Research on the Key Technology of Web Data Extraction and Mining Based on the Probability Distribution

Table 1

Experimental results of the first group.

The domain name	The number of words
	Title	Author	Date	Affiliation
Correct-marked words	749	557	85	621
Words in data set	806	621	93	683
Words in extracted result set	835	575	101	691
REC	0.929280	0.896940	0.913978	0.909224
PRE	0.897001	0.968696	0.841582	0.898698