Open jaidevd opened 1 year ago
Filter the scattertext output by brands and products, and make brand-specific recommendations.
Study the affinity of clusters with certain behaviours or actions.
For e.g.: Clusters 7 and 8 never give a bad rating! All their ratings are >= 40 These are "early morning" reviewers. If they give good ratings - what do the late night people do?
Cluster 5 represents users who:
Cluster 1:
Cluster 4:
Cluster 9:
Cluster 8:
Cluster 7:
Cluster 0:
Cluster 10: Noise
Just leaving some thoughts here: