← Volver a los artículos

Measuring Technological Innovation Over the Long Run

★ ★ ★ ★ ☆

Resumen del artículo

Título de Paperzilla
Word Nerds Unite: Can We Predict Breakthroughs by Reading Patents?

This paper introduces a new text-based measure of patent significance that predicts future citations and correlates with market value. Using this measure, the authors identify three major technological waves over two centuries and show that these waves are strong predictors of aggregate and sectoral productivity.

Explícamelo como si tuviera cinco años

Scientists found a way to tell how important old inventions were by looking at their papers. They saw that big new ideas came in waves, like bursts of creativity, which helped us make more and better things over time.

Posibles conflictos de intereses

At least one co-author has disclosed a financial relationship of potential relevance for this research.

Limitaciones identificadas

The measure of innovation may not fully capture economic value
The measure of innovation used is based on textual analysis of patents, which may not fully capture the true economic value of an innovation. For instance, patents that have a minor scientific impact, yet are successful in restricting competition, could generate sizable private values, which our measure is unlikely to capture.
Limited sample period for patent value analysis
The sample period for analysis of the relation between patent values and textual analysis-based quality metrics is limited to 1927-2012 due to data constraints. This is much shorter than the 1840-2010 period used for the analysis of innovation trends.
Limited availability of patent citations before 1945
Patent citations are only consistently recorded after 1945, limiting the comparison with the textual analysis measure in earlier periods.

Explicación de la calificación

This paper presents a novel approach to measuring technological innovation using textual analysis of patents, which offers advantages over traditional citation-based measures, particularly for analyzing long-run trends. The methodology is well-validated and the findings regarding technological waves and their link to productivity are significant. However, there are some limitations regarding the potential disconnect between the textual measure and true economic value, and data constraints affect the scope of some analyses.

Conviene saber

Este es el análisis de Starter. Paperzilla Pro verifica cada cita, investiga los antecedentes de los autores y las fuentes de financiación, y utiliza razonamiento avanzado con IA para ofrecer información más exhaustiva.

Explorar Pro →

Información del archivo

Título original: Measuring Technological Innovation Over the Long Run
Subido: 14 jul 2025, 10:37:47
Privacidad: Público