Polarity semantics engine analytics platform
Embodiments of the systems and methods disclosed herein provide a prescriptive analytics platform, a polarity analysis engine, and a semantic analysis engine in which a user can identify a target objective and use the system to find out whether the user's objectives are being met, what predictive factors are positively or negatively affecting the targeted objectives, as well as what recommended changes the user can make to better meet the objectives. The systems and methods may include a polarity analysis engine configured to determine the polarity of terms in free-text input in view of the target objective and the predictive factors and use the polarity to generate the recommended changes. The systems and methods may also include a semantic analysis engine to extend the results of the polarity analysis engine for improved determination of predictive factors and improved recommendations.
1. A system comprising:
one or more electronic databases storing:
a set of response data comprising a structured data set and free text data;
an objective corresponding to the set of response data; and
one or more hardware processors configured to execute computer-executable instructions in order to:
access a correlated structured data set based at least in part on the structured data set and key predictive factors that are correlated to the objective;
apply a predictive model that is based at least in part on the structured data set and the first objective to generate a first electronic graph data dependency structure that represents relationships among at least a portion of variables of the correlated structured data set;
generate a second electronic graph data dependency structure of associations among predictive model inputs and polarity values associated with at least a portion of the free text data, wherein the polarity values indicate that the associated free text data is associated with a degree of impact on one or more outcomes;
generate an extended electronic graph data dependency structure based at least in part on the first and second electronic graph data dependency structures; and
generate a recommendation based at least in part on the objective and the extended electronic graph data dependency structure.
2. The system of claim 1 , wherein the set of response data is based at least in part on an aggregated customer feedback data set.
3. The system of claim 1 , wherein the objective is selected by a user.
4. The system of claim 1 , wherein the key predictive factors that are correlated to the first objective indicate one or more behavior patterns associated with the objective.
5. The system of claim 4 , wherein the predictive model indicates one or more behavior patterns associated with an objective.
6. The system of claim 1 , wherein the relationships among at least a portion of variables of the correlated structured data set are based at least in part on the strength of an association among each of the variables of the correlated structured data set.
7. The system of claim 1 , wherein the one or more hardware processors are further configured to execute computer-executable instructions in order to:
determine associative interpretations or causal interpretations of discovered relationships between each of the variables of the correlated structured data set.
8. The system of claim 2 , wherein the recommendation is based at least in part on the associative or causal interpretations.
9. The system of claim 1 , wherein the one or more hardware processors are further configured to execute computer-executable instructions in order to:
generate a data packet that includes a graphical representation of at least a subset of the polarity values that includes a graphical representation of the extended graph, the data packet configured for display on a remote computing device.
10. The system of claim 1 , wherein the one or more hardware processors are further configured to execute computer-executable instructions in order to:
generate a data packet that includes a graphical representation of at least a subset of the polarity values that includes a graphical representation of whether a term in the at least a subset of the polarity values corresponds to a negative sentiment or a positive sentiment, the data packet configured for display on a remote computing device.
11. The system of claim 1 , wherein the one or more hardware processors are further configured to execute computer-executable instructions in order to:
generate a data packet that includes a graphical representation of at least a subset of the polarity values that includes a graphical representation of the frequency and strength of terms in the subset, the data packet configured for display on a remote computing device.
12. The system of claim 1 , wherein the one or more hardware processors are further configured to execute computer-executable instructions in order to:
generate a data packet that includes a graphical representation of at least a subset of the polarity values that includes a graphical representation of whether a term in the subset corresponds to a negative sentiment or a positive sentiment and the frequency and strength of terms in the subset, the data packet configured for display on a remote computing device.
13. A method comprising:
accessing a correlated structured data set based at least in part on the structured data set and key predictive factors that are correlated to an objective, wherein the objective corresponds to a set of response data comprising a structured data set and free text data;
applying a predictive model that is based at least in part on the structured data set and the first objective to generate a first electronic graph data dependency structure that represents relationships among at least a portion of variables of the correlated structured data set;
generating a second electronic graph data dependency structure of associations among predictive model inputs and polarity values associated with at least a portion of the free text data, wherein the polarity values indicate that the associated free text data is associated with a degree of impact on one or more outcomes;
generating an extended electronic graph data dependency structure based at least in part on the first and second electronic graph data dependency structures; and
generating a recommendation based at least in part on the objective and the extended electronic graph data dependency structure.
14. The method of claim 13 , wherein the set of response data is based at least in part on an aggregated customer feedback data set.
15. The method of claim 13 , wherein the key predictive factors that are correlated to the first objective indicate one or more behavior patterns associated with the objective.
16. The method of claim 13 , wherein the relationships among at least a portion of variables of the correlated structured data set are based at least in part on the strength of an association among each of the variables of the correlated structured data set.
17. Non-transitory computer storage having stored thereon a computer program, the computer program including executable instructions that instruct a computer system to at least:
access a correlated structured data set based at least in part on the structured data set and key predictive factors that are correlated to an objective, wherein the objective corresponds to a set of response data comprising a structured data set and free text data;
apply a predictive model that is based at least in part on the structured data set and the first objective to generate a first electronic graph data dependency structure that represents relationships among at least a portion of variables of the correlated structured data set;
generate a second electronic graph data dependency structure of associations among predictive model inputs and polarity values associated with at least a portion of the free text data, wherein the polarity values indicate that the associated free text data is associated with a degree of impact on one or more outcomes;
generate an extended electronic graph data dependency structure based at least in part on the first and second electronic graph data dependency structures; and
generate a recommendation based at least in part on the objective and the extended electronic graph data dependency structure.
18. The non-transitory computer storage of claim 17 , wherein the set of response data is based at least in part on an aggregated customer feedback data set.
19. The non-transitory computer storage of claim 17 , wherein the key predictive factors that are correlated to the first objective indicate one or more behavior patterns associated with the objective.
20. The non-transitory computer storage of claim 17 , wherein the relationships among at least a portion of variables of the correlated structured data set are based at least in part on the strength of an association among each of the variables of the correlated structured data set.