What does the public say? A computational analysis of regulatory comments

While regulations affect your life every day, and millions of public comments are submitted to regulatory agencies in response to their proposals, analyzing the comments has traditionally been reserved for legal experts. Vlad Eidelman outlines how natural language processing (NLP) and machine learning can be used to automate the process by analyzing over 10 million publicly released comments.

Whether we know it or not, regulations affect our lives every day—from the Federal Communications Commission’s (FCC) net neutrality, to the Environmental Protection Agency’s (EPA) greenhouse gas, and the Securities and Exchange Commission’s (SEC) Dodd-Frank rules. Analysis of the impact these policy changes have on organizations and the public has long been the domain of legal experts. However, in recent years, as both the ease of participation and interest in rule making have grown, there’s been an explosion of public participation, and agencies now receive millions of comments each year concerning proposed agency actions. As these comments are submitted by a wide range of stakeholders, including affected companies, advocacy groups, and the general public, the text within them represents a trove of information about the real-world impact a law will have through diverse perspectives and arguments in support of and opposition to the proposals. Vlad Eidelman outlines how natural language processing and machine learning techniques can be used to automate the comment review process. He presents the first large-scale analysis of over 10 million publicly released comments across agencies over the last several decades. By performing automated stance detection and argument mining, you can begin to determine which comments are likely more influential than others, how the expert commenters—businesses and advocacy groups—differ from the general public, and how comments submitted to different agencies differ in what they say and how they say it.