Social media affect financial markets, but public posts by financial media personas are voluntary disclosures, hence undisclosed views are unobserved. We address this measurement problem by conducting repeated, real-time interviews of “digital twins'' built from finfluencers' X accounts. The interviews recover stock-level public-persona belief proxies even when no public recommendation is made. Because interview responses are generated before the return windows, the design avoids look-ahead bias. We show that digital-twin responses predict the cross section of large-cap stock returns in the expected direction. Repeated real-time interviews therefore show how selective disclosure can be turned into measurable panels of market views.Just created for emails