This API allows to visualize the different hate speech target community networks obtained by mixing data views of a different nature (feature or graph space)
- Clustering techniques: K-means & K-medoids {KM}, Spectral clustering {SC}, and Multi-view Spectral Clustering {MvSC}
- Feature sets
- mBERT view {mBERT} - multilingual BERT
- mUSE view {mUSE} - multilingual Universal Sentence Encoder
- Affinity matrices
- Projection view {mBERT-PRO & mUSE-PRO}
- Network view {mBERT-NET & mUSE-NET}
Parameters
Network Projection
(click on nodes to explore)
To visualize the corresponding network of words, please click: