Conversation slipstream propagation

A system, comprising:

• a processor configured to initiate operations including:
• constructing, using machine learning, a conversations graph representing conversations conducted over an electronic communications network by a plurality of participants and collected from at least one messaging platform;
• generating a conversation slipstream comprising at least one communication extracted from the conversations in response to receiving a secondary communication over the electronic communications network, the at least one communication represented by a sub-graph of the conversations graph that corresponds to a graph of the secondary communication, wherein the generating the conversation slip stream comprises selecting sub-graphs of the conversations graph and comparing each sub-graph selected to the graph of the secondary communication and determining a predefined similarity based on the comparing, the selecting the sub-graphs of the conversation comprising determining a resolution of a nodal path in each sub-graph, the resolution being a classification indicating whether the conversation is complete, incomplete or evolving;
• and
• presenting the conversation slipstream to at least one participant to the secondary communication.

A computer program product, the computer program product comprising:

• one or more non-transitory computer-readable storage media and program instructions collectively stored on the one or more non-transitory computer-readable storage media, the program instructions executable by a processor to cause the processor to initiate operations including:
• constructing, using machine learning, a conversations graph representing conversations conducted over an electronic communications network by a plurality of participants and collected from at least one messaging platform;
• generating a conversation slipstream comprising at least one communication extracted from the conversations in response to receiving a secondary communication over the electronic communications network, the at least one communication represented by a sub-graph of the conversations graph that corresponds to a graph of the secondary communication, wherein the generating the conversation slip stream comprises selecting sub-graphs of the conversations graph and comparing each sub-graph selected to the graph of the secondary communication and determining a predefined similarity based on the comparing, the selecting the sub-graphs of the conversation comprising determining a resolution of a nodal path in each sub-graph, the resolution being a classification indicating whether the conversation is complete, incomplete or evolving;
• and
• presenting the conversation slipstream to at least one participant to the secondary communication.