sanlunainiu / us-ai-patents

Code and Data for Text Classification of AI Related Patents Research Paper

Using Supervised Machine Learning for Large-Scale Classification in Management Research

Code and Data for: Miric, M., Jia, N. and Huang, K. (Forthcoming) Using Supervised Machine Learning for Large-Scale Classification In Management Research: The Case For Identifying Artificial Intelligence Patents. Strategic Management Journal.

Abstract

Researchers increasingly use unstructured text data to construct quantitative variables for analysis. This goal has traditionally been achieved using keyword-based approaches, which require researchers to specify a dictionary of keywords mapped to the theoretical concepts of interest. However, recent machine learning (ML) tools for text classification and natural language processing can be used to construct quantitative variables and to classify unstructured text documents. In this paper we demonstrate how to employ ML tools for this purpose and discuss one application for identifying artificial intelligence (AI) technologies in patents. We compare and contrast various ML methods with the keyword-based approach, demonstrating the advantages of the ML approach. We also leverage the classification outcomes generated by ML models to demonstrate general patterns of AI technology development.

About

This online repository contains the code needed to reconstruct the tables and figures from the paper. We demonstrate several classification approaches:

• Notebook A. Text Classification with a Bag-of-Words Representation
• Notebook B. Text Classification with a Embedding Based Text Representation
• Notebook C. Text Classification using a Convolutional Neural Network
• Notebook D. Text CLassification using Transformer Based Models
• Notebook X. Summary and Comparison of Different Classification Approaches

Notebooks are shown in GitHub but you can explort and open in Google Colab to replicate and utilize in own research projects.

License & Reuse

This code is availible with a Attribution-NonCommercial (CC BY-NC) license. You are welcome to use, or reuse the code as you wish. We hope that if you find this work helpful you will cite the research paper.

Natural language processing and text classification is a rapidly advancing field. We hope to keep this repository updated and add new code, extensions or updated data as they become availible. If you would like us to link or share additional extensions, please let us know.

Citation

@article{Miric2022,
  author = {Miric, Milan and Jia, Nan and Huang, Kenneth},
  title = {Using Supervised Machine Learning for Large-Scale Classification In Management Research: The Case For Identifying Artificial Intelligence Patents},
  year = {2022},
  journal = {Strategic Management Journal}
}

Acknowledggements