Method and system for topic disambiguation and classification

One or more non-transitory computer storage media encoded with computer program instructions that, when executed by one or more computers, cause the one or more computers to perform operations comprising:

• obtaining, for a message that was broadcasted on a social network platform and is associated with an initial classification that identifies a first set of topics for the message, topic engagement information about third party accounts engaging with the message, the topic engagement information comprising one or more distributions of topic interest scores, topic expertise scores, or both, associated with the third party accounts;
• determining that the message is associated with an engagement-based classification using the topic engagement information, wherein the engagement-based classification associates the message with a second set of topics of a plurality of topics that includes the first set of topics;
• validating the initial classification for the message by:
• determining whether the engagement-based classification is the same as the initial classification;
• and
• determining a final classification for the message using a result of the determination whether the engagement-based classification is the same as the initial classification;
• generating, using the final classification, a recommendation for one or more other accounts of the social network platform;
• and
• broadcasting the recommendation to the one or more other accounts.

A computer-implemented method comprising:

• obtaining, for a message that was broadcasted on a social network platform and is associated with an initial classification that identifies a first set of topics for the message, topic engagement information about third party accounts engaging with the message, the topic engagement information comprising one or more distributions of topic interest scores, topic expertise scores, or both, associated with the third party accounts;
• determining that the message is associated with an engagement-based classification using the topic engagement information, wherein the engagement-based classification associates the message with a second set of topics of a plurality of topics that includes the first set of topics;
• validating the initial classification for the message by:
• determining whether the engagement-based classification is the same as the initial classification;
• and
• determining a final classification for the message using a result of the determination whether the engagement-based classification is the same as the initial classification;
• generating, using the final classification, a recommendation for one or more other accounts of the social network platform;
• and
• broadcasting the recommendation to the one or more other accounts.