Digital trace data have the potential to offer rich insight into complex behaviors that were once out of reach, but their use has raised vital and unresolved questions about what is—or is not—public opinion. Building on the work of James Bryce, Lindsay Rogers, Herbert Blumer, Paul Lazarsfeld, and more, this essay revisits the discipline’s historical roots and draws parallels between past theory and present practice. Today, scholars treat public opinion as the summation of individual attitudes, weighted equally and expressed anonymously at static points in time through polls, yet prior to the advent of survey research, it was conceived as something intrinsically social and dynamic. In an era dominated by online discussion boards and social media platforms, the insights of this earlier “classical tradition” offer two pathways forward. First, for those who criticize computational social science as poorly theorized, it provides a strong justification for the work that data scientists do in text mining and sentiment analysis. And second, it offers clues for how emerging technologies might be leveraged effectively for the study of public opinion in the future.