We have extracted 500 pieces on sport of documents from the net(http:// sports.163. com) as training and testing documents. The experiment result has shown that the system takes about 4 seconds to complete the classification of a 10k length with system classification number 5, and the accuracy of the classification attains 81% (on the environment of P4 2.8G Hz. 256M windows XP).
6. Conclusions
This text has introduced a new branch of data mining —Web text mining. It has mainly discussed some key algorithms about text classification. The whole process is based on parameters and configurations of management control, to provide graphics interface edit or the guide operation. Due to its excellent result of the collection, it can be used to create knowledge database, and it can also be treated as a small scaled vertical search system. The system will provide the exact information to the final consumer. It turns extensive information from non-preface to a preface in the process of classification during the process so that the system is very adaptable and convenient to make the information more generally and easily used by the consumers, and it can provide different personalized services according to different consumers’ requirements. It is different from search engine and intelligence technique. The Web mining classification technique is fully used in the system to do extraction and classification, to pick up valid data for process from the web page, to get needed information that usually is the majority of the data. This is a popular direction of new generation network application. However, we have to admit that the system still have some drawbacks, such as the backup of the data as well as the derivative and the maintenance of the data. In addition, there are some specific requirements for customers who should be professional and familiar with the html language to operating and maintaining the system.
7. References
[1] Jingfeng Zhang, Ming Zhen, Yan Wu, the Script
Language and Dynamic Web Page Designing, China
Water Power Press (2004) (in Chinese)
[2] Zhili Zhou, Renwu Wang, A Study of Web Data
Automation Extraction and its Application, E-COMMERCE, 4(2006 ) 58-63 (in Chinese)
[3] P.Mitra, C.A. Murthy, and S. K. Pal.Unsupervised feature
selection using feature similarity [J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 24(3)( 2002) 301-312
[4] Weiha Feng, Zhangfeng Mao. The Research of Web
Pages Information Extraction Based on Web, Journal of Luoyang Technology College,3( 2005)30-31 (in Chinese)
[5] Jicheng Wang. Research on Web text mining[J
].Computer research and development, 37(5)( 2000 )513 - 520
[6] Shentao Li, Design and Realization of Focused Web
Crawler, Chinese Academy of Sciences, 1-3(2002) (in Chinese)
[7] Wei Li, Jianyi Liu, Huacan He, Cong Wang, Research
and Realization of Intelligent Focused Web Crawler, Application research of Computers, 2(2006)163-166 (in Chinese)
[8] Lihui Wu, Bin Wang, Gang Zhang, A Customized Web
Crawling Model, Computer engineering, 22(2005)86-88 (in Chinese)
[9] Magdalini Eirinaki ,Michalis Vazirgiannis Web Mining
for Web Personalization. ACM Transaction on Internet Technology ,Vol.3,No.1, 2(2003)1-27
[10] Zhenlong Li.Study of Improving Strategy and
echnological Analysis for Information Searching. Computer science 33(2006) 181-184
[11] Jun Chen,Yan Tang. Web Recommendation Model
Based on Web Social Network. Computer science 33(2006) 185-187
[12] Feldman R ,Dagan I. Knowledge discovery in textual
databases (KDT) [C] . In :Proc of the 1st Int’l Conf on Knowledge Discovery.Montreal ,(1995)112 - 117
[13] Wuthrich B ,Permunetilleke D ,Leung S et al . Daily
prediction of majorstock indices from textual WWW data [C] . In :Proc of the 4th Int’l Conf on Knowledge Discovery. New York ,(1998)
[14] Koller D ,Sahami M. Hierarchically classifying
documents using very few words[J ] . ICML97 ,(1997) 170 - 178.
[15] Teng Lv and Ping Yan. XML Constraint-tree-based
functional dependencies. Proc. of 2006 IEEE International Conference on e-Business Engineering (ICEBE2006), IEEE Computer Society Press, (2006) 224-228.
criteriahavebeenimplementedsinceDecember1st.2011.’...classificationofdiabetes fordiagnosisandmelfitusinthen...algorithm[外文期刊] 2005 6.Agarwal MM;Dhatt GS;...
Specifying and implement... 暂无评价 13页 免费 Modeling the Visual Cort.....Responsibilities Shlaer - Mellor Object lifecycles Odell Classification -24- ...
themodelofthree.weightneuraInetworkand i忸implementtext biomimeticpatternaBPR ...researchpurposeofthree-weightneuralnetworkaBPRtextclassifier,whosetextclassification...
- Quickly analyze requirements and gaps - Efficiently implement the R/3 System...Classification LO170 Quality Management Inspection Catalogs broken deformed fault...
thetheseThirdIevelThedesignandimplement(P1)Cost(P2...(OF2)Thecoston hisresearchteamintroducedthecost...themostpopularqualityclassification:preventioncost,...
– at each CLK tick (system heart beat) 6 TI Training Material Thread Classification HWI Hardware Interrupts Used to implement 'urgent' part of real-...
The encryption algorithm RC4 for Windows95, What...the following, respectively, simple classification. ...SSL3.0 to implement an electronic certificate (...
State Machine Classification There are two types of state machines as ...The easiest method to understand and implement is the two-always block ...
This paper presents a preprocessing classification algorithm that is based on...dispersive and heterogenous raw data is how to implement data preprocessing....
such as narration, description, comparison, classification and process analysis...draws on the relevant physiological mechanisms to implement the plan in the ...
热门文档