Abstract
In recent years, most part of search engines use link analysis algorithms to measure the importance of web pages. The most famous link analysis algorithm is PageRank algorithm. However, previous researches in recent years have found that there exists an inherent bias against newly created pages in PageRank. In the previous work, a new ranking algorithm called DRank has been proposed to solve this issue. It utilizes the cluster phenomenon of PageRank in a directory to predict the possible importance of pages in the future and to diminish the inherent bias of search engines to new pages. In this paper, we modify the original DRank algorithm to complement the weaker part of DRank which could fail while the number of pages in directory is not enough. In our experiments, the augmented algorithm, i.e., DRank+ algorithm, obtains more accuracy in predicting the importance score of pages at next time stage than the original DRank algorithm. DRank+ not only alleviates the bias of newly created pages successfully but also reaches more accuracy than Page Quality and original DRank in predicting the importance of newly created pages.
| Original language | English |
|---|---|
| Title of host publication | WEBIST 2008 - 4th International Conference on Web Information Systems and Technologies, Proceedings |
| Pages | 175-180 |
| Number of pages | 6 |
| Volume | 2 |
| Publication status | Published - 2008 |
| Event | WEBIST 2008 - 4th International Conference on Web Information Systems and Technologies - Funchal, Madeira, Portugal Duration: 2008 May 4 → 2008 May 7 |
Other
| Other | WEBIST 2008 - 4th International Conference on Web Information Systems and Technologies |
|---|---|
| Country | Portugal |
| City | Funchal, Madeira |
| Period | 08-05-04 → 08-05-07 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Networks and Communications
- Computer Science Applications
- Information Systems and Management
Cite this
}
DRank+ : A directory based PageRank prediction method for fast pagerank convergence. / Kao, Hung-Yu; Liu, Chia Sheng; Tsai, Yu Chuan; Shih, Chia Chun; Tsai, Tse Ming.
WEBIST 2008 - 4th International Conference on Web Information Systems and Technologies, Proceedings. Vol. 2 2008. p. 175-180.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
TY - GEN
T1 - DRank+
T2 - A directory based PageRank prediction method for fast pagerank convergence
AU - Kao, Hung-Yu
AU - Liu, Chia Sheng
AU - Tsai, Yu Chuan
AU - Shih, Chia Chun
AU - Tsai, Tse Ming
PY - 2008
Y1 - 2008
N2 - In recent years, most part of search engines use link analysis algorithms to measure the importance of web pages. The most famous link analysis algorithm is PageRank algorithm. However, previous researches in recent years have found that there exists an inherent bias against newly created pages in PageRank. In the previous work, a new ranking algorithm called DRank has been proposed to solve this issue. It utilizes the cluster phenomenon of PageRank in a directory to predict the possible importance of pages in the future and to diminish the inherent bias of search engines to new pages. In this paper, we modify the original DRank algorithm to complement the weaker part of DRank which could fail while the number of pages in directory is not enough. In our experiments, the augmented algorithm, i.e., DRank+ algorithm, obtains more accuracy in predicting the importance score of pages at next time stage than the original DRank algorithm. DRank+ not only alleviates the bias of newly created pages successfully but also reaches more accuracy than Page Quality and original DRank in predicting the importance of newly created pages.
AB - In recent years, most part of search engines use link analysis algorithms to measure the importance of web pages. The most famous link analysis algorithm is PageRank algorithm. However, previous researches in recent years have found that there exists an inherent bias against newly created pages in PageRank. In the previous work, a new ranking algorithm called DRank has been proposed to solve this issue. It utilizes the cluster phenomenon of PageRank in a directory to predict the possible importance of pages in the future and to diminish the inherent bias of search engines to new pages. In this paper, we modify the original DRank algorithm to complement the weaker part of DRank which could fail while the number of pages in directory is not enough. In our experiments, the augmented algorithm, i.e., DRank+ algorithm, obtains more accuracy in predicting the importance score of pages at next time stage than the original DRank algorithm. DRank+ not only alleviates the bias of newly created pages successfully but also reaches more accuracy than Page Quality and original DRank in predicting the importance of newly created pages.
UR - http://www.scopus.com/inward/record.url?scp=58049175923&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=58049175923&partnerID=8YFLogxK
M3 - Conference contribution
SN - 9789898111265
VL - 2
SP - 175
EP - 180
BT - WEBIST 2008 - 4th International Conference on Web Information Systems and Technologies, Proceedings
ER -