Research and Implementation of Discovering and Recommending Experts in Medical Community-Based Q&A
- DOI
- 10.2991/bep-16.2017.35How to use a DOI?
- Keywords
- health;experts-recommendation;relationship matrix
- Abstract
With the continuous development of the Internet, community-based Q&A (CQA) system has become an effective platform for people to access online information and help. People can submit their own question in CQA and get answers from others. There will be an enormous amount of questions all the time, and new questions which put forward by users are very easy to be buried. Even though there is no new question raising in a short time, the difficult questions will also be buried, because there are no enough users with professional approach to discover and answer the questions in time. To solve such problems, the technology of recommending experts emerged. We propose an optimized LDA recommendation model which combined with medical features in this thesis, by means of the recommendation technology, we can get around 3~4 potential topics of each experts interested in and the corresponding probabilities with the improved topics model. Thus we can obtain a relationship matrix. Then we can get a scores ranking according to the customized scoring approach of experts, and recommend. The experimental results show that, compared to the conventional recommendation algorithm, the results and accuracy of the recommendation algorithm proposed in this thesis has improved.
- Copyright
- © 2017, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Lan FANG AU - Yu FANG PY - 2016/12 DA - 2016/12 TI - Research and Implementation of Discovering and Recommending Experts in Medical Community-Based Q&A BT - Proceedings of the 2016 International Conference on Biological Engineering and Pharmacy (BEP 2016) PB - Atlantis Press SP - 169 EP - 172 SN - 2468-5747 UR - https://doi.org/10.2991/bep-16.2017.35 DO - 10.2991/bep-16.2017.35 ID - FANG2016/12 ER -