Systems and Methods for Generating a Message Topic Training Dataset from User Interactions in Message Clients

A computing system, comprising:

• one or more processors;
• memory storing one or more programs to be executed by the one or more processors, wherein the one or more programs comprise instructions for:
• collecting a plurality of recipient initiated message interaction events for messages in a first plurality of messages from a plurality of recipients, including a plurality of priority designation assignments and a plurality of message category change events in which a recipient has changed a category of a given message in the first plurality of messages from an original message category to an updated message category;
• identifying a subset of the first plurality of messages as having trusted message category assignments based on the plurality of recipient initiated message interaction events;
• constructing a message categorization dataset from the identified subset of the first plurality of messages, the constructing including selecting messages in the first plurality of messages that have undergone a recipient initiated message interaction event, wherein the message categorization dataset comprises, for each selected message from the identified subset, information identifying the message and information corresponding to a currently assigned message category for the message;
• training a message classifier using the message categorization dataset;
• after training the message classifier, classifying each message in a second plurality of messages using the message classifier by the one or more processors;
• and
• delivering the second plurality of messages to one or more recipients with a designation of a respective message category of each message in the second plurality of messages, as determined by the message classifier.

A non-transitory computer readable storage medium storing instructions for execution by one or more processors, the instructions, when executed, causing the one or more processors to perform a method of:

• collecting a plurality of recipient initiated message interaction events for messages in a first plurality of messages from a plurality of recipients, including a plurality of priority designation assignments and a plurality of message category change events in which a recipient has changed a category of a given message in the first plurality of messages from an original message category to an updated message category;
• identifying a subset of the first plurality of messages as having trusted message category assignments based on the plurality of recipient initiated message interaction events;
• constructing a message categorization dataset from the identified subset of the first plurality of messages, the constructing including selecting messages in the first plurality of messages that have undergone a recipient initiated message interaction event, wherein the message categorization dataset comprises, for each selected message from the identified subset, information identifying the message and information corresponding to a currently assigned message category for the message;
• training a message classifier using the message categorization dataset;
• after training the message classifier, classifying each message in a second plurality of messages using the message classifier by the one or more processors;
• and
• delivering the second plurality of messages to one or more recipients with a designation of a respective message category of each message in the second plurality of messages, as determined by the message classifier.