Abstract | ||
---|---|---|
This paper discusses web page classification using hypertext features such as the text included in the web page, the title, headings, URL, and anchor text. Five different classification approaches based on SVM that use individual features or combinations are investigated on the LookSmart dataset. The initial experimental results have shown that combining the features improves the performance of the classifier and that some features such as title and headings can be very useful for certain tasks. On the basis of this analysis, we propose a voting method that further improves the performance compared with the individual classifiers. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1109/WI-IATW.2006.23 | IAT Workshops |
Keywords | Field | DocType |
voting method,certain task,web page,paper discusses web page,initial experimental result,anchor text,individual feature,individual classifier,looksmart dataset,web pages,different classification,classification,internet,information exchange,url,support vector machines | Data mining,Hypertext,Web page,Information retrieval,Voting,Computer science,Information exchange,Support vector machine,Anchor text,Classifier (linguistics),The Internet | Conference |
ISBN | Citations | PageRank |
0-7695-2749-3 | 4 | 0.47 |
References | Authors | |
15 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Rui Fang | 1 | 4 | 0.47 |
Alexander Mikroyannidis | 2 | 116 | 21.79 |
Babis Theodoulidis | 3 | 353 | 76.60 |