Todd Taulman Photography / Shutterstock / The Atlantic

Updated at 10:08 a.m. ET on June 2, 2019.

Democratic and Republican politicians agree on one thing about President Donald Trump’s tax returns: The Constitution determines who can see them. Democrats such as Representative David Cicilline insist that Congress needs access to fulfill its “constitutional responsibilities of oversight” and evaluate possible violations of the Constitution’s emoluments clauses. Republicans such as Representative Bradley Byrne insist that the House Ways and Means Committee’s request for the returns raises “questions of grave constitutional significance.” According to Republican Senator Chuck Grassley, the request goes beyond what the Framers of the Constitution “had in mind” when they “created Article I.”

Statements such as these illustrate something important about how the Constitution figures in public life. Elected officials from both parties appeal routinely to the nation’s foundational document. But, far from serving as a symbol of “unity and common purpose,” the Constitution has come to enable, or even exacerbate, partisan strife. In political debates such as the Trump tax tussle, it often feels as if the United States has two legal charters, one for Republicans and another for Democrats.

That’s not just an anecdotal impression. The tools of computational analysis shed light on how wide the chasm has grown.

The three of us recently examined the evolution of constitutional rhetoric on the floor of Congress from 1873 to 2016. We first identified the hundreds of thousands of remarks that referred to the Constitution. We then trained a machine-learning classifier to predict—based solely on the content of the remarks—whether Republicans or Democrats were speaking. If the algorithm finds this task hard to do, it implies that the parties are apt to talk in similar or overlapping ways. By contrast, if the algorithm performs this task with a high degree of accuracy, it implies that the parties are largely talking past each other.

The results are sobering. Since around 1980, it has become increasingly easy for an algorithm to predict whether any given constitutional remark was made by a Republican or a Democrat. It has likewise become increasingly easy to predict whether the speaker was a conservative or a liberal. By the time Trump took office, the machine was guessing right roughly 80 percent of the time, an all-time high by historic standards.

This result holds up across multiple machine-learning classifiers, multiple measures of algorithmic accuracy, and multiple criteria for what counts as a constitutional remark. Additional tests of the “disjointness” between the parties’ rhetoric point to the same conclusion: To an unprecedented extent, Republican and Democratic members of Congress no longer speak the same constitutional language.

Underlying this polarization of constitutional discourse, we further found, are competing constitutional vocabularies. Terms dating back to the ratification of the original Constitution in the late 1700s have become relatively associated with the Republican Party. For instance, today’s conservatives are more likely to use the phrase Founding Fathers and cite textual provisions such as the First, Second, and Tenth Amendments, emphasizing themes of individual liberty and the autonomy of the states.

Terms from or about the Reconstruction Amendments of 1865–70, on the other hand, have become relatively associated with the Democratic Party. Democrats are more likely to deploy the phrases civil rights and voting rights in particular, emphasizing themes of equality and federal authority. The perennial tension in constitutional law “between the values of the Founding and the values of Reconstruction,” as the law professor Kermit Roosevelt has described it, is today a highly partisan struggle.

Even more so than the fight over Trump’s tax returns, the ongoing debate over a high-profile Democratic electoral-reform bill shows how this struggle plays out. After House Democrats introduced H.R. 1 in January, Republicans insisted that the bill would “limit Americans’ First Amendment right to political speech” (Senator Mitch McConnell), encroach on “the liberties and powers of the Constitution reserved for the states and the people” (Representative Jeff Duncan), and undermine “the original intent of the Founders” (Representative Barry Loudermilk). Democrats countered that the bill would provide crucial protections for the “constitutional right to vote” (Representative Sheila Jackson Lee) and help redeem “a Constitution that was flawed” at its inception “by not recognizing the full equality of every American” (Senator Jeff Merkley).

As these remarks reflect, members of each party follow a certain constitutional script. The details change, depending on the issue. The broad interpretative themes, and ideological fault lines, stay the same.

Instead of transcending preexisting political divides, arguments framed in constitutional terms thus tend to mirror or magnify those divides. Since 1980, discourse about the Constitution has polarized at least as rapidly as discourse about other matters—on most measures, even more rapidly. Any number of legal thinkers have imagined the Constitution as supplying a kind of cultural glue that disciplines disagreement and tempers partisan passions. At least in recent decades, our findings suggest something closer to the opposite.

The two sides also rely on constitutional arguments to different degrees over time. During the 1960s and early 1970s, Democratic legislators invoked their preferred constitutional clauses and tropes far more often than Republican legislators invoked theirs. By the turn of the millennium, the situation had flipped. Of the 50 constitutional terms that were most strongly owned by one of the parties under President Barack Obama, fully three-quarters—from freedom of speech to bear arms to commander in chief—belonged to Republicans. Democrats may have dominated constitutional discourse in the Capitol at the height of the civil-rights movement, but Republicans have caught up, and then some. Although it is hard to measure the impact of such a rhetorical reversal, qualitative evidence suggests it has emboldened a variety of actors in the GOP coalition, including judges, and contributed to the growing use of hardball tactics on the right.

This confronts Democrats with a choice. One option is to accept the asymmetry and continue to emphasize nonconstitutional narratives. Yet insofar as the Constitution really is America’s civil religion, future Democrats who wish to enact transformative legislative programs may need to develop a more robust “higher law” language with which to make their case. The alternative is not just constitutional polarization, but constitutional marginalization—and the kinds of political setbacks that you don’t need a computer algorithm to track.

We want to hear what you think about this article. Submit a letter to the editor or write to letters@theatlantic.com.