Collaboration synchronization
Synchronizing collaboration times for members of a team includes extracting emotive content and topical indicia from conversation data generated from multiple electronically captured conversations involving the team members. A model for generating time-based collaboration profiles for each member with respect to a specific topic can be constructed based on the emotive content and topical indicia. A synchronized collaboration time for the members of the team can be determined based on comparisons of each team member's respective collaboration profile.
1. A method, comprising:
extracting, using computer hardware, emotive content and topical indicia from conversation data generated by a plurality of electronically captured conversations involving a plurality of users;
constructing for each of the plurality of users, using computer hardware, a model based on the emotive content and topical indicia, each model generating a time-based collaboration profile for a corresponding user with respect to at least one topic; and
determining, using computer hardware, a synchronized collaboration time for the plurality of users based on a comparison of the collaboration profiles.
2. The method of claim 1 , wherein the determining comprises determining a time that a majority of the plurality of users is classified, based on the users' respective collaboration profiles, as positively emotive.
3. The method of claim 1 , wherein the determining comprises determining a time based on collaboration profiles that provide ordinal rankings, the time corresponding to a time that the sum of the users' ordinal rankings is greatest.
4. The method of claim 1 , wherein the extracting emotive content and topical indicia comprises identifying emotive content using natural language processing of users' contributions to the electronically captured conversations, and extracting topical indicia comprises at least one of modelling the conversation data using latent Dirichlet allocation and modelling word-word co-occurrences in the conversation data.
5. The method of claim 1 , further comprising incorporating at least one of the plurality of user models for generating a time-based collaboration profile into a collaboration tool.
6. The method of claim 5 , further comprising determining whether to stop an on-going collaboration workflow using the collaboration tool and, responsive to the collaboration workflow stopping, recommending a time to initiate a new collaboration workflow.
7. The method of claim 6 , further comprising generating a bot configured to recommend a time for at least one of initiating a collaborative workflow and stopping a collaborative workflow.
8. A system, comprising:
a processor programmed to initiate executable operations including:
extracting emotive content and topical indicia from conversation data generated by a plurality of electronically captured conversations involving a plurality of users;
constructing for each of the plurality of users a model based on the emotive content and topical indicia, each model generating a time-based collaboration profile for a corresponding user with respect to at least one topic; and
determining a synchronized collaboration time for the plurality of users based on a comparison of the collaboration profiles.
9. The system of claim 8 , wherein the determining comprises determining a time that a majority of the plurality of users is classified, based on the users' respective collaboration profiles, as positively emotive.
10. The system of claim 8 , wherein the determining comprises determining a time based on collaboration profiles that provide ordinal rankings, the time corresponding to a time that the sum of the users' ordinal rankings is greatest.
11. The system of claim 8 , wherein the extracting emotive content and topical indicia comprises identifying emotive content using natural language processing of users' contributions to the electronically captured conversations, and extracting topical indicia comprises at least one of modelling the conversation data using latent Dirichlet allocation and modelling word-word co-occurrences in the conversation data.
12. The system of claim 8 , further comprising incorporating at least one of the plurality of user models for generating a time-based collaboration profile into a collaboration tool.
13. The system of claim 12 , further comprising determining whether to stop an on-going collaboration workflow using the collaboration tool and, responsive to the collaboration workflow stopping, recommending a time to initiate a new collaboration workflow.
14. A computer program product, comprising:
a computer readable storage medium having program code stored thereon, the program code executable by a data processing system to initiate operations including:
extracting emotive content and topical indicia from conversation data generated by a plurality of electronically captured conversations involving a plurality of users;
constructing for each of the plurality of users a model based on the emotive content and topical indicia, each model generating a time-based collaboration profile for a corresponding user with respect to at least one topic; and
determining a synchronized collaboration time for the plurality of users based on a comparison of the collaboration profiles.
15. The computer program product of claim 14 , wherein the determining comprises determining a time that a majority of the plurality of users is classified, based on the users' respective collaboration profiles, as positively emotive.
16. The computer program product of claim 14 , wherein the determining comprises determining a time based on collaboration profiles that provide ordinal rankings, the time corresponding to a time that the sum of the users' ordinal rankings is greatest.
17. The computer program product of claim 14 , wherein the extracting emotive content and topical indicia comprises identifying emotive content using natural language processing of users' contributions to the electronically captured conversations, and extracting topical indicia comprises at least one of modelling the conversation data using latent Dirichlet allocation and modelling word-word co-occurrences in the conversation data.
18. The computer program product of claim 14 , further comprising incorporating at least one of the plurality of user models for generating a time-based collaboration profile into a collaboration tool.
19. The computer program product of claim 18 , further comprising determining whether to stop an on-going collaboration workflow using the collaboration tool and, responsive to the collaboration workflow stopping, recommending a time to initiate a new collaboration workflow.
20. The computer program product of claim 19 , further comprising generating a bot configured to recommend a time for at least one of initiating a collaborative workflow and stopping a collaborative workflow.