Community profiling for social media
View Patent ↗Embodiments of the invention relate to modeling communities associated with groups of data items. Tools are provided to iteratively assign data items to communities and to update topic and participant distribution in the assigned communities. As the distributions are updated, the characteristics of the communities are updated. Each activity area is defined from the perspective of a single user. Participants in a community are connected to a user, but not necessarily to each other. The combination of formations of communities and the statistical aspect of evaluating characteristics of the communities provides a multi-facetted organization of connections between data items and associated participants.
1. A computer program product for use with electronic communication data, the computer program product comprising:
a computer readable non-transitory storage medium having computer readable program code embodied therewith, which when executed causes a computer to:
initialize a plurality of communities, each community being a defined grouping of interconnected participants and having an activeness, at least one topic, and at least two participants;
iteratively assign each received communication item into one of the communities;
in response to the assignment of the received communication item, update a statistical distribution of topics and a statistical distribution of participants in each of the communities, wherein the updating reflects the activeness;
iteratively update a topic assignment for each word from the assigned communication; and
profile each of the communities based on the updated statistical distribution of topics and participants.
2. The computer program product of claim 1 , further comprising computer readable program code configured to calculate a maximum likelihood of membership of a select communication with a select community, wherein the calculation is based on a select topic word and participant distribution for the community.
3. The computer program product of claim 2 , further comprising computer readable program code configured to assign the select communication to the select community responsive to the calculated maximum likelihood meeting a threshold value.
4. The computer program product of claim 2 , further comprising computer readable program code configured to calculate the maximized likelihood based on a current topic of the communication being assigned and distribution of participants in the communities.
5. The computer program product of claim 1 , further comprising computer readable program code configured to remove a previously assigned communication from one of the communities and to update the community subject to the removal.
6. The computer program product of claim 5 , further comprising computer readable program code configured to update a community profile for the community subject to the communication removal, and code to recalculate both a topic and distribution of the participants for the subject community.
7. The computer program product of claim 1 , further comprising computer readable program code configured to remove a word from a community, including removal of topic statistics of the community from which the word has been removed.
8. The computer program product of claim 7 , further comprising computer readable program code configured to update a word topic assignment for the community subject to the word removal.
9. A system comprising:
a shared pool of configurable resources, the shared pool including a physical host in communication with a plurality of physical machines, the physical host having a processing unit in communication with a memory module and data storage;
a functional unit local to the memory module and in communication with the processor, the functional unit having tools to support organization of data items, the tools comprising:
an initialization manager to initialize a plurality of communities, each community being a defined grouping of interconnected participants and having an activeness, at least one topic, and at least two participants;
an assignment manager in communication with the initialization manager, the assignment manager to iteratively assign each received data item into one of the initialized communities;
an update manager in communication with the assignment manager, the update manager to update a statistical distribution in each of the communities and respond to the assignment of the received data item, including a statistical distribution of topics and a statistical distribution of participants in each of the communities, a topic assignment for each word from the assigned data items in response to the assignment of the received data item, wherein the updating reflects the activeness; and
a profile manager in communication with the update manager, the profile manager to profile each of the communities based on the updated statistical distribution of topics and participants.
10. The system of claim 9 , further comprising a calculation manager in communication with the profile manager, the calculation manager to calculate a maximum likelihood of membership of a select communication with a select community, the calculation manager to base the calculation on a select topic word and participant distribution for the community.
11. The system of claim 10 , further comprising the assignment manager to assign the select communication to the select community responsive to the calculated maximum likelihood meeting a threshold value.
12. The system of claim 10 , further comprising the calculation manager to calculate the maximized likelihood based on a current topic of the communication being assigned and distribution of participants in the community.
13. The system of claim 9 , further comprising the assignment manager to remove a previously assigned communication from one of the communities and update the community subject to the removal.
14. The system of claim 13 , further comprising the update manager to update a community profile for the community, subject to removal of the assigned communication, and recalculate a topic and distribution of participants for the subject community.
15. The system of claim 9 , further comprising the assignment manager to remove a word from a community, and the update manager to remove topic statistics of the community from which the word has been removed.
16. The system of claim 15 , further comprising the update manager to update a word topic assignment for the community subject to the word removal.