Dissertation > Excellent graduate degree dissertation topics show

Web-based social network search method to judge the identity of names

Author: PangYongJie
Tutor: ZhangXiaoFang
School: Huazhong University of Science and Technology
Course: Computer Software and Theory
Keywords: Social Network Vector space model Determine identity Hierarchical clustering
CLC: TP393.09
Type: Master's thesis
Year: 2011
Downloads: 29
Quote: 0
Read: Download Dissertation

Abstract


As computer science and Internet technology continues to progress, people with each other through a variety of software and methods for online interactions, no longer limited by time and geographical constraints. As people's behavior on the Internet increasingly rich Internet social behavior and relationships gradually approaching the traditional objective world of social networks, and between people can truly reflect the true relationship in the objective world. From the Internet by searching for a way to build a real objective world of social networks. Social network search technology and its methods gradually become a research hotspot, the wealth of information the Internet mostly included in the Web, you can get from the Web on an individual's social network information, but more than one person will have a same name, then how identity for each Web for names judge called social web search of key technologies. In order to accurately search for social network, determine the identity of the technical realization names. Introduced in the field of information retrieval vector space model. In order to accurately extracted from the text feature and reduce the vector dimension is given based on a C? Value and word frequency eigenvectors IDF weight calculation method. Implemented based on cosine similarity calculation algorithm angle; through the text clustering algorithm hierarchical clustering algorithm and classification clustering algorithm gives an improved hierarchical clustering algorithm to achieve names identity judgments; to clustering algorithm to improve the convergence rate, give a cluster center is calculated. In order to achieve social web search, the design of a Web-based framework for the social web search system. In order to obtain the information contained social network Web documents, give a Web Downloader implementations; ICTCLAS-API completed through the use of the Web of the Chinese word processing; under C? Value and word frequency IDF weight calculation lexical items, and according to Feature selection criteria Select features lexical items as vectors; through the use of clustering algorithm for Web document classification complete names identity judgments; gives the relationship between the characters strength is defined through the use of existing commercial search engine, designed and implemented strength of character relationships and relational access The specific calculation algorithms. To illustrate the use of C? Value * IDF weight calculation method and an improved hierarchical clustering algorithm to determine the performance of identity names, the names in the search engine search results to be tested. Illustrates the hierarchical clustering algorithm based on improved identity of names names judge judgment can effectively reduce the time, but to lose some accuracy rate price.

Related Dissertations

  1. Based on the Social Network Perspective of Cultural and Creative Industries in Taiwan,G124
  2. Research on Focused Crawler Based on SVM Classification Algorithm,TP391.3
  3. Based on Social Network Analysis of Undergraduate Research Network opinion leaders,G206
  4. An Improvement of Cluster on Phylogenetic Profiling Method,TP311.13
  5. Research on Problem of College Students’ Social Network Communicative,D669.5
  6. From Virtual Community to the Real Life: How the Star Stautus Influence People’s Social Capital,G206
  7. Research on Dynamic Spreading Progress of Technology Production of Company G,F273.1;F407.672
  8. Based on the User’s Perceptual Needs’ Handle GPS Design,TN967.1
  9. Design and Implementation of the Character Classification System Used in Search Engine,TP391.3
  10. Research and Implement of the Theme Crawler for Automotive Industry,TP391.3
  11. Research and Application on Short Message Text Clustering,TP391.1
  12. Design and Implementation of Web Collaborative Learning Platform Based on SNS,TP311.52
  13. Research for Event Extraction Method in Specific Domain Based on Tree Conditional Random Field,TP391.1
  14. HMM-based Connection between the Social Network Analysis,F49
  15. The Relationship between Use of Social Network Sites and Individual Social Capital,G206
  16. SMBSDD: An improved search mechanism in unstructured P2P networks,TP393.02
  17. Web news hot discovery system design and implementation,TP393.09
  18. Research on multi-role social networks,TP393.09
  19. Classification model based monitoring of e-commerce Prohibited Research and Implementation,TP393.09
  20. Based on Social Network textile and garment production services agglomeration mechanism of Competitiveness,F426.8
  21. Social Capital: harmonious society adhesive,C912

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Computer network > General issues > The application of computer network
© 2012 www.DissertationTopic.Net  Mobile