Improvement of HITS-based algorithms on web documents Export

@inproceedings{citeulike:312787, abstract = {In this paper, we present two ways to improve the precision of HITS-based algorithms on Web documents. First, by analyzing the limitations of current HITS-based algorithms, we propose a new weighted HITS-based method that assigns appropriate weights to in-links of root documents. Then, we combine content analysis with HITS-based algorithms and study the effects of four representative relevance scoring methods, VSM, Okapi, TLS , and CDR , using a set of broad topic queries. Our experimental results show that our weighted HITS-based method performs significantly better than Bharat's improved HITS algorithm. When we combine our weighted HITS-based method or Bharat's HITS algorithm with any of the four relevance scoring methods, the combined methods are only marginally better than our weighted HITS-based method. Between the four relevance-scoring methods, there is no significant quality difference when they are combined with a HITS-based algorithm.}, address = {New York, NY, USA}, author = {Li, Longzhuang and Shang, Yi and Zhang, Wei}, booktitle = {WWW '02: Proceedings of the 11th international conference on World Wide Web}, citeulike-article-id = {312787}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=511514}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/511446.511514}, doi = {10.1145/511446.511514}, isbn = {1-58113-449-5}, keywords = {hits, link-analysis, weighted}, location = {Honolulu, Hawaii, USA}, pages = {527--535}, posted-at = {2009-10-21 04:40:12}, priority = {2}, publisher = {ACM}, title = {Improvement of HITS-based algorithms on web documents}, url = {http://dx.doi.org/10.1145/511446.511514}, year = {2002} }

TY - CONF ID - citeulike:312787 L3 - citeulike-article-id:312787 N2 - In this paper, we present two ways to improve the precision of HITS-based algorithms on Web documents. First, by analyzing the limitations of current HITS-based algorithms, we propose a new weighted HITS-based method that assigns appropriate weights to in-links of root documents. Then, we combine content analysis with HITS-based algorithms and study the effects of four representative relevance scoring methods, VSM, Okapi, TLS , and CDR , using a set of broad topic queries. Our experimental results show that our weighted HITS-based method performs significantly better than Bharat's improved HITS algorithm. When we combine our weighted HITS-based method or Bharat's HITS algorithm with any of the four relevance scoring methods, the combined methods are only marginally better than our weighted HITS-based method. Between the four relevance-scoring methods, there is no significant quality difference when they are combined with a HITS-based algorithm. CY - Honolulu, Hawaii, USA SN - 1-58113-449-5 AD - New York, NY, USA EP - 535 TI - Improvement of HITS-based algorithms on web documents PB - ACM T2 - WWW '02: Proceedings of the 11th international conference on World Wide Web SP - 527 KW - hits KW - link-analysis KW - weighted AU - Li, Longzhuang AU - Shang, Yi AU - Zhang, Wei PY - 2002/// UR - http://dx.doi.org/10.1145/511446.511514 ER -