The Internet is a major source of online news content. Current efforts to evaluate online news content including text, storyline, and sources is limited by the use of small-scale manual techniques that are time consuming and dependent on human judgments. This article explores the use of machine learning algorithms and mathematical techniques for Internet-scale data mining and semantic discovery of news content that will enable researchers to mine, analyze, and visualize large-scale datasets. This research has the potential to inform the integration and application of data mining to address realworld socio-environmental issues, including water insecurity in the Southwestern United States. This paper establishes a formal definition of framing and proposes an approach for the discovery of distinct patterns that characterize prominent frames. The authors’ experimental evaluation shows the proposed process is an effective approach for advancing semi-supervised machine learning and may assist in advancing tools for making sense of unstructured text.