapped at least one demographic segment being a demographic segment of a targeted audience of each of said plurality of web documents, wherein said at least one editorial feature is identified by analyzing the layout of graphical elements of a graphical user interface (GUI) of a respective web document of said plurality of web documents, wherein said analyzing the layout includes one or more members selected from the group consisting of: arrangement of at least one of video files and images in the web document, prevalence of at least one of video files and images in the web document, icons used to represent functions, and size and position of windows;

code to receive by said hardware processor through said data interface over said network an advertisement and a target demographic segment from an advertisement server,

code to select, using said hardware processor, a cluster of web documents from said plurality of web documents such that said at least one writing pattern and said at least one editorial feature of each member of said cluster is associated with a demographic segment of said targeted audience of web documents that corresponds to said target demographic segment, and

code to send instructions over a network to a client terminal to present said advertisement when said member of said cluster is rendered by a browser of said client terminal;

wherein as a response of executing said sent instructions when at least one visitor sends a request to view said member of said cluster, said advertisement and said member are presented together in said browser to said at least one visitor.

2. The computerized system of claim 1 , wherein said plurality of demographic segments are based on at least one characteristic of a group consisting of: a gender, a social class, a socio economic class, a native language, a personality characteristic, an education level, an income level, and sociability.

3. A computer usable non-transitory storage medium having a computer program embodied thereon for causing a suitably programmed system to select advertisement spots for web documents, by performing the following steps when said computer program is executed by a processor, the steps comprising:

providing database storing a dataset mapping between at least one of a plurality of writing patterns, at least one editorial feature, and at least one of a plurality of demographic segments, wherein each of said plurality of writing patterns comprises a frequency of occurrence of a member from a group consisting of an article, an auxiliary verb, a conjunction, a preposition, and a pronoun, wherein the at least one editorial feature is a feature that has an effect on the look and feel of an analyzed web document;

identifying at least one writing pattern in each of a plurality of web documents, wherein said at least one writing pattern is selected from a plurality of writing patterns, and identifying at least one editorial feature in each of said plurality of web documents, wherein said at least one writing pattern maps to at least one of said plurality of demographic segments, said mapped at least one demographic segment being a demographic segment of a targeted audience of each of said plurality of web documents, wherein said at least one editorial feature is identified by analyzing the layout of graphical elements of a graphical user interface (GUI) of a respective web document of said plurality of web documents, wherein said analyzing the layout includes one or more members selected from the group consisting of: arrangement of at least one of video files and images in the web document, prevalence of at least one of video files and images in the web document, icons used to represent functions, and size and position of windows;

receiving an advertisement and a target demographic segment;

selecting a cluster of web documents from said plurality of web documents such that respective said at least one writing pattern and said at least one editorial feature of each member of said cluster is associated with a demographic segment of said targeted audience of web documents that corresponds to said target demographic segment; and

sending instructions to present said advertisement when said member of said cluster is rendered by a browser;

wherein as a response of executing said sent instructions when at least one visitor sends a request to view said member of said cluster, said advertisement and said member are presented together in said browser to said at least one visitor.

4. The system of claim 1 , wherein each of said plurality of writing patterns comprises at least one content-based textual feature and at least one style-based textual feature, wherein combination of said at least one content-based textual feature and at least one style-based textual feature are specific to one of said plurality of demographic segments.

5. The computerized system of claim 1 , wherein each of said plurality of writing patterns comprises a further association with a member from a group consisting of demographically distinct lexical features, demographically distinct syntactic features, demographically distinct vocabulary features, demographically distinct grammatical errors and demographically distinct orthographic errors, and wherein said further association determines at least one of said plurality of demographic segments.

6. The computer usable non-transitory storage medium system of claim 3 , wherein each of said plurality of writing patterns comprises at least one content-based textual feature and at least one style-based textual feature, wherein combination of said at least one content-based textual feature and at least one style-based textual feature are specific to one of said plurality of demographic segments.

7. The computer usable non-transitory storage medium system of claim 3 , wherein each of said plurality of writing patterns comprises a further association with a member from a group consisting of demographically distinct lexical features, demographically distinct syntactic features, demographically distinct vocabulary features, demographically distinct grammatical errors and demographically distinct orthographic errors, and wherein said further association determines at least one of said plurality of demographic segments.

8. The computerized system of claim 1 , wherein each of said plurality of writing patterns further comprises one of a plurality of certain web document layout designs, each of said plurality of certain web document layout designs associated with one of said plurality of demographic segments, wherein each of said plurality of certain web document layout designs comprises an demographically distinct organization pattern of content and images on a web document.

9. A method for selecting advertisement spots for web documents, comprising:

providing database storing a dataset mapping between at least one of a plurality of writing patterns, at least one editorial feature, and at least one of a plurality of demographic segments, wherein each of said plurality of writing patterns comprises a frequency of occurrence of a member from a group consisting of an article, an auxiliary verb, a conjunction, a preposition, and a pronoun, wherein the at least one editorial feature is a feature that has an effect on the look and feel of an analyzed web document;

identifying at least one writing pattern in each of a plurality of web documents, wherein said at least one writing pattern is selected from a plurality of writing patterns, wherein said at least one writing pattern maps to at least one of the plurality of demographic segments, said mapped at least one demographic segment being a demographic segment of a targeted audience of each of said plurality of web documents, and identifying at least one editorial feature in each of said plurality of web documents, wherein said at least one editorial feature is identified by analyzing the layout of graphical elements of a graphical user interface (GUI) of a respective web document of said plurality of web documents, wherein said analyzing the layout includes one or more members selected from the group consisting of: arrangement of at least one of video files and images in the web document, prevalence of at least one of video files and images in the web document, icons used to represent functions, and size and position of windows, wherein said at least one editorial feature maps to at least one of the plurality of demographic segments;

receiving an advertisement and a target demographic segment;

selecting a cluster of web documents from said plurality of web documents such that respective said at least one writing pattern and said at least one editorial feature of each member of said cluster is associated with a demographic segment of said targeted audience of web documents that corresponds to said target demographic segment; and

sending instructions to present said advertisement when said member of said cluster is rendered by a browser;

wherein as a response of executing said sent instructions when at least one visitor sends a request to view said member of said cluster, said advertisement and said member are presented together in said browser to said at least one visitor.

10. The method of claim 9 , wherein said plurality of demographic segments are based on at least one characteristic of a group consisting of: a gender, a social class, a socio economic class, a native language, a personality characteristic, an education level, an income level, and sociability.

11. The method of claim 9 , wherein said plurality of writing patterns comprise a further association with a member from a group consisting of demographically distinct lexical features, demographically distinct syntactic features, demographically distinct vocabulary features, demographically distinct grammatical errors and demographically distinct orthographic errors, and wherein said further association determines at least one of said plurality of demographic segments.