ABSTRACT
At present, more and more methods are used to solve the problem of doctor recommendation in online medical community. LDA topic model, vector space model, AHP method, knowledge map and other methods have shown good characteristics and recommendation effect. However, different recommendation methods often get different results, which often leads to inconsistent recommendation, so there are some deficiencies. This paper introduces information fusion technology to fuse the recommendation results obtained by different recommendation methods, obtains further optimization results, and solves the problem of inconsistent results obtained by different recommendation methods. Based on LDA model and word2vec model, this paper established a doctor recommendation model based on information fusion. In the empirical research, Haodaifu (www.haodf.com) has been selected as the research object. The empirical results show that the doctor recommendation model based on information fusion is better than the separate LDA topic model and word2vec model in accuracy and effectiveness.
- Bobby Swar, Tahir Hameed, and Iris Reychav. 2017. Information overload, psychological ill-being, and behavioral intention to continue online healthcare information search. Computers in Human Behavior 70, (May 2017), 416–425. DOI:https://doi.org/10.1016/j.chb.2016.12.068Google ScholarDigital Library
- Hamid Naderi, Behzad Kiani, Sina Madani, and Kobra Etminani. 2020. Concept based auto-assignment of healthcare questions to domain experts in online Q&A communities. International Journal of Medical Informatics 137: 104108. https://doi.org/10.1016/j.ijmedinf.2020.104108Google ScholarCross Ref
- Pan Youneng, Ni Xiuli. 2020. Recommending Online Medical Experts with Labeled-LDA Model [J]. Data Analysis and Knowledge Discovery, 2020, 4(4): 34-43.)Google Scholar
- Qiuqing Meng and Huixiang Xiong. 2021. Research on doctor recommendation based on online consultation text information. information science 39, 06 (2021), 152–160. DOI:https://doi.org/10.13833/j.issn.1007-7634.2021.06.021Google Scholar
- Zhan Yang, Wei Xu, and Runyu Chen. 2021. A deep learning-based multi-turn conversation modeling for diagnostic Q&A document recommendation. Information Processing & Management 58, 3 (May 2021), 102485. DOI:https://doi.org/10.1016/j.ipm.2020.102485Google ScholarCross Ref
- Yin Zhang, Min Chen, Dijiang Huang, Di Wu, and Yong Li. 2017. iDoctor: Personalized and professionalized medical recommendations based on hybrid matrix factorization. Future Generation Computer Systems 66, (January 2017), 30–35. DOI:https://doi.org/10.1016/j.future.2015.12.001Google ScholarDigital Library
- Yan Ye, Yang Zhao, Jennifer Shang, and Liyi Zhang. 2019. A hybrid IT framework for identifying high-quality physicians using big data analytics. International Journal of Information Management 47, (August 2019), 65–75. DOI:https://doi.org/10.1016/j.ijinfomgt.2019.01.005Google ScholarDigital Library
- Yuan Luo, Xi Chen, and Yaya Sun. 2019. A Fuzzy Linguistic Method for Evaluating Doctors of Online Healthcare Consultation Platform Using BWM and Prospect Theory. IEEE Xplore, 506–510. DOI:https://doi.org/10.1109/IEA.2019.8715035Google Scholar
- Hui Yuan and Weiwei Deng. 2021. Doctor recommendation on healthcare consultation platforms: an integrated framework of knowledge graph and deep learning. Internet Research ahead-of-print, ahead-of-print (June 2021). DOI:https://doi.org/10.1108/intr-07-2020-0379Google Scholar
- W. Wen and H.F. Durrant-Whyte. 1992. Model-based multi-sensor data fusion. IEEE Xplore, 1720–1726 vol.2. DOI:https://doi.org/10.1109/ROBOT.1992.220130Google Scholar
- Aihua Li, Weijia Xu, and Yong Shi. 2020. A New Data Fusion Framework of Business Intelligence and Analytics in Economy, Finance and Management. IEEE Xplore, 940–945. DOI:https://doi.org/10.1109/WIIAT50758.2020.00144Google Scholar
- Liang Zhang, Lingling Zhang, Yibing Chen, and Weili Teng. 2015. Application of data mining method based on information fusion in corporate financial early warning. Chinese Journal of Management Science 23, 10 (2015), 170–176. DOI:https://doi.org/DOI:10.16381/j.cnki.issn1003-207x.2015.10.020Google Scholar
- Shulin Cheng, Bofeng Zhang, Guobing Zou, Mingqing Huang, and Zhu Zhang. 2018. Friend recommendation in social networks based on multi-source information fusion. International Journal of Machine Learning and Cybernetics 10, 5 (February 2018), 1003–1024. DOI:https://doi.org/10.1007/s13042-017-0778-1Google Scholar
- Hamed Jelodar, Yongli Wang, Chi Yuan, Xia Feng, Xiahui Jiang, Yanchao Li, and Liang Zhao. 2018. Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimedia Tools and Applications 78, 11 (November 2018), 15169–15211. DOI:https://doi.org/10.1007/s11042-018-6894-4Google Scholar
- Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arXiv.org. Retrieved from https://arxiv.org/abs/1301.3781Google Scholar
- Han, S., Zhang, Y., Ma, Y., Tu, C., Guo, Z., Liu, Z., & Sun, M. 2016. THUOCL: Tsinghua open Chinese lexicon. Tsinghua University.Google Scholar
Recommendations
A Doctor Recommendation Framework for Online Medical Platforms Using Multi-Source Heterogeneous Data
ICCAI '21: Proceedings of the 2021 7th International Conference on Computing and Artificial IntelligenceThe emergence of the online medical platform provides convenience for patients, but at the same time, how to choose the right doctor among thousands of doctors on the platform has become a problem for patients. Nowadays, most doctor recommendation ...
A Hybrid Multigroup Coclustering Recommendation Framework Based on Information Fusion
Special Section on Visual Understanding with RGB-D SensorsCollaborative Filtering (CF) is one of the most successful algorithms in recommender systems. However, it suffers from data sparsity and scalability problems. Although many clustering techniques have been incorporated to alleviate these two problems, ...
A trust-semantic fusion-based recommendation approach for e-business applications
Collaborative Filtering (CF) is the most popular recommendation technique but still suffers from data sparsity, user and item cold-start problems, resulting in poor recommendation accuracy and reduced coverage. This study incorporates additional ...
Comments