Incorporating weight properties in detection of web spam

This paper focus on incorporating weight properties to enhance Web spam detection algorithms. Our proposed methodology adds this feature into Anti-TrustRank algorithm and call it weighted Anti-TrustRank algorithm to show the effectiveness of the weight properties using a new metric. Experiments are...

Full description

Bibliographic Details
Main Authors: Goh, Kwang Leng Alex, Ravi, Kumar, Singh, Ashutosh Kumar
Other Authors: John Wu (Contact)
Format: Conference Paper
Published: Institute of Electrical and Electronics Engineers 2012
Online Access:http://hdl.handle.net/20.500.11937/31508
Description
Summary:This paper focus on incorporating weight properties to enhance Web spam detection algorithms. Our proposed methodology adds this feature into Anti-TrustRank algorithm and call it weighted Anti-TrustRank algorithm to show the effectiveness of the weight properties using a new metric. Experiments are conducted on WEBSPAM-UK2006, a public Web spam dataset and have shown that weighted Anti-TrustRank significantly outperforms Anti-TrustRank algorithm up to 37.85%.