Filtering machine for sponsored content

A machine comprising:

• communication circuitry coupled to at least one network and configured to receive first sponsored content from a first client device;
• quality model circuitry;
• and
• filtering circuitry coupled to the communication circuitry and to the quality model circuitry, the filtering circuitry configured to:
• receive the first sponsored content from the communication circuitry;
• input at least a portion of the first sponsored content into the quality model circuitry;
• receive from the quality model circuitry a quality metric for the first sponsored content;
• compare the quality metric to a quality threshold;
• and
• effect provision of the first sponsored content to a second client device for display on the second client device when the quality metric exceeds the quality threshold;
• wherein the quality model circuitry is configured to generate the quality metric for the first sponsored content based upon (i) historical feedback associated with other sponsored content and (ii) a trustworthiness factor of the first sponsored content determined based upon an analysis of coherence corresponding to textual features of the first sponsored content, wherein the coherence is determined based upon a cosine similarity between bag of word vectors of a title of the first sponsored content and a description of the first sponsored content.

A method comprising:

• receiving, at filtering circuitry via communication circuitry, first sponsored content from a first client device and second sponsored content from a third client device;
• inputting, by the filtering circuitry, at least a portion of the first sponsored content and at least a portion of the second sponsored content into quality model circuitry;
• implementing, by the quality model circuitry, a predictive model;
• generating, by the quality model circuitry, a first quality metric for the first sponsored content based upon (i) historical feedback associated with other sponsored content and (ii) a trustworthiness factor of the first sponsored content determined based upon an analysis of coherence corresponding to textual features of the first sponsored content, wherein the coherence is determined based upon a cosine similarity between bag of word vectors of a title of the first sponsored content and a description of the first sponsored content;
• generating, by the quality model circuitry, a second quality metric for the second sponsored content based upon (i) the historical feedback associated with the other sponsored content and (ii) a second trustworthiness factor of the second sponsored content;
• comparing, by the filtering circuitry, the first quality metric and the second quality metric;
• and
• effecting provision of the first sponsored content to a second client device for display on the second client device with higher priority than the second sponsored content when the first quality metric of the first sponsored content exceeds the second quality metric of the second sponsored content.