Dynamic contrarian view analysis in natural language content
From a first content including a first assertion, using a natural language processing engine, a plurality of knowledge blocks is extracted. A metric corresponding to a first knowledge block in the plurality of knowledge blocks is computed, the metric evaluating a corpus of content against the first knowledge block. By comparing the metric with the first knowledge block, the first assertion is identified as a contrarian assertion. An indication of the contrarian assertion is caused to become visually associated with a portion of the first content on a presentation device.
1. A computer-implemented method comprising:
constructing a modified natural language processing (NLP) engine, the constructing comprising:
enabling the NLP engine to extract, from an input comprising a first content including a first assertion, a plurality of knowledge blocks;
configuring a computational module to operate with the NLP engine to compute a metric corresponding to a first knowledge block in the plurality of knowledge blocks, the metric evaluating a corpus of content against the first knowledge block, wherein the computational module causes a behavior of the NLP engine to adjust the metric using a half-life hyperparameter on a consensus detected in the corpus;
further configuring the NLP engine to dynamically determine a contrarian view expressed in a corpus of content by comparing the metric with the first knowledge block and identifying the first assertion as a contrarian assertion, wherein the contrarian assertion is an assertion that has a contrary correlation with the consensus detected in the corpus; and
causing a presentation device to visually associate an indication of the contrarian assertion with a portion of the first content.
2. The computer-implemented method of claim 1 , wherein the first knowledge block comprises an assertion of a direction of an indicator and the metric comprises a ratio of upward assertions of the indicator present in the corpus to total assertions of the indicator present in the corpus.
3. The computer-implemented method of claim 2 , wherein the ratio is weighted by a half-life parameter, the half-life parameter decreasing according to an elapsed time.
4. The computer-implemented method of claim 1 , further comprising:
computing a novelty metric corresponding to the first knowledge block, the novelty metric evaluating the corpus of content against the first knowledge block, wherein the novelty metric comprises a ratio of assertions of the first knowledge block within a first time period to assertions of the first knowledge block within a second time period, the second time period longer than the first time period.
5. The computer-implemented method of claim 1 , further comprising:
adding, to the corpus of content, the first content and the plurality of knowledge blocks.
6. The computer-implemented method of claim 1 , further comprising:
receiving a query comprising a second knowledge block;
evaluating, using the metric, the corpus of content against the second knowledge block;
identifying, using the metric, a second content within the corpus, the second content comprising an assertion responsive to the query; and
causing an indication of the assertion responsive to the query to become visually associated with a portion of the second content on the presentation device.
7. A computer program product comprising one or more computer readable storage medium, and program instructions collectively stored on the one or more computer readable storage medium, the program instructions executable by a processor to cause the processor to perform operations comprising:
constructing a modified natural language processing (NLP) engine, the constructing comprising:
enabling the NLP engine to extract, from an input comprising a first content including a first assertion, a plurality of knowledge blocks;
configuring a computational module to operate with the NLP engine to compute a metric corresponding to a first knowledge block in the plurality of knowledge blocks, the metric evaluating a corpus of content against the first knowledge block, wherein the computational module causes a behavior of the NLP engine to adjust the metric using a half-life hyperparameter on a consensus detected in the corpus;
further configuring the NLP engine to dynamically determine a contrarian view expressed in a corpus of content by comparing the metric with the first knowledge block and identifying the first assertion as a contrarian assertion, wherein the contrarian assertion is an assertion that has a contrary correlation with the consensus detected in the corpus; and
causing a presentation device to visually associate an indication of the contrarian assertion with a portion of the first content.
8. The computer program product of claim 7 , wherein the stored program instructions are stored in a computer readable storage device in a data processing system, and wherein the stored program instructions are transferred over a network from a remote data processing system.
9. The computer program product of claim 7 , wherein the stored program instructions are stored in a computer readable storage device in a server data processing system, and wherein the stored program instructions are downloaded in response to a request over a network to a remote data processing system for use in a computer readable storage device associated with the remote data processing system, further comprising:
program instructions to meter use of the program instructions associated with the request; and
program instructions to generate an invoice based on the metered use.
10. The computer program product of claim 7 , wherein the first knowledge block comprises an assertion of a direction of an indicator and the metric comprises a ratio of upward assertions of the indicator present in the corpus to total assertions of the indicator present in the corpus.
11. The computer program product of claim 10 , wherein the ratio is weighted by a half-life parameter, the half-life parameter decreasing according to an elapsed time.
12. The computer program product of claim 7 , further comprising:
computing a novelty metric corresponding to the first knowledge block, the novelty metric evaluating the corpus of content against the first knowledge block, wherein the novelty metric comprises a ratio of assertions of the first knowledge block within a first time period to assertions of the first knowledge block within a second time period, the second time period longer than the first time period.
13. The computer program product of claim 7 , further comprising:
adding, to the corpus of content, the first content and the plurality of knowledge blocks.
14. The computer program product of claim 7 , further comprising:
receiving a query comprising a second knowledge block;
evaluating, using the metric, the corpus of content against the second knowledge block;
identifying, using the metric, a second content within the corpus, the second content comprising an assertion responsive to the query; and
causing an indication of the assertion responsive to the query to become visually associated with a portion of the second content on the presentation device.
15. A computer system comprising a processor and one or more computer readable storage media, and program instructions collectively stored on the one or more computer readable storage media, the program instructions executable by the processor to cause the processor to perform operations comprising:
constructing a modified natural language processing (NLP) engine, the constructing comprising:
enabling the NLP engine to extract, from an input comprising a first content including a first assertion, a plurality of knowledge blocks;
configuring a computational module to operate with the NLP engine to compute a metric corresponding to a first knowledge block in the plurality of knowledge blocks, the metric evaluating a corpus of content against the first knowledge block, wherein the computational module causes a behavior of the NLP engine to adjust the metric using a half-life hyperparameter on a consensus detected in the corpus;
further configuring the NLP engine to dynamically determine a contrarian view expressed in a corpus of content by comparing the metric with the first knowledge block and identifying the first assertion as a contrarian assertion, wherein the contrarian assertion is an assertion that has a contrary correlation with the consensus detected in the corpus; and
causing a presentation device to visually associate an indication of the contrarian assertion with a portion of the first content.
16. The computer system of claim 15 , wherein the first knowledge block comprises an assertion of a direction of an indicator and the metric comprises a ratio of upward assertions of the indicator present in the corpus to total assertions of the indicator present in the corpus.
17. The computer system of claim 16 , wherein the ratio is weighted by a half-life parameter, the half-life parameter decreasing according to an elapsed time.
18. The computer system of claim 15 , further comprising:
computing a novelty metric corresponding to the first knowledge block, the novelty metric evaluating the corpus of content against the first knowledge block, wherein the novelty metric comprises a ratio of assertions of the first knowledge block within a first time period to assertions of the first knowledge block within a second time period, the second time period longer than the first time period.
19. The computer system of claim 15 , further comprising:
adding, to the corpus of content, the first content and the plurality of knowledge blocks.
20. The computer system of claim 15 , further comprising:
receiving a query comprising a second knowledge block;
evaluating, using the metric, the corpus of content against the second knowledge block;
identifying, using the metric, a second content within the corpus, the second content comprising an assertion responsive to the query; and
causing an indication of the assertion responsive to the query to become visually associated with a portion of the second content on the presentation device.