---
license: gpl-3.0
---

The model aims to assess the moral dimension of Twitter posts in Italian about immigration.
Namely, limited to the immigration subject, the model is capable to classify tweets according to the expression of both moral dyads:

* 0:care/harm
* 1:fairness/cheating
* 2:loyalty/betrayal
* 3:authority/subversion
* 4:purity/degradation
* 5:no moral

and <b>focus concerns</b>, i.e, one of
* 0:prescriptive
* 1:prohibitive
* 2:no focus

These weights include the parameters of the custom layers, including the weights and biases of the two classifiers attached to the pre-trained model.

The model was built as part of the European project [VALAWAI](www.valawai.eu).