Assessing a treatment service based on a measure of trust dynamics
Techniques regarding autonomously determining an entity's susceptibility towards one or more treatment services are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise an assessment component that can determine a susceptibility disposition value that measures a susceptibility of an entity to a treatment service based on a trust disposition value. The trust disposition value can be determined based on a communication with the entity using machine learning technology.
1 . A system, comprising:
a memory that stores computer executable components;
a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
an assessment component that determines, via a trained machine learning model, a susceptibility disposition value that measures a susceptibility of a patient to a treatment service, wherein the susceptibility disposition value is computed from a trust disposition value, the trust disposition value being derived from features extracted from electronic communications involving commitments between the patient and one or more entities, the commitments comprising debtor, creditor, antecedent, and consequent parameters, and being evaluated as fulfilled or violated to update binary evidence values <r,s>; and
a model component that generates a computer model depicting, as a trust graph, linkages between a plurality of entities associated with the patient and the treatment service, wherein the linkages depict how the patient is indirectly correlated with the treatment service, and wherein the computer model is algorithmically traversable to generate a prediction of the susceptibility disposition value for the patient.
2 . The system of claim 1 , further comprising:
a data collection component that generates a dataset that represents a plurality of features extracted from a communication between the patient and a chatbot using machine learning technology.
3 . The system of claim 2 , further comprising:
an evaluation component that determines a plurality of trust disposition values that characterize trust that the patient has in the plurality of entities based on the communication.
4 . The system of claim 3 , wherein the plurality of trust disposition values are associated with the linkages in the computer model.
5 . The system of claim 2 , wherein the communication regards a commitment regarding an entity from the plurality of entities, and wherein the plurality of features delineates whether the commitment was fulfilled.
6 . The system of claim 1 , further comprising:
a distribution component that generates a recommendation regarding whether to perform the treatment service based on the susceptibility disposition value, and wherein the treatment service regards a chemical effect affecting the patient.
7 . The system of claim 6 , wherein the chemical effect is a chemically induced dependency generated by a chemical compound.
8 . The system of claim 6 , wherein the distribution component sends the recommendation to the patient.
9 . The system of claim 1 , further comprising:
a distribution component that distributes the treatment service to the patient based on a comparison of the susceptibility disposition value to a predefined threshold.
10 . The system of claim 1 , wherein the susceptibility disposition value is determined in a cloud computing environment.
11 . A computer-implemented method, comprising:
determining, by executing a machine learning classifier trained on commitment-based features, a susceptibility disposition value that quantitatively measures a susceptibility of a patient to a treatment service, wherein the susceptibility disposition value is computed from a trust disposition value, the trust disposition value being derived from features extracted from electronic communications involving commitments between the patient and one or more entities, the commitments comprising debtor, creditor, antecedent, and consequent parameters, and being evaluated as fulfilled or violated to update binary evidence values <r,s>; and
generating, by the system, a computer model implemented as a graph data structure stored in memory, the computer model depicting linkages between a plurality of entities associated with the patient and the treatment service, wherein the linkages are weighted by the trust disposition values, and wherein traversing the graph algorithmically facilitates prediction of the susceptibility disposition value.
12 . The computer-implemented method of claim 11 , further comprising:
generating, by the system, a dataset that represents a plurality of features extracted from a communication between the patient and a chatbot using machine learning technology; and
determining, by the system, a plurality of trust disposition values that characterize trust that the patient has in the plurality of entities based on the communication.
13 . The computer-implemented method of claim 11 , further comprising:
generating, by the system, a recommendation regarding whether to perform the treatment service based on the susceptibility disposition value, and wherein the treatment service regards a chemical effect affecting the patient.
14 . The computer-implemented method of claim 11 , further comprising:
distributing, by the system, the treatment service to the patient based on a comparison of the susceptibility disposition value to a predefined threshold value.
15 . The computer-implemented method of claim 14 , wherein the treatment service is a media selected from a group consisting of a text, a video and an audio signal.
16 . A computer program product for assessing a treatment service, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
(a) receive communication data and extract, using natural language processing and feature extraction, parameters of commitments involving the patient, the commitments comprising debtor, creditor, antecedent, and consequent parameters;
(b) update trust evidence <r,s> values based on whether the commitments are fulfilled or violated;
(c) determine a trust disposition value from the updated evidence values using a learned probabilistic model; and
(d) generate a computer model implemented as a trust graph stored in memory, the trust graph comprising linkages between a plurality of entities associated with the patient and the treatment service, wherein the linkages are weighted by the trust disposition values, and wherein the trust graph is algorithmically traversable to compute a susceptibility disposition value for the patient.
17 . The computer program product of claim 16 , wherein the program instructions further cause the processor to:
generate, by the processor, a dataset that represents a plurality of features extracted from a communication between the patient and a chatbot using machine learning technology; and
determine, by the processor, a plurality of trust disposition values that characterize trust that the patient has in the plurality of entities based on the communication.
18 . The computer program product of claim 16 , wherein the program instructions further cause the processor to:
generate, by the processor, a recommendation regarding whether to perform the treatment service based on the susceptibility disposition value, and wherein the treatment service regards a chemical effect affecting the patient.
19 . The computer program product of claim 16 , wherein the program instructions further cause the processor to:
distribute, by the processor, the treatment service to the patient based on a comparison of the susceptibility disposition value to a predefined threshold value.
20 . The computer program product of claim 19 , wherein the treatment service is a media selected from a group consisting of a text, a video and an audio signal.