Humanitarian Crisis Analysis Using Secondary Information Gathered By a Focused Web Crawler

A computer program product for analyzing an event, the computer program product comprising a computer-readable storage medium having a computer-readable program stored therein, wherein the computer-readable program, when executed on a computing device including at least one processor, causes the at least one processor to perform:

• crawling a network using a trained learning model to identify a set of secondary-source documents related to the event;
• identifying one or more hub pages from the set of secondary-source documents that include one or more links predicted to link to at least one new relevant secondary-source document;
• adding the at least one new relevant secondary-source document to the set of secondary-source documents;
• extracting information from the set of secondary-source documents;
• receiving feedback information indicative of a relevancy level for the extracted information as applied to the event;
• classifying each document in the set of secondary-source documents into one or more categories related to the event, based on the extracted information and the received feedback information;
• and
• training a learning model based on the received feedback.

A system for analyzing an event, the system comprising:

• at least one processor;
• and
• a memory operably coupled to the at least one processor, wherein the memory comprises program instructions which, when executed by the at least one processor, cause:
• crawling a network using a trained learning model to identify a set of secondary-source documents related to the event;
• identifying one or more hub pages from the set of secondary-source documents that include one or more links predicted to link to at least one new relevant secondary-source document;
• adding the at least one new relevant secondary-source document to the set of secondary-source documents;
• extracting information from the set of secondary-source documents;
• receiving feedback information indicative of a relevancy level for the extracted information as applied to the event;
• classifying each document in the set of secondary-source documents into one or more categories related to the event, based on the extracted information and the received feedback information;
• and
• training a learning model based on the received feedback.