Essay scoring is a difficult and contentious business. The problem is exacerbated when there are no “right” answers for the essay prompts. This research developed a simple toolset for essay analysis by integrating a freely available Latent Dirichlet Allocation (LDA) implementation into a homegrown assessment assistant. The complexity of the essay assessment problem is demonstrated and illustrated with a representative collection of open-ended essays. This research also explores the use of “expert vectors” or “keyword essays” for maximizing the utility of LDA with small corpora. While, by itself, LDA appears insufficient for adequately scoring essays, it is quite capable of classifying responses to open-ended essay prompts and providing insight into the responses. This research also reports some trends that might be useful in scoring essays once more data is available. Some observations are made about these insights and a discussion of the use of LDA in qualitative assessment results in proposals that may assist other researchers in developing more complete essay assessment software.

This report is the consolidated work of an interdisciplinary course project in CEE494/598, CON598, and SOS598, Urban Infrastructure Anatomy and Sustainable Development. In Fall 2012, the course at Arizona State University used sustainability research frameworks and life-cycle assessment methods to evaluate the comprehensive benefits and costs when transit-oriented development is infilled along the proposed light rail transit line expansion. In each case, and in every variation of possible future scenarios, there were distinct life-cycle benefits from both developing in more dense urban structures and reducing automobile travel in the process.

Results from the report are superseded by our publication in Environmental Science and Technology.

Global climate models predict increases in precipitation events in the Phoenix-metropolitan area and with the proposition of more flooding new insights are needed for protecting roadways and the services they provide. Students from engineering, sustainability, and planning worked together in ASU’s Urban Infrastructure Anatomy Spring 2016 course to assess:
       1. How historical floods changed roadway designs.
       2. Precipitation forecasts to mid-century.
       3. The vulnerability of roadways to more frequent precipitation.
       4. Adaptation strategies focusing on safe-to-fail thinking.
       5. Strategies for overcoming institutional barriers to enable transitions.
The students designed an EPA Storm Water Management Model for the City of Phoenix and forced it with future precipitation forecasts. Vulnerability indexes were created for infrastructure performance and social outcomes. A multi-criteria decision analysis framework was created to prioritize infrastructure adaptation strategies.