HP INCFollow

Abstract

People within large originations have difficulty finding individuals or groups who have expertise

or products for any specific domain. This is largely due to the difficulty of tracking what each

individual or group is working on in a dynamic environment. The proposed solution is to create a

Search Engine which can query individuals based off their domain expertise. The proposed

solution uses the 􀜦􀝋􀜿2􀜸􀝁􀜿􁈾􀬷􁈿 model to produce topic vectors for every email or other textual

communication by employees. The communication topic vectors provide spatial correlated topics

where similar topics will be found close together, and dissimilar topics will be found far apart from

each other. Converting textual communication into spatial related topic vectors allows for the use

of well proven and robust correlation models such as K Nearest Neighbors (K‐NN) to find

appropriate similarities.

Creative Commons License

Creative Commons License
This work is licensed under a Creative Commons Attribution-Share Alike 4.0 License.

Download

Share

COinS