Improving performance of automated scoring through detection of outliers and understanding model instabilities Research Report

@inproceedings{Foltz2013ImprovingPO,
  title={Improving performance of automated scoring through detection of outliers and understanding model instabilities Research Report},
  author={Peter W. Foltz},
  year={2013}
}
Automated scoring of writing operates under the assumption that the quality of a student essay can be characterized by a model of weighted features that are extracted from the essay. Because the automated scoring model is trained predicated on a representative sample of essays for a prompt, associated with each feature is an expected range of acceptable values based on the distribution in the training set. However, if the value for a particular feature or combined values for a group of features… CONTINUE READING
1 Citations
12 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-10 of 12 references

Contrasting state-of-the-art automated scoring of essays: Analysis

  • M. Shermis, B. Hammer
  • Paper presented at NCME annual meeting, Vancouver…
  • 2012
Highly Influential
1 Excerpt

Increasing Reliability Throughout the Automated Scoring Development Process

  • K. E. Lochbaum, M. B. Rosenstein, L. Davis
  • 2012

Increasing Reliability Throughout the Automated Scoring Development Process. Paper presented at the National Council for Measurement in Education

  • P. W. Foltz, K. E. Lochbaum, M. B. Rosenstein, L. Davis
  • Annual Conference,
  • 2012
2 Excerpts

locfit: Local Regression, Likelihood and Density Estimation

  • C. Loader
  • R package version 1.5-8. http://CRAN.R-project…
  • 2012
1 Excerpt

The measurement of textual coherence with Latent Semantic Analysis

  • P. W. Foltz, W. Kintsch, T. K. Landauer
  • Discourse Processes,
  • 1998
1 Excerpt

Similar Papers

Loading similar papers…