SVO-BASED TAXONOMY-DRIVEN TEXT ANALYTICS

• US 20140129213A1
• Filed: 09/09/2013
• Published: 05/08/2014
• Est. Priority Date: 11/07/2012
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Li, Yunyao, Vaithyanathan, Shivakumar, Kimelfeld, Benny
• Granted Patent: US 9,465,790 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 40/211 Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars

Abstract

Organizing textual data 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 method comprising:

receiving textual data, and analyzing the received data, including identifying at least one sentence from the received data;

parsing the identified sentence, including extracting and identifying a subject, a verb, and an object, within the parsed sentence;

identifying a verb usage pattern in the parsed sentence;

categorizing the extracted and identified subject, verb, and object, the categorization of the verb responsive to the identified verb usage pattern; and

classifying the sentence based on the categorized subject, verb, and object.

2. The method of claim 1, further comprising deriving sentiment from the extracted and identified subject, verb, and object within the sentence.

3. The method of claim 2, wherein the derived sentiment is determined from a predefined category, the category including positive, neutral, and negative.

4. The method of claim 2, further comprising classifying the sentence with respect to the derived sentiment.

5. The method of claim 4, further comprising producing an analysis report reflective of the classified sentence, and clustering the received data into a summary report reflective of the analysis report.

6. The method of claim 1, further comprising classifying the subject, verb, and object of the parsed sentence based upon a domain specific taxonomy associated with the received data.

7. The method of claim 1, wherein the categorization of the verb responsive to the identified verb usage pattern is based on a reference to an existing linguistic resource to provide a mapping from the verb usage pattern to the categorization of the verb.