Mahsa Forati
Dr. Evangelos Milios
The benefits of knowing the knowledgeable people in different topics is obvious to everybody and finding the solution to this problem was popular even before the advent of computers. Today, the new technologies are able to look through a huge amount of data and compare a big set of candidates to find the ones that fit the best for doing a specific task. This project is mainly devoted to the finding expertise of researchers in the academic area, which could be used in a variety of applications such as, personalized article recommendation systems, automatic paper assignment to the reviewers in a conference and helping in role assignment in big companies.
In this project we are going to propose a framework that let the user to investigate researcher’s expertise and also visualize the network of co-authorship among researchers. This is not a trivial task because we do not have access to the people’s mind to extract their knowledge. Here we are using publications of researchers as documents that are representative of their knowledge and try to extract information about their research area. Most of traditional approaches only consider the explicit overlap between documents and ignore the semantic similarity of them. Using Wikipedia we tried to model documents not only based on their explicit surface similarity, but also using the concepts that appeared in them. A few visualization components using D3 library has been provided, too.
