Text analysis on unstructured text to identify a high level of intensity of negative thoughts or beliefs

Patent metadata

Field	Value
Publication number	US-9875230-B2
Application number	US-201615094352-A
Country	US
Kind code	B2
Filing date	Apr 8, 2016
Priority date	Apr 8, 2016
Publication date	Jan 23, 2018
Grant date	Jan 23, 2018

Abstract

A method, a processing device, and a computer program product are provided. Via at least one processing device, each text file is selected from a collection of text files, wherein the collection of text files has an intensity with respect to negative sentiment toward a common issue. At least one profile algorithm is performed, each calculating a corresponding profile score for that text file. At least one corresponding profile score of the text files of the collection are combined to produce an aggregated profile score for each of at least one profile algorithm. The aggregated profile score of each of the at least one profile algorithm for the collection is stored. A signature for the collection of text files includes the aggregated profile score of each of the at least one profile algorithm for the collection.

First claim

The invention claimed is:

1. A computer-implemented method comprising:
selecting, via at least one processing device, each text file from a collection of text files, wherein the collection of text files have an intensity with respect to negative sentiment toward a common issue;
performing, for each text file, by the at least one processing device, at least one profile algorithm, each calculating a corresponding profile score for that text file;
combining, by the at least one processing device, at least one corresponding profile score of the text files of the collection to produce a signature for the collection of text files including an aggregated profile score for each of the at least one profile algorithm;
storing the aggregated profile score of each of the at least one profile algorithm for the collection;
performing the at least one profile algorithm with respect to a desired text file to calculate a signature for the desired text file, the signature including a corresponding profile score for each of the at least one profile algorithm performed with respect to the desired text file; and
performing a user-configured action when the signature of the collection is within a threshold distance of the signature of the desired text file, the user-configured action being a contacting action.

2. The computer-implemented method of claim 1 , further comprising:
computing a signature for each of one or more other collections of text files, each of the collections of text files being authored by a respective author and includes a varying intensity.

3. The computer-implemented method of claim 2 , wherein at least some of the authors performed a negative act with undesirable impact and are associated with an intensity of the negative sentiment of a corresponding collection.

4. The computer-implemented method of claim 2 , further comprising:
calculating a distance between the signature of each of the collection of text files and the signature of the desired text file.

5. The computer-implemented method of claim 4 , wherein the distance is based on a Euclidean distance.

6. The computer-implemented method of claim 1 , wherein at least one of the at least one profile algorithm includes a first algorithm that calculates a profile score based on use and frequency of use of specific keywords in a text file.

7. At least one processing device, each of the at least one processing device comprising:
at least one processor;
a memory; and
a communication bus connecting the at least one processor with the memory, wherein the memory has stored therein instructions, which when executed by the at least one processor cause the at least one processing device to perform a method comprising:
selecting each text file from a collection of text files, wherein the collection of text files have an intensity with respect to negative sentiment toward a common issue; and
performing for each text file, at least one profile algorithm, each calculating a corresponding profile score for that text file;
combining at least one corresponding profile score of the text files of the collection to produce a signature for the collection of text files including an aggregated profile score for each of the at least one profile algorithm;
storing the aggregated profile score of each of the at least one profile algorithm for the collection;
performing the at least one profile algorithm with respect to a desired text file to calculate a signature for the desired text file, the signature including a corresponding profile score for each of the at least one profile algorithm performed with respect to the desired text file; and
performing a user-configured action when the signature of the collection is within a threshold distance of the signature of the desired text file, the user-configured action being a contacting action.

8. The at least one processing device of claim 7 , wherein at least one of the at least one profile algorithm includes a first algorithm that calculates a profile score based on use and frequency of use of specific keywords in a text file.

9. The at least one processing device of claim 7 , wherein the method further comprises:
computing a signature for each of one or more other collections of text files, each of the collections of text files being authored by a respective author and includes a respective varying intensity.

10. The at least one processing device of claim 9 , wherein at least some of the authors performed a negative act with undesirable impact and are associated with an intensity of negative sentiment of a corresponding collection.

11. The at least one processing device of claim 9 , further comprising:
calculating a distance between the signature of each of the collection of text files and the signature of the desired text file.

12. The at least one processing device of claim 11 , wherein the distance is based on a Euclidean distance.

13. A computer program product comprising:
a computer readable storage medium having computer readable program code embodied therewith for execution on a processing system, the computer readable program code being configured to be executed by the processing system to:
select each text file from a collection of text files, wherein the collection of text files have an intensity with respect to negative sentiment toward a common issue;
perform for each text file at least one profile algorithm, each calculating a corresponding profile score for that text file;
combine at least one corresponding profile score of the text files of the collection to produce a signature for the collection of text files including an aggregated profile score for each of the at least one profile algorithm;
store the aggregated profile score for each of the at least one profile algorithm for the collection;
perform the at least one profile algorithm with respect to a desired text file to calculate a signature for the desired text file, the signature including a corresponding profile score for each of the at least one profile algorithm performed with respect to the desired text file; and
performing a user-configured action when the signature of the collection is within a threshold distance of the signature of the desired text file, the user-configured action being a contacting action.

14. The computer program product of claim 13 , wherein the computer readable program code is further configured to be executed by the processing system to:
compute a signature for each of one or more other collections of text files, each of the collections of text files being authored by a respective author and includes a respective varying intensity.

15. The computer program product of claim 14 , wherein at least some of the authors performed a negative act with undesirable impact and are associated with an intensity of the negative sentiment of a corresponding collection.

16. The computer program product of claim 14 , further comprising:
calculating a distance between the signature of each of the collection of text files and the signature of the desired text file.

17. The computer program product of claim 16 , wherein the distance is based on a Euclidean distance.

Assignees

• IBM

Inventors

• Fink Patrick W
• Mcneil Kristin E
• Parker Philip E
• Werts David B

Classifications

• G06F40/30 Primary

  Semantic analysis · CPC title

• G06F16/35 Primary

  Clustering; Classification · CPC title

• G06F17/2785

  Physics · mapped topic

• G06F17/2705 Primary

  Physics · mapped topic