@misc{10481/33681,
year = {2014},
url = {http://hdl.handle.net/10481/33681},
abstract = {When selecting relevant inputs in modeling problems with low quality data, the ranking of the most informative inputs is also uncertain. In this paper, this issue is addressed through a new procedure that allows the extending of different crisp feature selection algorithms to vague data. The partial knowledge about the ordinal of each feature is modelled by means of a possibility distribution, and a ranking is hereby applied to sort these distributions. It will be shown that this technique makes the most use of the available information in some vague datasets. The approach is demonstrated in a real-world application. In the context of massive online computer science courses, methods are sought for automatically providing the student with a qualification through code metrics. Feature selection methods are used to find the metrics involved in the most meaningful predictions. In this study, 800 source code files, collected and revised by the authors in classroom Computer Science lectures taught between 2013 and 2014, are analyzed with the proposed technique, and the most relevant metrics for the automatic grading task are discussed.},
organization = {This work was supported by the Spanish Ministerio de Economía y Competitividad under Project TIN2011-24302, including funding from the European Regional Development Fund.},
publisher = {Hindawi Publishing Corporation},
keywords = {Massive Open Online Courses (MOOCs)},
keywords = {Metrics},
keywords = {Automatic grading},
keywords = {Vague data},
keywords = {Genetic learning},
title = {A Procedure for Extending Input Selection Algorithms to Low Quality Data in Modelling Problems with Application to the Automatic Grading of Uploaded Assignments},
doi = {10.1155/2014/468405},
author = {Otero, José and Palacios Jiménez, Ana and Suárez, Rosario and Junco, Luis and Couso, Inés and Sánchez, Luciano},
}