Social and environmental factors affecting land use change are among the most significant drivers transforming the planet. Such change has been and continues to be monitored through the use of satellite imagery, aerial photography, and technical reports. While these monitoring tools are useful in observing the empirical results of land use change and issues of sustainability, the data they provide are often not useful in capturing the fundamental policies, social drivers, and unseen factors that shape how landscapes are transformed. In addition, some monitoring approaches can be prohibitively expensive and too slow in providing useful data at a timescale in which data are needed. This paper argues that techniques using information fusion and conducting assessments of continuous data feeds can be beneficial for monitoring primary social and ecological mechanisms affecting how geographic settings are changed over different time scales. We present a computational approach that couples open source tools in order to conduct an analysis of text data, helping to determine relevant events and trends. To demonstrate the approach, we discuss a case study that integrates varied newspapers from two Midwest states in the United States, Iowa and Nebraska, showing how potentially significant issues and events can be captured. Although the approach we present is useful for monitoring current web-based data streams, we argue that such a method should ultimately be integrated closely with less managed systems and modeling techniques to enhance not only land use monitoring but also to better forecast and understand landscape change.