基于改进语义距离的网络评论聚类研究
作者:
基金项目:

国家自然科学基金(61001178);国家软科学研究计划(2010GXQ5D317);北京市优秀人才计划;北京市属高等学校青年拔尖人才计划(CITTCD201404052);北京市教育委员会科技计划(KM201210005024);北京工业大学基础研究基金;可信计算北京市重点实验室开放课题


Online Comment Clustering Based on an Improved Semantic Distance
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [31]
  • |
  • 相似文献 [20]
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    针对在线评论,提出了一种短文本语义距离计算模型,将文本距离看成是形式距离和单元语义距离的综合.首先,在对变异短文本进行预处理的基础上,以中文词语为单位,利用词典进行语义扩展,计算短文本间最大匹配距离,将其作为衡量短文本间形式距离的指标;其次,基于短文本中的实义单元和非实义单元的不同作用,利用改进的编辑距离算法计算短文本的单元语义距离;最后,利用加权的方法将形式距离和单元语义距离综合为文本距离,并将其应用于网络在线评论的聚类分析.特别地,为了缓解短文本长度差异所造成的计算误差,提出利用词表长度对距离进行惩罚,并根据Zipf's Law和Heap's Law的对应关系,给出了一种文本词表长度的估计方法,并阐明了文本Zipf指数a对长度惩罚的关键性作用机制.实验结果表明,改进算法优于传统方法,聚类性能显著提升.

    Abstract:

    An improved semantic distance for short text is proposed. The new method calculates the semantic distance between two word strings as balance of the extent of word sequence alignment and the meaning matching between word strings. First, after linguistic preprocessing, the extent of word sequence alignment is computed by the structural distance which measures the maximum matching based on the HIT-CIR Tongyici Cilin (extended edition). Then the meaning matching between word strings is computed by an improved edit distance which allocates each word a weight according to its word type. Finally, the semantic distance between the word strings is measured as a balance of structural distance and word meaning matching distance. In addition, in order to eliminate the influence of the sentence length, the proposed semantic distance is adjusted using the distinct word count estimated by the Heap's law and Zipf law. Experimental results show that the presented methods are more efficient than the classical edit distance models.

