Method and system for document classification based on document structure and written style

• US 8,082,248 B2
• Filed: 05/29/2008
• Issued: 12/20/2011
• Est. Priority Date: 05/29/2008
• Status: Active Grant

• Current Assignee: Rania Abouyounes
• Original Assignee: Rania Abouyounes
• Inventors: Abouyounes, Rania
• Primary Examiner(s): Betit, Jacob F
• Assistant Examiner(s): HOLLAND, SHERYL L
• Application Number:
  US12/129,596
• Publication Number:
  US 20090300046A1
• Time in Patent Office: 1,300 Days
• Field of Search: 707/771, 707/999.007, 707/731, 707/739
• US Class Current: 707/731
• CPC Class Codes: G06F 16/353 into predefined classes
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually

Abstract

A classification method and system for documents containing text sentences and images having meta-data. The classification method and system categorizes document sentences into subjective and non-subjective sentences and categorizes document images into descriptive and non-descriptive. The categorization is further used to calculate subjectivity and descriptive-images classification of a document. This classification system can be used by a web search engine to filter, sort or tag a set of document references based on user selection.

Claims

1. A method for determining the subjectivity, complexity and descriptive image classifications for a plurality of documents containing text sentences, alphabetic words and images having meta-data, comprising:

for each document of a plurality of documents;

a) categorizing at least one sentence as a subjective sentence and at least one sentence as non-subjective sentence;

wherein the at least one subjective sentence is categorized as a subjective sentence because the sentence includes one or more pronouns of the group;

I, we, he, she, they or you; and

wherein the at least one non-subjective sentence is categorized as a non-subjective sentence because the sentence does not include one or more pronouns of the group;

I, we, he, she, they or you;

b) categorizing at least one alphabetical word as a complex word and at least one alphabetical word as a non-complex word;

wherein the at least one complex word is categorized as a complex word because the number of syllables is over a threshold number of syllables; and

wherein the at least one non-complex word is categorized as a non-complex word because the number of syllables is less than a threshold number of syllables;

c) categorizing at least one image as descriptive image and at least one image as non-descriptive;

wherein the at least one descriptive image is categorized as a descriptive image because the at least one descriptive image includes an image size greater than a designated image size and the image meta-data includes a title or description; and

wherein the at least one non-descriptive image is categorized as a non-descriptive image because the at least one non-descriptive image includes an image size less than a designated image size or the image meta-data does not include a title or a description;

d) designating a document subjectivity classification that is equal to the ratio of subjective sentences to non-subjective sentences; and

designating a document complexity classification that is equal to the ratio of complex alphabetical words to non-complex alphabetical words; and

designating a document descriptive image classification that is equal to the total number of the descriptive images in a document;

e) wherein the subjectivity classification, the complexity classification and the descriptive image classification are associated with the document and stored in a database;

designating at least one document of the plurality of documents as a subjective document because its subjectivity classification is higher than a predetermined value;

designating at least one document of the plurality of documents as a non-subjective document because its subjectivity classification is lower than a predetermined value;

designating at least one document of the plurality of documents as a complex document because its complexity classification is higher than a predetermined value;

designating at least one document of the plurality of documents as a non-complex document because its complexity classification is lower than a predetermined value.

2. A document classification system for determining the subjectivity, complexity and descriptive image classifications for a plurality of documents containing text sentences, alphabetic words and images having meta-data, comprising:

at least one non-transitory computer readable medium; and

at least one processor; and

instructions stored on the at least one non-transitory computer readable medium which when executed by the at least one processor are configured to perform the following steps;

for each document of a plurality of documents;

a) categorizing at least one sentence as a subjective sentence and at least one sentence as non-subjective sentence;

wherein the at least one subjective sentence is categorized as a subjective sentence because the sentence includes one or more pronouns of the group;

I, we, he, she, they or you; and

wherein the at least one non-subjective sentence is categorized as a non-subjective sentence because the sentence does not include one or more pronouns of the group;

I, we, he, she, they or you;

b) categorizing at least one alphabetical word as a complex word and a non-complex word;

wherein the at least one alphabetical word is categorized as complex if the number of syllables is over a threshold; and

wherein the at least one alphabetical word is categorized as non-complex if the number of syllables is less than a threshold value;

c) categorizing at least one image as descriptive image and at least one image as non-descriptive;

wherein the at least one descriptive image is categorized as a descriptive image because the at least one descriptive image includes an image size greater than a designated size and the image meta-data includes a title or description; and

wherein the at least one non-descriptive image is categorized as a non-descriptive image because the at least one non-descriptive image includes an image size less than a designated image size or the image meta-data does not include a title or a description; and

d) designating a document subjectivity classification that is equal to the ratio of subjective sentences to non-subjective sentences; and

designating a document complexity classification that is equal to the ratio of complex alphabetical words to non-complex alphabetical words; and

designating a document descriptive image classification that is equal to the total number of the descriptive images per document; and

e) wherein the subjectivity classification, the complexity classification and the descriptive image classification are associated with the document and stored in a database;

designating at least one document of the plurality of documents as a subjective document because its subjectivity classification is higher than a predetermined value; and

designating at least one document of the plurality of documents as a non-subjective document because its subjectivity classification is lower than a predetermined value; and

designating at least one document of the plurality of documents as a complex document because its complexity classification is higher than a predetermined value; and

designating for each document of the plurality of documents as a non-complex document because its complexity classification is lower than a predetermined value.