Modeling analysis of team behavior and communication
A computer evaluates free-form text messages among members of a team, using natural language processing techniques to process the text messages and to assess psychological state of the team members as reflected it the text messages. The computer assembles the psychological state as reflected in the messages to evaluate team collective psychological state. The computer reports a trend of team collective psychological state in natural language text form.
1. A method, comprising:
receiving, at a processor, text data associated with a first compute device and a second compute device that are from a plurality of compute devices;
generating, via the processor, using a machine learning model, and based on the text data, a state;
generating, via the processor and based on the state, (1) a first node that is (a) associated with the first compute device, (b) from a plurality of nodes associated with the plurality of compute devices, and (c) included in a graph, (2) a second node that is (a) associated with the second compute device, (b) from the plurality of nodes, and (c) included in the graph, and (3) an edge between the first node and the second node and having an edge weight based on the state, the edge being from a plurality of edges having a plurality of edge weights;
determining, via the processor and based on the plurality of edges having the plurality of edge weights, a collective state associated with a user of the first compute device and a user of the second compute device; and
causing, via the processor, transmission of a signal indicating the collective state.
2. The method of claim 1 , wherein the state is a first state, the edge is a first edge, the edge weight is a first edge weight, and the graph is a multiplex graph having (1) a first layer including the first node and the second node and (2) a second layer, the method further comprising:
generating, via the processor, using the machine learning model, and based on the text data, a second state; and
generating, via the processor and based on the second state, (1) a third node associated with the first compute device and included in the second layer of the graph, (2) a fourth node associated with the second compute device and included in the second layer of the graph, and (3) a second edge between the third node and the fourth node and having a second edge weight based on the second state.
3. The method of claim 1 , wherein the text data is included in a text message transmitted from the first compute device to the second compute device.
4. The method of claim 1 , wherein the determining the collective state includes:
generating, via the processor and based on the plurality of edges having the plurality of edge weights, a measure associated with at least one of community detection, community modularity, or graph centrality; and
determining, via the processor, the collective state based on the measure.
5. The method of claim 1 , wherein the machine learning model is a first machine learning model, the method further comprising:
generating, via the processor and using a second machine learning model, an indication of significance associated with the collective state based on an identity associated with the plurality of compute devices.
6. The method of claim 1 , further comprising generating, via the processor and using a recommendation algorithm, an indication of a recommended intervention based on at least one of the state or the collective state.
7. The method of claim 6 , further comprising:
storing, via the processor and at a memory, an indication of an implemented intervention and an indication of an effect associated with the implemented intervention; and
modifying, via the processor and based on the indication of the implemented intervention, at least one weight included in the recommendation algorithm to cause the recommendation algorithm to generate an indication of a modified recommended intervention.
8. The method of claim 1 , further comprising:
training the machine learning model based on at least one of (1) a first linguistic signal associated with a team including the plurality of compute devices, (2) a second linguistic signal not associated with the team, (3) an extralinguistic signal, or (4) a linguistic feature of team communication.
9. The method of claim 1 , wherein:
the machine learning model is a first machine learning model; and
the generating the state further includes generating, via the processor and using a second machine learning model, the state based on extralinguistic data associated with at least one of (1) the user of the first compute device or (2) the user of the second compute device.
10. The method of claim 9 , wherein at least one of (1) a signal generated by the first machine learning model is used to train the second machine learning model or (2) a signal generated by the second machine learning model is used to train the first machine learning model.
11. The method of claim 9 , wherein the extralinguistic data includes at least one of telemetry data, biological measurement data, environmental data, appetite data, exercise data, or sleep data.
12. The method of claim 11 , wherein the extralinguistic data includes the telemetry data, and the telemetry data includes at least one of (1) location data associated with at least one of the user of the first compute device or the user of the second compute device, or (2) camera data depicting the at least one of the user of the first compute device or the user of the second compute device.
13. The method of claim 1 , wherein the machine learning model is a first machine learning model, the method further comprising:
receiving, via the processor, facial recognition data associated with at least one of (1) the user of the first compute device or (2) the user of the second compute device; and
verifying, via the processor, the state based on the facial recognition data.
14. A method, comprising:
receiving, at a processor, data that (1) includes at least one of text data or extralinguistic data and (2) is associated with at least one compute device from a plurality of compute devices;
generating, via the processor, using at least one machine learning model, and based on the data, a state having an attribute and associated with the at least one compute device;
generating, via the processor and based on the state, (1) a plurality of nodes associated with the plurality of compute devices and included in a layer (a) of a graph and (b) associated with the attribute and (2) at least one edge associated with the at least one compute device and having an edge weight based on the state;
determining, via the processor and based on the graph, a collective state for a plurality of users associated with the plurality of compute devices; and
causing, via the processor, transmission of a signal indicating the collective state.
15. The method of claim 14 , wherein:
the layer is from a plurality of layers included in the graph;
the attribute is from a plurality of attributes; and
each attribute from the plurality of attributes is associated with a respective layer from the plurality of layers.
16. The method of claim 14 , wherein the collective state includes a measure of fractionation for a plurality of users associated with the plurality of compute devices.
17. The method of claim 14 , wherein the collective state includes a measure of graph connectedness and indicates an intrateam communication metric associated with the plurality of compute devices.
18. The method of claim 14 , wherein the collective state indicates a collective allostatic load.