Seeing Through Green: Text-Based Classification and the Firm's Returns from Green Patents

Lapo Santarlasci, Armando Rungi, Antonio Zinilli
7/3/2025
econ.GNcs.CL

No official code found. Best implementation: lapo-s/seeing-through-green-code (0 stars, MIT, last commit 2025-12-23).

Abstract

This paper introduces Natural Language Processing for identifying ``true'' green patents from official supporting documents. We start our training on about 12.4 million patents that had been classified as green from previous literature. Thus, we train a simple neural network to enlarge a baseline dictionary through vector representations of expressions related to environmental technologies. After testing, we find that ``true'' green patents represent about 20\% of the total of patents classified as green from previous literature. We show heterogeneity by technological classes, and then check that `true' green patents are about 1\% less cited by following inventions. In the second part of the paper, we test the relationship between patenting and a dashboard of firm-level financial accounts in the European Union. After controlling for reverse causality, we show that holding at least one ``true'' green patent raises sales, market shares, and productivity. If we restrict the analysis to high-novelty ``true'' green patents, we find that they also yield higher profits. Our findings underscore the importance of using text analyses to gauge finer-grained patent classifications that are useful for policymaking in different domains.

View on arXivView PDF

Code Implementations(1)

lapo-s/seeing-through-green-codeCommunity67%
MIT

Code to replicate the analysis in the paper "Seeing Through Green: Text-Based Classification and the Firm's Returns from Green Patents"

00Stata, PythonDec 19, 202510 months agoMIT

Similar Papers

Solution for the EPO CodeFest on Green Plastics: Hierarchical multi-label classification of patents relating to green plastics using deep learning

82% match2023

From scratch to silver: Creating trustworthy training data for patent-SDG classification using Large Language Models

81% match2025

Early screening of potential breakthrough technologies with enhanced interpretability: A patent-specific hierarchical attention network model

80% match2024

Tracing the Flow of Knowledge From Science to Technology Using Deep Learning

80% match2025

Unveiling Black-boxes: Explainable Deep Learning Models for Patent Classification

80% match2023

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

79% match1 repo892022

Cite this paper

@article{santarlasci2025seeing,
  title  = {Seeing Through Green: Text-Based Classification and the Firm's Returns from Green Patents},
  author = {Lapo Santarlasci and Armando Rungi and Antonio Zinilli},
  year   = {2025},
  eprint = {2507.02287},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.02287v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.02287.svg)](https://codeofpaper.com/paper/2507.02287)

Discussion