Webpage Segments Classification with Incremental Knowledge Acquisition
This paper suggests an incremental information extraction method for social network analysis of web publications. For this purpose, we employed an incremental knowledge acquisition method, called MCRDR (Multiple Classification Ripple-Down Rules), to classify web page segments. Our experimental results show that our MCRDR-based web page segments classification system successfully supports easy acquisition and maintenance of information extraction rules.
KeywordsInformation extraction social networks knowledge acquisition
Unable to display preview. Download preview PDF.