Scholars and the Machine. On automation and academic performance

A central question in economics is whether technological innovations complement or substitute workers’ skills, thus enhancing or replacing workers’ productivity. However, occupational output is typically hard to measure, especially for high-skilled workers performing abstract tasks. In this paper, we focus on the effect of technology on productivity and inequality within a specific high-skilled group, that of researchers in economics, for whom we collect the universe of research output (i.e. published papers) for the period 1990-2020. We use as a case study the introduction of DYNARE, a software designed to easily solve and simulate dynamic stochastic general equilibrium (DSGE) models. We develop a heterogeneous agents dynamic model of research and citations accumulation, in which the arrival of the technology allows some researchers to perform more easily a subset of the tasks needed to write academic papers. Next, we test the model’s implications by leveraging quasi-experimental variation in DYNARE adoption across economic fields. We find that treated fields experience a differential increase in the yearly number of publications with respect to untreated ones. Second, at the author level, we find that the most-exposed researchers experienced a sharp and persistent decline in citation impact relative to their peers. Analyzing their abstracts using text embeddings shows that they converged on a narrower set of topics rather than exploring new fields, suggesting that while technology lowered barriers to entry and boosted aggregate output, it eroded the comparative advantage of researchers who had specialized in automated tasks, diminishing their academic standing.