Collective intelligence systems, methods, and devices

A computer-implemented method implemented by one or more computers including each including hardware, including one or more processors, and software, the method comprising:

• (A) presenting a poll question to a group of users;
• (B) collecting user responses to the poll question, at least some of the user responses including a corresponding user reason;
• (C) determining an aggregated prediction based on the user responses;
• (D) determining a set of aggregated reasons based on user reasons provided with the user responses, wherein the determining of the set of aggregated reasons in (D) comprises:
• (D)(1) converting the user reasons into high dimensional vectors using an embedding model;
• (D)(2) applying a transformation to each textual input embedding such that the embeddings better cluster;
• (D)(3) clustering the transformed textual input embeddings;
• and
• (D)(4) summarization and rewriting texts that have been clustered;
• (E) presenting a summary of the user responses, the summary including the aggregated prediction and an aggregated reason corresponding to the aggregated prediction;
• (F) in response to the presenting, collecting modified user responses to the poll question, at least some of the user-modified responses including a corresponding modified user reason, wherein the modified user reason is selected from the set of aggregated reasons;
• (G) in response to the collecting in (F), determining an updated aggregated prediction based on the modified user responses;
• and
• (H) presenting a summary of the user responses, the summary including the updated aggregated prediction and an aggregated reason corresponding to the aggregated prediction.