Career Mobility in Construction Leadership: Insights from LinkedIn Recommendations and Data-Driven Analysis

Career mobility—the movement of individuals across roles, positions, or industries—is essential in today’s evolving job market. Guided by signaling theory, this study examines how LinkedIn recommendation characteristics relate to career mobility, measured by the number of positions held and companies worked at. We collected LinkedIn profile data from construction leaders at major US firms and used natural language processing to analyze the content of their received recommendations. Latent Dirichlet allocation (LDA) was applied to assess thematic breadth and depth, and regression models were used to explore associations with career mobility indicators. Findings suggest that the depth of recommendations significantly influences career mobility, surpassing both the length and quantity of recommendations. Competency-related themes emerged as the second most impactful factor. These results underscore the value of high-quality, content-rich recommendations in shaping perceived career potential, highlighting how digital professional signals can influence career trajectories.