A Tibetan and Uygur Sensitive Word Tracking System

  • Xiaodong Yan
  • Xiaobing Zhao
  • Guosheng Yang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 219)


“Sensitive words” are the terms, certain words, and other bad words which are restricted to be used by the state or institutions. Here, we built a Tibetan and Uygur sensitive word tracking system, in it we first built a sensitive word vocabulary and classified the sensitive words. Then in order to track Tibetan and Uygur sensitive word effectively, we tried to search sensitive word on Web based on the sensitive word vocabulary. According to the search results, we have found the high focused sensitive words on Web, so these words are those we will track next. In our track system, we adopted a new link analysis algorithm to track high usage frequency Tibetan, Uygur sensitive word. From the experiments, we can see that it has effective performance.


Sensitive words Classify Topic tracking 


  1. 1.
    Liu G, Fang Y, Liu J (2009) Sensitive word-stock designing based on correlative word and extension rule. J Sichuan Univ (Natural Science Edition) 03:667–671Google Scholar
  2. 2.
    Lian W, Cheung DW (2004) An efficient and scalable algorithm for clustering XML documents by structure. IEEE Tram Knowl Data Eng 16(1):82–84CrossRefGoogle Scholar
  3. 3.
    Song D, Lin H, Yang Z (2006) A web news tracking algorithm with hyperlink analysis. In: The 3rd academic computational linguistics seminar, vol 11. Shenyang, China, pp 321–326Google Scholar
  4. 4.
    Feng Y (2009) Research on building public opinion sensitive topics on network searching system, vol 05. Master’s Thesis, Beijing Jiaotong University, pp 45–49Google Scholar
  5. 5.
    Huan X (2007) Research on monitoring and blocking network information, vol 04. Master’s Thesis, Beijing Jiaotong University, pp 11–17Google Scholar
  6. 6.
    Zhu W (2008) Automated blog text extraction of sensitive information, vol 08. Master’s Thesis, Shanghai Jiaotong University, pp 79–88Google Scholar
  7. 7.
    Sahon G (1989) Automatic text processing: the trans formation, analysis, and retrieval of information by computer, vol 41. Addition Wesley, Boston, pp 256–264Google Scholar
  8. 8.
    Jin Z, Lin H (2005) Research on topic tracking and tendentious classification based on hownet. J China Soc Sci Tech Inf 24(5):555–561Google Scholar

Copyright information

© Springer-Verlag London 2013

Authors and Affiliations

  1. 1.Minzu University of ChinaBeijingChina

Personalised recommendations