Machine Learning Approach for Answer Detection in Discussion Forums: An Application of Big Data Analytics

Table 2

Fourteen lexical, content-based, and semantic features (including proposed semantic features F1, F16, and F17).

Code	Abbreviation
F1	ThrdCntrodRplyWMDistance
F2	ThrdCentrodRplyCosnSmlrty
F3	TtlRplyCosnSmlrtyWholCrps
F4	QustionRplyCosnSmlrtyWholCrps
F5	TtlRplyCosnSmlrty
F6	QustionRplyCosnSmlrty
F7	UnqWrds
F11	ReWrdsOvrlpInitialPost
F12	ReWrdsOvrlpThrdTitl
F13	IsRplyContan5WHWrds
F15	IsRplyHvHyperlnk
F16	“WMDbtwnTitlRpl”
F17	“WMDbtwnQustionRpl”
F20	NoWrdsRply