Cognitive ranking of terms used during a conversation

A computer program product comprising a non-transitory computer readable medium having a computer readable program stored therein, wherein the computer readable program, when executed on a computing device, configures the computing device to implement a conversation monitoring system that operates to:

• monitor a conversation between at least two participants;
• extract key terms present in communications between the at least two participants;
• generate a provenance graph data structure based on the extraction of the key terms, wherein the provenance graph data structure comprises speaker nodes representing the at least two participants, term nodes representing the key terms present in the communications, and edges connecting nodes in the provenance graph;
• analyze the provenance graph data structure to identify a relative ranking of the key terms within the conversation;
• generate an output representing content of the conversation based on the relative ranking of the key terms;
• and
• perform a cognitive operation on at least one communication in the conversation based on the relative ranking of key terms, wherein the output comprises a result of the performance of the cognitive operation by the cognitive system, and wherein the cognitive operation comprises analyzing a plurality of provenance graph data structures to identify terms that are emerging terms and terms that are stable terms using a term frequency-inverse document frequency metric for terms associated with term nodes in the provenance graph data structures.