    参考文献
    [1] Yang F, Peng QK, Xu T. Sentiment classification for online comments based on random network theory. Acta Automatica Sinica, 2010,36(6):837-844 (in Chinese with English abstract). [doi: 10.3724/SP.J.1004.2010.00837]
    [2] Balog K, Mishne G, de Rijke M. Why are they excited? Identifying and explaining spikes in blog mood levels. In: Proc. of the ECACL 2006. 2006. 207-210.
    [3] Turney PD, Littman ML. Measuring praise and criticism: Inference of semantic orientation from association. ACM Trans. on Information Systems, 2003,21(4):315-346.
    [4] Kyosuke N, Takahide H, Ko F. Improving tweet stream classification by detecting changes in word probability. In: Proc. of the ACM SIGIR 2012. 2012. 971-980. [doi: 10.1145/2348283.2348412]
    [5] Fan XH, Wang P. Chinese short text classification in two steps. Journal of Dalian Maritime University, 2008,34(3):121-124 (in Chinese with English abstract).
    [6] Yang Z, Lai YX, Duan LJ, Li YJ. Short text sentiment classification based on context reconstruction. Acta Automatica Sinica, 2012, 38(1):55-67 (in Chinese with English abstract). [doi: 10.3724/SP.J.1004.2012.00055]
    [7] Sriram B, Fuhry D, Demir E, Ferhatosmanoglu H, Demirbas M. Short text classification in twitter to improve information filtering. In: Proc. of the ACM SIGIR 2010. 2010. 841-842. [doi: 10.1145/1835449.1835643]
    [8] Mihalcea R, Courtney C, Strapparava C. Corpus-Based and knowledge-based measures of text semantic similarity. In: Proc. of the AAAI 2006. 2006. 775-780.
    [9] Pu Q, Yang GW. Short-Text classification based on ICA and LSA. In: Proc. of the ISNN 2006. LNCS 3972, Heidelberg: Springer- Verlag, 2006. 265-270. [doi: 10.1007/11760023_39]
    [10] Yang Z, Fan KF, Lei JJ, Guo J. Text manifold based on semantic analysis. Acta Electronica Sinica, 2009,37(3):557-561 (in Chinese with English abstract). [doi: 10.3321/j.issn:0372-2112.2009.03.024]
    [11] Liu YP, Li S, Zhao TJ. System combination based on wsd using WordNet. Acta Automatica Sinica, 2010,36(11):1575-1580 (in Chinese with English abstract). [doi: 10.3724/SP.J.1004.2010.01575]
    [12] Li B, Liu T, Qin B, Li S. Chinese sentence similarity computing based on semantic dependency relationship analysis. Application Research of Computers, 2003,20(12):15-17 (in Chinese with English abstract). [doi: 10.3969/j.issn.1001-3695.2003.12.005]
    [13] Peng J, Yang DQ, Tang SW, Fu Y, Jiang HK. A novel text clustering algorithm based on inner product space model of semantic. Chinese Journal of Computers, 2007,30(8):1354-1363 (in Chinese with English abstract). [doi: 10.3321/j.issn:0254-4164.2007.08. 017]
    [14] Li SJ. Research of relevancy between sentences based on semantic computation. Computer Engineering and Applications, 2002, 38(7):75-76 (in Chinese with English abstract). [doi: 10.3321/j.issn:1002-8331.2002.07.025]
    [15] Ristud ES, Yianilos PN. Learning string-edit distance. IEEE Trans. on Pattern Analysis and Machine Intelligence, 1998,20(5): 522-532. [doi: 10.1109/34.682181]
    [16] Sui ZF, Yu SW. The skeletal-dependency-tree-based computational model for the sentence similarity. In: Proc. of the Conf. of Chinese Information Processing. 1998. 458-465 (in Chinese with English abstract).
    [17] Chatterjee N. A statistical approach for similarity measurement between sentences for EBMT. In: Proc. of Symp. on Translation Support Systems. 2001.
    [18] Che WX, Li ZH, Liu T. LTP: A Chinese language technology platform. In: Proc. of the Coling 2010. 2010. 13-16.
    [19] Mei JJ, Zhu YM, Gao YQ, Yin HX. TongYiCi CiLin. 2nd ed., Shanghai: Shanghai Lexicographic Publishing House, 1996 (in Chinese).
    [20] Li YJ, Liu B. A normalized levenshtein distance metric. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2007,29(6): 1091-1095. [doi: 10.1109/TPAMI.2007.1078]
    [21] Heaps HS. Information Retrieval: Computational and Theoretical Aspects. Academic Press, 1978.
    [22] Zipf GK. Human Behavior and the Principle of Least Effort. Oxford: Addison-Wesley Press, 1949.
    [23] Lü LY, Zhang ZK, Zhou T. Zipf's law leads to heaps' law: Analyzing their relation in finite-size systems, Plot Ones, 2010,5(12):1-11.
    [24] Ma X, Xu WR, Guo J, Hu RL. SMS-2008: An annotated Chinese short messages corpus. Journal of Chinese Information Processing, 2009,23(4):22-26 (in Chinese with English abstract). [doi: 10.3969/j.issn.1003-0077.2009.04.004]
    [25] Frey BJ, Dueck D. Clustering by passing messages between data points. Science, 2007,315(5814):972-976. [doi: 10.1126/science. 1136800]
    [26] Zhao Y, Karypis G. Empirical and theoretical comparisons of selected criterion functions for document clustering. Machine Learning, 2004,55(3):311-331. [doi: 10.1023/B:MACH.0000027785.44527.d6]
    [27] Papapetrou O, Siberski W, Fuhr N. Decentralized probabilistic text clustering. IEEE Trans. on Knowledge and Data Engineering, 2012,24(10):1848-1861. [doi: 10.1109/TKDE.2011.120]
    [28] Damerau FJ. A technique for computer detection and correction of spelling errors. Communications of the ACM, 1964,7(3): 171-176. [doi: 10.1145/363958.363994]
    [29] Schauerte B, Fink GA. Focusing computational visual attention in multi-modal human-robot interaction, In: Proc. of the Int'l Conf. on Multimodal Interfaces and the Workshop on Machine Learning for Multimodal Interaction. 2010. [doi: 10.1145/ 1891903.1891912]
    [30] Perlibakas V. Distance measures for PCA-based face recognition. Pattern Recognition Letters, 2004,25(6):711-724. [doi: 10.1016/j. patrec.2004.01.011]
    [31] Beitzel SM, Jensen EC, Chowdhury A, Grossman D, Frieder O. Hourly analysis of a very large topically categorized Web query log. In: Proc. of the ACM SIGIR 2004. 2004. 321-328. [doi: 10.1145/1008992.1009048]
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

杨震,王来涛,赖英旭.基于改进语义距离的网络评论聚类研究.软件学报,2014,25(12):2777-2789

复制
分享
文章指标
  • 点击次数:6583
  • 下载次数: 8377
  • HTML阅读次数: 2898
  • 引用次数: 0
历史
  • 收稿日期:2014-05-05
  • 最后修改日期:2014-08-21
  • 在线发布日期: 2014-12-04
文章二维码
您是第20542574位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京市海淀区中关村南四街4号,邮政编码:100190
电话:010-62562563 传真:010-62562533 Email:jos@iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号