Framing Unionization on Facebook: Communication around Representation Elections in the United States

A team of researchers including Arianna Pera, Veronica Jude, Ceren Budak, and Luca Maria Aiello published a groundbreaking study analyzing the connection between social media communication and union election outcomes. By combining National Labor Relations Board (NLRB) election data with 158,000 Facebook posts from U.S. labor unions between 2015 and 2024, they applied computational methods to understand how digital discourse influences real-world organizing. Using a fine-tuned RoBERTa classifier—a state-of-the-art natural language processing model—they systematically annotated posts across five established discourse frames: diagnostic (identifying problems), prognostic (proposing solutions), motivational (mobilizing action), community (emphasizing solidarity), and engagement (promoting interaction).

The analysis revealed that diagnostic and community frames dominated overall union communication, but strategic variations mattered significantly. Crucially, unions that employed more diagnostic, prognostic, and community frames in the period leading up to a representation election had higher odds of achieving a successful outcome. Post-election, framing patterns diverged based on results: after wins, the use of prognostic and motivational frames decreased, while after losses, prognostic and engagement frames saw increased usage. This research provides empirical evidence that specific communication strategies on platforms like Facebook correlate with tangible organizational success in labor movements.

The study, accepted at ICWSM 2026, contributes both methodological tools and open data to the intersection of computational social science and labor studies. By examining message-level framing at scale, it moves beyond anecdotal evidence to show how digital platforms have become central to modern labor organizing. The findings offer practical insights for unions seeking to optimize their social media strategies and for researchers studying how online discourse translates into offline collective action outcomes.