U.S. regulatory agencies are required to solicit, consider, and respond to public comments before issuing regulations. In recent years, agencies have begun to accept comments via both email and Web forms. The transition from paper to electronic comments makes it much easier for individuals to customize "form" letters, which they do, creating "near-duplicate" comments that express the same viewpoint in slightly different languages. This paper explores the use of simple text clustering and retrieval algorithms for identifying near-duplicate public comments. Experiments with public comments about a recent regulation proposed by the Environmental Protection Agency (EPA) demonstrate the effectiveness of the algorithms.
展开▼
