Sentiment Unity example is not correct.

[99bits]

Hi, I'm testing the unity example: https://github.com/dotnet/machinelearning-samples/tree/main/samples/csharp/end-to-end-apps/Unity-HelloMLNET/HelloMLNET

Very strange that the prediction is Toxic for very basic statements like: "The world is a beautiful place" "I am loved" "Life is wonderful"

Is this a problem with the model? or is it with the unity example?