Loading...

Expertise Retrieval and Ranking

Neshati, Mahmood | 2014

1131 Viewed
  1. Type of Document: Ph.D. Dissertation
  2. Language: Farsi
  3. Document No: 46419 (19)
  4. University: Sharif University of Technology
  5. Department: Computer Engineering
  6. Advisor(s): Beigy, Hamid
  7. Abstract:
  8. This thesis investigates the expertise ranking problem. Recently, the expertise ranking problem has attracted lots of attention in Information Retrieval community. The broad usages of expert ranking algorithms in commercial search engines indicate its importance and usability. Expertise ranking problem is concerned with finding people who are knowledgeable in a given topic. The main research questions in this thesis are related to three important questions related to expert ranking problem. The first question is what the sources of evidences are and how we can infer expertise of a person on a given topic. The second question is concerned with the modeling of information related to each person and finally the last question is how we can integrate the expertise evidences. In this thesis, we first propose a method for integration of social and bibliographic networks. The proposed method is based on relational classification which is able to significantly improve the quality of integration problem. In second part of thesis, the problem of expert group formation is investigated and a framework based on facility location analysis is proposed to model three types of expert group formation problem. In last part of thesis, we investigate the evidence integration problem and propose two approaches to improve the expert ranking quality in bibliographic networks. The first approach is based on the learning to rank framework and based on the hypothesis that co-authors should not get equivalent expertise score. The second approach is proposed to consider the temporal effect of textual evidences in expert ranking.
    In our proposed methods, we use well-known and effective frameworks to solve the expertise ranking problems efficiently and effectively. In order to investigate the effectiveness and applicability of our proposed methods, standard as well as manually generated test collections have been used. The generated test collections are publicly available for other researchers. Apart from designing various experiments and statistical testing, our proposed methods are conceptually compared with related works to show their effectiveness
  9. Keywords:
  10. Facility Location Model ; Expertise Retrieval ; Expertise Ranking ; Network Integration ; Relational Classification ; Expertise Group Formation

 Digital Object List

 Bookmark

...see more