Sociolinguistics on Twitter

& network—feature dependencies

Sébastien Lerique, Jacobo Levy-Abitbol, & Márton Karsai

IXXI, École Normale Supérieure de Lyon

Socio-economic status

Language style

Topics

Network structure

25%

francophone

GMT/GMT+1

Sociolinguistics

Toy model & questions

  • Create a task-independent representation of network + features

  • What is the dependency between network structure and feature structure

  • Can we capture that dependency in a representation

network—feature dependencies

network—feature independence

GCN + Variational auto-encoders = 🎉💖🎉

Socio-economic status

Language style

Topics

Socio-economic status

Language style

Topics

Compressed & combined representation of nodes + network

Kipf & Welling (2016)

How is this useful

a.k.a., questions we can (will be able to) ask

how much can we compress network + features

(down to what dimension)

how well does feature set 1 + network structure predict feature set 2
(and how much does network structure help in predicting)

→ relative importance of network/feature in predicting links or clusters

Socioeconomic status

Language style

More at git{hub,lab}.com/ixxi-dante/nw2vec

No correlation

Full correlation

Our model

Reference model