SVO-based taxonomy-driven text analytics

• US 9,817,810 B2
• Filed: 11/07/2012
• Issued: 11/14/2017
• Est. Priority Date: 11/07/2012
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Kimelfeld, Benny, Li, Yunyao, Vaithyanathan, Shivakumar
• Primary Examiner(s): PULLIAS, JESSE SCOTT
• Application Number:
  US13/671,213
• Publication Number:
  US 20140129211A1
• Time in Patent Office: 1,833 Days
• Field of Search: 704 1, 704 9, 704 10
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars

Abstract

Textual data is organized into statement clusters. Sentences are extracted from textual data and parsed. A verb usage pattern is identified and an SVO triplet is determined. The SVO triplet is compared to a taxonomy associated with the domain of the data and a sentiment is derived. A statement cluster is constructed comprising a higher level SVO triplet sensitive to the taxonomy and verb usage pattern, as well as the derived sentiment. Accordingly, the statement clusters may be organized by grouping.

Claims

1. A computer program product for classifying data, the computer program product comprising a computer readable storage device having program code embodied therewith, the program code being executable by a processor to:

receive textual data, and analyze the received data,

wherein the analysis comprises program code to;

identify at least one sentence from the received data;

parse parts of speech of one or more words of the identified sentence using a linguistic parser, including parsing a verb from the at least one parsed sentence, and identifying a verb usage pattern in the at least one identified sentence;

form a low level subject-verb-object (SVO) triplet for the at least one parsed sentence, including identifying a subject, verb, and object of the at least one parsed sentence, wherein the identification of the subject, verb, and object comprises joining the identified verb usage pattern with a form of the identified verb to ascertain linguistic taxonomy;

form a high level SVO triplet for the at least one parsed sentence, including determining a subject category for the subject, a verb category for the verb, and an object category for the object based on the taxonomy; and

classify the at least one parsed sentence based on the high level SVO triplet; and

summarize the analysis of the stored data, including;

produce an analysis report reflective of the analysis; and

convert the produced analysis report into a summary report reflective of the analysis report, including cluster the received textual data into one or more statement clusters, wherein the summary report comprises the statement clusters.

2. The computer program product of claim 1, further comprising program code to derive sentiment from the identified subject, verb, and object.

3. The computer program product of claim 2, wherein the derived sentiment is determined from a predefined category selected from the group consisting of:

positive, neutral, and negative.

4. The computer program product of claim 2, wherein the sentence is further classified with respect to the derived sentiment.

5. The computer program product of claim 1, wherein the taxonomy is a domain specific taxonomy associated with the received data.

6. The computer program product of claim 1, wherein the joining of the identified verb usage pattern with a form of the identified verb comprises program code to map the verb usage pattern to the identified verb based on a reference to an existing linguistic resource.

7. The computer program product of claim 1, wherein the form of the identified verb is a root form of the identified verb.

8. The computer program product of claim 1, wherein the parsing comprises program code to create a parse tree to provide a tag for each token in the at least one identified sentence.

9. A system comprising:

a processing unit in communication with data storage;

a functional unit having memory and in communication with the processing unit, the functional unit having tools to support data classification, the tools comprising;

an extraction manager in communication with data storage, the extraction manager to receive textual data, and analyze the received data;

an identification manager in communication with the extraction manager, the identification manager to;

identify at least one sentence from the received data;

parse parts of speech of one or more words of the identified sentence using a linguistic parser, including parse a verb from the at least one parsed sentence, and identify a verb usage pattern in the at least one identified sentence; and

form a low level subject-verb-object (SVO) triplet for the at least one parsed sentence, including identify a subject, verb, and object of the at least one parsed sentence, wherein the identification of the subject, verb, and object comprises a join of the identified verb usage pattern with a form of the identified verb to ascertain linguistic taxonomy; and

an organization manager in communication with the identification manager, the organization manager to;

form a high level SVO triplet for the at least one parsed sentence, including determine a subject category for the subject, a verb category for the verb, and an object category for the object based on the taxonomy; and

classify the at least one parsed sentence based on the high level SVO triplet; and

summarize the analysis of the stored data, including;

produce an analysis report reflective of the analysis; and

convert the produced analysis report into a summary report reflective of the analysis report, including cluster the received textual data into one or more statement clusters, wherein the summary report comprises the statement clusters.

10. The system of claim 9, further comprising the identification manager to derive sentiment from the identified subject, verb and object.

11. The system of claim 10, wherein the organization manager further classifies the sentence with respect to the derived sentiment.

12. The system of claim 10, wherein the derived sentiment is determined from a predefined category selected from the group consisting of:

positive, neutral, and negative.

13. The system of claim 9, wherein the form of the identified verb is a root form of the identified verb.

14. The system of claim 9, further comprising the identification manager to create a parse tree to provide a tag for each token in the at least one identified sentence.

15. The system of claim 9, wherein the taxonomy is a domain specific taxonomy associated with the received data.

16. The system of claim 9, wherein the join of the identified verb usage pattern with a form of the identified verb comprises a map of the verb usage pattern to the identified verb based on a reference to an existing linguistic resource.