Novel Approach for Policy Network Extraction from Web Documents

Abstract: The increment of information in the web is too large, so search engine come to play an important role to find relation between input keywords. Policy networks are one well defined domain for research. In Today�s World Policy networks are used by economists and political scientists. The analysis of policy networks demands a series of arduous and time-consuming some steps which are manual including interviews and questionnaires .We are calculating the strength of relation between actors in policy networks using feature extracted from data harvested from the web. Features are like out links, webpage counts. Features are like out links, webpage counts, and derived some lexical information from web snippets, documents. The features are evaluated both in jointly and isolation for both positive and negative actor relations Performance is measuring in terms of co-relation between the human rated and the automatically extracted relations.

Keywords: Policy Network, relatedness metrics, web link, web Documents.