The idea of implementing a solution for spam i.e SpamBrainz started in 2017. Since then, there has been progress towards it by implementing a high accuracy model in Keras called Lodbrok to detect spam. However, this model has been entirely trained offline with batches from a stored dataset.
The proposed idea is to complete this integration and make spam detection automated and a thing of the past.
The main parts I will focus on:
● Implement online learning of the Lodbrok model using the SpamNinja system feedback as the classifier.
● Complete SpamBrainz API to connect Lodbrok with SpamNinja.
● Create a dedicated web-site for SpamBrainz documentation and setup needed to help new contributors and get more traction.
In the future, the same concept of spam detection can be extended to all other MetaBrainz projects