id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_sr4htmz7ybetbljnas2gnhc45a	RS Forsyth	Feature-finding for text classification	1996.0	27	.pdf	application/pdf	10320	928	69	Results of a benchmark test on 10 representative text-classification problems technique is applied to 10 test problems using five different types of textual marker. example, it is arguable that in the field of forecasting, the work of Makridakis and colleagues (e.g. Makridakis & Wheelwright, 1989), who tested a number of forecasting methods on a wide range Text Archive, stylometry currently lacks an equivalent set of accepted test problems. The text-categorization problems in this suite were selected to fulfil a number of requirements. stylometric studies, showing the length, in words, of text blocks that various researchers have tried data-driven feature-finding tested on the benchmark suite, namely those proposed by previous To recapitulate, textual features found by five different methods were tested on a range of textcategorization problems. text markers) and 10 levels on the second (problem number). stylistic marker types based on results obtained on a benchmark suite of text classification	./cache/work_sr4htmz7ybetbljnas2gnhc45a.pdf	./txt/work_sr4htmz7ybetbljnas2gnhc45a.txt