Diabetes-Related Topic Detection in Chinese Health Websites Using Deep Learning

详细信息    查看全文

• 作者：Xinhuan Chen (20)
  Yong Zhang (20)
  Chunxiao Xing (20)
  Xiao Liu (21)
  Hsinchun Chen (21)
  
• 关键词：classification ; topic detection ; diabetes ; Chinese ; deep learning
• 刊名：Lecture Notes in Computer Science
• 出版年：2014
• 出版时间：2014
• 年：2014
• 卷：8549
• 期：1
• 页码：13-24
• 全文大小：837 KB
• 参考文献：1. Monnier, J., Laken, M., Carter, C.L.: Patient and Caregiver Interest in Internet-Based Cancer Services. Cancer Practice聽10(6), 305鈥?10 (2002) CrossRef
  2. Chinese Diabetes Society, http://cdschina.org/news_show.jsp?id=2121.html
  3. Deep Learning Tutorials by LISA lab, http://www.deeplearning.net/tutorial/
  4. Socher, R., Bengio, Y., Manning, C.D.: Deep learning for NLP (without magic).Tutorial Abstracts of ACL. p. 5. Association for Computational Linguistics (2012)
  5. Gouws, S.: Deep unsupervised feature learning for natural language processing. In: Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics, pp. 48鈥?3 (2012)
  6. Lu, Y., Zhang, P., Liu, J., et al.: Health-related hot topic detection in online communities using text clustering. PloS One聽8(2), e56221 (2013)
  7. Weitzman, E.R., Cole, E., Kaci, L., et al.: Social but safe? Quality and safety of diabetes-related online social networks. JAMIA聽18(3), 292鈥?97 (2011)
  8. Shrank, W.H., Choudhry, N.K., Swanton, K., et al.: Variations in structure and content of online social networks for patients with diabetes. Archives of Internal Medicine聽171(17), 1589鈥?591 (2011) CrossRef
  9. Greene, J.A., Choudhry, N.K., Kilabuk, E., et al.: Online social networking by patients with diabetes: a qualitative evaluation of communication with Facebook. Journal of General Internal Medicine聽26(3), 287鈥?92 (2011) CrossRef
  10. Klemm, P., Nolan, M.T.: Internet cancer support groups: legal and ethical issues for nurse researchers. Oncology Nursing Forum聽25(4), 673鈥?76 (1998)
  11. Basch, E.M., Thaler, H.T., Shi, W., et al.: Use of information resources by patients with cancer and their companions. Cancer聽100(11), 2476鈥?483 (2004) CrossRef
  12. Li, N., Wu, D.D.: Using text mining and sentiment analysis for online forums hotspot detection and forecast. Decision Support Systems聽48(2), 354鈥?68 (2010) CrossRef
  13. Lin, Y., Li, W., Chen, K., et al.: A document clustering and ranking system for exploring MEDLINE citations. JAMIA聽14(5), 651鈥?61 (2007)
  14. Kandula, S., Curtis, D., Hill, B., et al.: Use of topic modeling for recommending relevant education material to diabetic patients. In: AMIA, vol.聽2011, p. 674 (2011)
  15. Brody, S., Elhadad, N.: Detecting salient aspects in online reviews of health providers. In: AMIA, vol.聽2010, p. 202 (2010)
  16. Tamilselvan, P., Wang, P.: Failure diagnosis using deep belief learning based health state classification. Reliability Engineering & System Safety聽115, 124鈥?35 (2013) CrossRef
  17. Wang, B., Liu, B., Wang, X., et al.: Deep learning approaches to semantic relevance modeling for chinese question-answer pairs. TALIP聽10(4), 21 (2011) CrossRef
  18. Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Computation聽18(7), 1527鈥?554 (2006) CrossRef
  19. Hinton, G.: A practical guide to training restricted Boltzmann machines. Momentum聽9(1), 926 (2010)
  20. Salakhutdinov, R., Hinton, G.: Semantic hashing. International Journal of Approximate Reasoning聽50(7), 969鈥?78 (2009) CrossRef
  
• 作者单位：Xinhuan Chen (20)
  Yong Zhang (20)
  Chunxiao Xing (20)
  Xiao Liu (21)
  Hsinchun Chen (21)
  
  20. Research Institute of Information Technology, Tsinghua National Laboratory for Information Science and Technology, Department of Computer Science and Technology, Tsinghua University, Beijing, China
  21. MIS Department, University of Arizona, United States
  
• ISSN：1611-3349

文摘

With 98.4 million people diagnosed with diabetes in China, most of the Chinese health websites provide diabetes related news and articles in diabetes subsection for patients. However, most of the articles are uncategorized and without a clear topic or theme, resulting in time consuming information seeking experience. To address this issue, we propose an advanced deep learning approach to detect topics for diabetes related articles from health websites. Our research framework for topic detection on diabetes related articles in Chinese is the first one to incorporate deep learning in topic detection in Chinese. It can identify topics of diabetes articles with high performance and potentially assist health information seeking. To evaluate our framework, experiment is conducted on a test bed of 12,000 articles. The results showed the framework achieved an accuracy of 70% in detecting topics and significantly outperformed the SVM based approach.