Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 46761 (19)
- University: Sharif University of Technology
- Department: Computer Engineering
- Advisor(s): Beigy, Hamid
- Abstract:
- Expert retrieval when the number of experts are limited is an open problem. Undoubtedly, becoming an expert in a field is a time consuming and expensive task; thus finding the best candidates is a crucial task. In addition, passage of time and growth of knowledge could change the view of a person towards life and his work, which may lead to the change of his or her field of work. When considering the changes each person makes in his or her life, it becomes obvious that they are not far from the original status. Therefore, recommending all possible options around a person could really help the task of decision making. This research is addressing two similar issues of finding experts, in a shortage of experts and a recommendation system for experts, which helps them explore their options and easily find their interests by simply estimating the rank of each person for a query.
Taking the resume of each person as a starting point, and creating the relativity network for each field, the nearest field for each person could be retrieved so he or she could follow any of them according to his or her need or interest. The result shows estimated values are most likely to be around current fields which was expected. Also change of interest in a field vary over time but it would not exceed from a certain range.
This system has the possibility to work at any scale and could easily be integrated with other systems. Since latent models have been used, motivations for change in fields could be shown by tracing a person’s footsteps - Keywords:
- Information Retrieval ; Topic Modeling ; Experd Retrieval ; Rank Estimation ; Rank Prediction ; Topic Classification
Digital Object List
-
محتواي کتاب
- view
Bookmark