courser web intelligence and big data 2 listen lecture slides

2

Ø 

Ø 

# R B

2 n n

1 N 1 N

“log-­‐likelihood”

p(xi

L = p(like | +)p(lot | +)[1− p(hate | +)][1− p(waste | +)]p(simple | +)[1− p(easy | +)][1− p(enjoy | +)]p(+) p(like | −)p(lot | −)[1− p(hate | −)][1− p(waste | −)]p(simple | −)[1− p(easy | −)][1− p(enjoy | −)]p(−)

L = .026

.00005

I(F, B) ≡ p( f , b)log p( f , b)

p( f )p(b)

f ,b

∑

I(H, S) = p(hate,+)log p(hate) p(+) p(hate,+) + p(¬hate,+)log p(¬hate) p(+) p(¬hate,+) + p(hate,−)log p(hate) p(−) p(hate,−) + p(¬hate,−)log p(¬hate) p(−) p(¬hate,−)

I(H, S) = p(hate,+)log p(hate) p(+) p(hate,+) + p(¬hate,+)log p(¬hate) p(+) p(¬hate,+) + p(hate,−)log p(hate) p(−) p(hate,−) + p(¬hate,−)log p(¬hate) p(−) p(¬hate,−)

– 

– 

English