Center for Earth Systems Engineering and Management

While the definition of sustainability remains open for all to contribute to and participate in, there do seem to be some notions it has come to embody that should not be neglected as the definition coalesces. Among these are the ethical and social dimensions of sustainability. Whether or not it is appropriate, required, or even desirable, concepts like social equity, human rights, ethical sharing of commons, etc. have increasingly come under the umbrella of the sustainability discourse. Even if “sustainability” as a bare word doesn’t imply those things, the concept of sustainable development certainly has taken on those dimensions. That sustainability might be redefined or re-scoped to be a purely environmental or a rigidly scientific endeavor, is not an immediate concern of this paper, though if that were to occur (whether for the sake of simplicity or pragmatics), it should be done explicitly so the ethical sub-discourse can be maintained (indeed, sustained) by some other movement.

This paper proposes a mechanism by which such a migration in terms can be prevented. First, in reviewing the work of Denis Goulet, it shows the solid basis for including an ethical aspect in the sustainability discourse. Second, it points out that Karl-Henrik Robèrt’s highly-lauded and broadly-employed sustainability framework, The Natural Step, is deficient in this area. This deficiency provides the impetus for, finally, proposing a mechanism by which The Natural Step can be extended to include the important social and ethical dimensions of sustainability. This mechanism is based on the capabilities approaches that, in many respects, evolved out of Goulet’s early work. Augmented accordingly, TNS can continue to be used without fear of overlooking the social and ethical aspects of the sustainability discourse.

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.