Detecting literary elements in literature and their importance through semantic analysis and literary correlation

• US 10,073,836 B2
• Filed: 09/18/2014
• Issued: 09/11/2018
• Est. Priority Date: 12/03/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Allen, Corville Orain, Carrier, Scott Robert, Woods, Eric
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Le, Thuykhanh
• Application Number:
  US14/489,652
• Publication Number:
  US 20150154179A1
• Time in Patent Office: 1,454 Days
• Field of Search: None
• CPC Class Codes: G06F 40/169 Annotation, e.g. comment data or footnotes
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

Automatic semantic analysis for characterizing and correlating literary elements within a digital work of literature is accomplished by employing natural language processing and deep semantic analysis of text to create annotations for the literary elements found in a segment or in the entirety of the literature, a weight to each literary element and its associated annotations, wherein the weight indicates an importance or relevance of a literary element to at least the segment of the work of literature; correlating and matching the literary elements to each other to establish one or more interrelationships; and producing an overall weight for the correlated matches.

Claims

1. A method for automatic semantic analysis for characterizing and correlating literary elements within a digital work of literature, the method comprising:

performing, by a computer system, deep semantic analysis of a digital work of literature to create annotations for one or more literary elements, wherein the deep semantic analysis comprises a combination of information retrieval operations, natural language processing, knowledge representation, and machine learning;

assigning, by a computer system, an importance and relevance weight to each of the annotations according as determined by the deep semantic analysis;

identifying, by a computer system, from the deep semantic analysis, one or more plot devices within each literary plot in the digital work of literature, wherein the one or more plot devices are distinguished from general theme and general plot,

associating, by a computer system, the one or more plot devices with one or more non-plot device literary elements;

identifying, by a computer system, a theme for each of the one or more plot devices;

combining, by a computer system, the importance and relevance weights associated with each respective interrelationship to yield an overall weight for each of the interrelationships; and

producing, by a computer system, an output depiction on a user interface device, the annotations, the interrelationships, and the overall weights, for facilitating the user to easily and conveniently see an overall make-up of the work of literature, to be informed of where each literary element exists in that make-up, and to understand relative strengths of each literary element within the context of the make-up.

2. The method as set forth in claim 1 wherein the annotations include one or more annotations selected from the group consisting of humor, imagery, adventure, character, character mood, and suspense.

3. The method as set forth in claim 2 wherein the humor annotation is further classified as a type of humor.

4. The method as set forth in claim 1 wherein at least one literary element annotation weight is normalized across a category in which the literary element has been categorized.

5. The method as set forth in claim 1 wherein at least one literary element weight is normalized across a segment of the digital work of literature in which the literary element is found.

6. The method as set forth in claim 1 further comprising, prior to the performing natural language processing and deep semantic analysis, automatically breaking by a computer system the digital work of literature into segments.

7. The method as set forth in claim 6 wherein the breaking into segments is performed according to one or more rules selected from the group consisting of proportionally dividing the entire digital work of literature into a fixed number of segments and dividing the entire digital work of literature into segments according to fixed lengths of the segments.

8. The method as set forth in claim 1 wherein the correlating and matching comprises assigning to each literary element one or more attributes selected from the group consisting of level of importance within the segment, level of prevalence within the segment, number of parties in a relationship to which the literary element pertains in the segment, and number of plot devices in the segment to which the literary element pertains.

9. The method as set forth in claim 8 wherein the combining overall weights for a literary element is bound within each associated segment by applying a mathematical weighting function to the one or more attributes.

10. The method as set forth in claim 9 wherein the correlating and matching further comprises calculating an overall weight for a literary element within a plurality of segments by applying a mathematical weighting function to one or more segment-bound overall weights.

11. The method as set forth in claim 8 wherein the correlating and matching further comprises calculating an overall weight for a literary element within the entire digital work of literature by applying a mathematical weighting function to the one or more attributes.