Techniques for identifying and validating online content items for presentation to users are disclosed. Disclosed systems and methods use a sentiment analyzer to determine a sentiment of a candidate content item and collateral content items identified using keywords associated with the candidate content item, determine a measure of agreement in sentiment using the sentiments determined for the candidate content item and collateral content items, and provide at least a portion of the candidate content item in a display at a client computing device, the display including a consensus belief indicator representing the measure of agreement in sentiment.