Weather-based natural language text processing

1. A method for performing electronic natural language processing on unstructured data, comprising:

extracting relationships between descriptors stored in one or more lists of weather condition descriptors and adverse event descriptors;

generating a data object according to a data model, based on the extracted relationships between the descriptors,

wherein generating the data object according to the data model further comprises generating the data object comprising at least three descriptors, including a weather condition descriptor, an adverse event descriptor, and a medical condition descriptor, wherein the at least three descriptors have a corresponding extracted relationship, and wherein the medical condition descriptor comprises a span of electronic text characters associated with an illness or abnormality;

retrieving a set of candidate unstructured documents comprising instances of the adverse event descriptor and a related weather condition descriptor;

filtering the retrieved set of candidate unstructured documents by selecting candidate unstructured documents that comprise a precautionary measure descriptor; and

displaying the filtered set of candidate unstructured documents on a display device.

2. The method of claim 1 , wherein the filtering further comprises:

selecting candidate unstructured documents that comprise a relationship rule between the weather condition descriptor and the adverse event descriptor.

3. The method of claim 1 , further comprising:

generating a summary of unstructured text comprising precautionary measure information associated with the precautionary measure descriptor.

4. The method of claim 1 , further comprising:

scanning a set of unstructured documents to identify one or more descriptors; and

generating the one or more lists of weather condition descriptors and adverse event descriptors based on the scanning.

5. The method of claim 1 ,

wherein the weather condition descriptor comprises a span of electronic text characters associated with an atmospheric condition,

wherein the adverse event descriptor comprises a span of electronic text characters associated with an occurrence, and

wherein the precautionary measure descriptor comprises a span of electronic text characters associated with an action relative to the adverse event descriptor.

6. The method of claim 1 , wherein generating a data object according to the data model further comprises:

generating the data object to include at least four descriptors, including the weather condition descriptor, the adverse event descriptor, the medical condition descriptor, and the precautionary measure descriptor, wherein the at least four descriptors have the corresponding extracted relationship.

7. The method of claim 1 , wherein extracting the relationships between descriptors stored in the one or more lists of weather condition descriptors and adverse event descriptors comprises:

generating a candidate data object comprising descriptors identified as related;

presenting the candidate data object to a user for identification of known relationships;

receiving an input from the user identifying the candidate data object as comprising the descriptors having a known relationship; and

filtering from the extracted relationships the user-identified candidate data object comprising descriptors having a known relationship, wherein generating a data object according to a data model excludes the filtered candidate data object.

8. The method of claim 1 , further comprising:

receiving the weather condition descriptor associated with a user;

determining, based on the generated data object, the adverse event descriptor and the precautionary measure descriptor associated with the received weather condition descriptor; and

generating a message to the user based on the adverse event descriptor and a related precautionary measure descriptor.

9. The method of claim 8 , wherein generating a message to the user comprises:

generating the message based on a summary of the related precautionary measure descriptor.

10. The method of claim 8 , wherein the generated data object comprises at least four descriptors, including a weather condition descriptor, an adverse event descriptor, a medical condition descriptor, and a precautionary measure descriptor, wherein the at least four descriptors have a corresponding extracted relationship, and wherein the determining further comprises:

receiving the medical condition descriptor associated with the user,

wherein generating the message is further based on the received medical condition descriptor.

11. The method of claim 8 , further comprising:

receiving the medical condition descriptor of the user;

scoring data objects in the generated data model based on the received medical condition descriptor of the user.

12. The method of claim 1 , wherein extracting relationships between descriptors stored in one or more lists of weather condition descriptors and adverse event descriptors comprises:

identifying the relationships using any one or more of: a co-occurrence analysis process, a machine learning process, and a syntactic analysis process.

13. The method of claim 1 , wherein an adverse event descriptor comprises:

a span of electronic text that includes a verb in gerund form and a noun to which the verb applies, where the noun has a negative sentiment as determined by a sentiment analyzer.

14. A computer program product for performing electronic natural language processing on unstructured data, comprising a non-transitory tangible storage device having program code embodied therewith, the program code executable by a processor of a computer to perform a method, the method comprising:

extracting, by the processor, relationships between descriptors stored in one or more lists of weather condition descriptors and adverse event descriptors;

generating, by the processor, a data object according to a data model, based on the extracted relationships between the descriptors,

wherein generating, by the processor, the data object according to the data model further comprises generating, by the processor, the data object comprising at least three descriptors, including a weather condition descriptor, an adverse event descriptor, and a medical condition descriptor, wherein the at least three descriptors have a corresponding extracted relationship, and wherein the medical condition descriptor comprises a span of electronic text characters associated with an illness or abnormality;

retrieving, by the processor, a set of candidate unstructured documents comprising instances of the adverse event descriptor and a related weather condition descriptor;

filtering, by the processor, the retrieved set of candidate unstructured documents by selecting candidate unstructured documents that comprise a precautionary measure descriptor; and

displaying, by the processor, the filtered set of candidate unstructured documents on a display device.

15. The computer program product of claim 14 , wherein the method further comprises:

generating, by the processor, a summary of unstructured text comprising precautionary measure information associated with the precautionary measure descriptor.

16. The computer program product of claim 14 , wherein the method further comprises:

scanning, by the processor, a set of unstructured documents to identify one or more descriptors; and

generating, by the processor, the one or more lists of weather condition descriptors and adverse event descriptors based on the scanning.

17. A computer system for performing electronic natural language processing on unstructured data, comprising:

one or more computer devices each having one or more processors and one or more tangible storage devices; and

a program embodied on at least one of the one or more storage devices, the program having a plurality of program instructions for execution by the one or more processors, the program instructions comprising instructions for:

extracting, by the computer, relationships between descriptors stored in one or more lists of weather condition descriptors and adverse event descriptors;

generating, by the computer, a data object according to a data model, based on the extracted relationships between the descriptors,

wherein generating, by the computer, the data object according to the data model further comprises generating, by the computer, the data object comprising at least three descriptors, including a weather condition descriptor, an adverse event descriptor, and a medical condition descriptor, wherein the at least three descriptors have a corresponding extracted relationship, and wherein the medical condition descriptor comprises a span of electronic text characters associated with an illness or abnormality;

retrieving, by the computer, a set of candidate unstructured documents comprising instances of the adverse event descriptor and a related weather condition descriptor;

filtering, by the computer, the retrieved set of candidate unstructured documents by selecting candidate unstructured documents that comprise a precautionary measure descriptor; and

displaying, by the computer, the filtered set of candidate unstructured documents on a display device.

18. The computer system of claim 17 , wherein the program instructions further comprise instructions for:

generating, by the computer, a summary of unstructured text comprising precautionary measure information associated with the precautionary measure descriptor.

19. The computer system of claim 17 , wherein the program instructions further comprise instructions for:

scanning, by the computer, a set of unstructured documents to identify one or more descriptors; and

generating, by the computer, the one or more lists of weather condition descriptors and adverse event descriptors based on the scanning.