Table 2.

The Akaike information criterion (AIC) results against all models. Each row is reported with the number of parameters (K), the residual sum of squares, and the AIC. A lower AIC is better.

Model	Number of parameters, K	Likelihood	AIC
MILA-SocNeta	59,668	−143.72	−597.05
MIL-SocNetb	56,296	−210.22	−464.45
Deep learning	138,502	−309.97	−260.84
Language	16695.5	−420.31	−61.03
LIWCc	93	−169.62	575.92
Usr2Vec	100	−190.28	640.32
Topic	200	−276.42	1290.66

^aMILA-SocNet: multiple instance learning with an anaphoric resolution for social network.

^bMIL-SocNet: multiple instance learning for social network.

^cLIWC: linguistic inquiry and word count.