Milan Miric (University of Southern California),
Nan Jia (University of Southern California)
& Kenneth Huang (National University of Singapore)
[Scroll Down for Paper, Supplementary Information, Data & Summary of Findings]
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.
Text-based documents offer a wealth of information for researchers and business analysts. However, researchers often need to find a way to classify these documents to use in subsequent research projects. In this paper, we demonstrate how supervised machine learning (ML) methods can be used to automate the process of classifying textual documents into pre-defined categories or groups. We provide an overview of when such techniques may be used in comparison to other methods, and the considerations and tradeoffs associated with each method. We apply these methods to identify artificial-intelligence (AI) based technologies from all patents in the U.S., based on patent abstract text. This allows us to show interesting patterns of AI innovation development in the United States. We also provide the code and data used in this paper for future research.
A goal of this paper was to document the development of AI related technologies through patent data. Below, we provide some trends on the development of AI related patents and technologies in the US. In particular, we report on the following.
Number and Share of AI Patents by Year
Geographic Distribution of AI Patents
Top Assignees in AI Related Patents
Most Common Patent Classes of AI Related Patents
These can be found by scrolling through the tableau visualization below.
Manuscript published at Strategic Management Journal
Supplementary information about methods and helpful background information.
Link to Data Request Form
(Being updated with latest data)
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.
NLP Methods are continuously developing and new patents are continuously granted. We will release period updates if new text classification methods become available, if new training data is created, or periodically as new patents are issued.
