Disclosure: The tool is built by me. It uses 6 distinct methods to classify text with a 93% accuracy rate, based on testing a dataset of 100k+ samples.

Where are you hosting the dataset? Would love to help out, I'm building an open source data version control tool to help iterate on ML datasets.

https://github.com/Oxen-AI/oxen-release

Would be cool if we could get a community around the test dataset to insure that 93% accuracy rate. Then people can add their failure cases to the repo and then you can iterate on them.