%0 Conference Paper %1 Rose:2003:HTC:1118894.1118904 %A Rose, Carolyn P. %A Roque, Antonio %A Bhembe, Dumisizwe %A VanLehn, Kurt %B Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2 %C Stroudsburg, PA, USA %D 2003 %I Association for Computational Linguistics %K Bayes CarmelTC classification text %P 68--75 %R 10.3115/1118894.1118904 %T A hybrid text classification approach for analysis of student essays %U http://dx.doi.org/10.3115/1118894.1118904 %X We present CarmelTC, a novel hybrid text classification approach for analyzing essay answers to qualitative physics questions, which builds upon work presented in (Rosé et al., 2002a). CarmelTC learns to classify units of text based on features extracted from a syntactic analysis of that text as well as on a Naive Bayes classification of that text. We explore the tradeoffs between symbolic and "bag of words" approaches. Our goal has been to combine the strengths of both of these approaches while avoiding some of the weaknesses. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two "bag of words" approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.

@inproceedings{Rose:2003:HTC:1118894.1118904, abstract = {We present CarmelTC, a novel hybrid text classification approach for analyzing essay answers to qualitative physics questions, which builds upon work presented in (Rosé et al., 2002a). CarmelTC learns to classify units of text based on features extracted from a syntactic analysis of that text as well as on a Naive Bayes classification of that text. We explore the tradeoffs between symbolic and "bag of words" approaches. Our goal has been to combine the strengths of both of these approaches while avoiding some of the weaknesses. Our evaluation demonstrates that the hybrid CarmelTC approach outperforms two "bag of words" approaches, namely LSA and a Naive Bayes, as well as a purely symbolic approach.}, acmid = {1118904}, added-at = {2011-07-06T09:45:45.000+0200}, address = {Stroudsburg, PA, USA}, author = {Rose, Carolyn P. and Roque, Antonio and Bhembe, Dumisizwe and VanLehn, Kurt}, biburl = {https://www.bibsonomy.org/bibtex/2b180579216f91645498d6069b93efb0e/jennymac}, booktitle = {Proceedings of the HLT-NAACL 03 workshop on Building educational applications using natural language processing - Volume 2}, description = {A hybrid text classification approach for analysis of student essays}, doi = {10.3115/1118894.1118904}, interhash = {da926da9472b8fa260f1278f5ffbe97f}, intrahash = {b180579216f91645498d6069b93efb0e}, keywords = {Bayes CarmelTC classification text}, numpages = {8}, pages = {68--75}, publisher = {Association for Computational Linguistics}, series = {HLT-NAACL-EDUC '03}, timestamp = {2011-07-06T09:45:45.000+0200}, title = {A hybrid text classification approach for analysis of student essays}, url = {http://dx.doi.org/10.3115/1118894.1118904}, year = 2003 }