Center for Earth Systems Engineering and Management

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.

There is increasing evidence that vehicle travel in developed countries may have peaked, contradicting many historical travel demand forecasts. The underlying causes of this peaking are still under debate and there has been a mobilization of research, largely focused at national scales, to study the explanatory drivers. There is, however, a dearth of research focused at the metropolitan scale where transportation policy and planning are frequently decided.

Using Los Angeles County, California, as a case study, we investigate the Peak Car theory and whether social, economic, and technical factors, including roadways that have become saturated at times, may be contributing to changes in travel behavior. After peaking in 2002, vehicle travel in Los Angeles County declined by 3.4 billion (or 4.1%) by 2010. The effects of changing fuel prices, fuel economy, population growth, increased utilization of alternate transportation modes, changes in driver demographics, income, and freight are first assessed. It is possible, and likely, that these factors alone explain the reduction in travel. However, the growth in congestion raises questions of how a constricting supply of roadway network capacity may contribute to travel behavior changes.

There have been no studies that have directly assessed how the maturing supply of infrastructure coupled with increasing demand affect travel behavior. We explore regional and urban factors in Los Angeles to provide insight into the drivers of Peak Car at city scales where the majority of travel occurs. The results show that a majority of the decline in VMT in Los Angeles can be attributed the rising fuel prices during the 2000s. While overall roadway network capacity is not yet a limiting factor for vehicle travel there is some evidence that suggests that congestion along certain corridors may be shifting some automobile travel to alternatives. The results also suggest that the relative impact of any factor on travel demand is likely to vary from one locale to another and Peak Car analysis across large geographic areas obscures the nuisances of travel behavior at a local scale.