Using feature construction to avoid large feature spaces in text classification

Created by W.Langdon from gp-bibliography.bib Revision:1.7615

@InProceedings{Mayfield:2010:gecco,

• author = "Elijah Mayfield and Carolyn Penstein-Rose",
• title = "Using feature construction to avoid large feature spaces in text classification",
• booktitle = "GECCO '10: Proceedings of the 12th annual conference on Genetic and evolutionary computation",
• year = "2010",
• editor = "Juergen Branke and Martin Pelikan and Enrique Alba and Dirk V. Arnold and Josh Bongard and Anthony Brabazon and Juergen Branke and Martin V. Butz and Jeff Clune and Myra Cohen and Kalyanmoy Deb and Andries P Engelbrecht and Natalio Krasnogor and Julian F. Miller and Michael O'Neill and Kumara Sastry and Dirk Thierens and Jano {van Hemert} and Leonardo Vanneschi and Carsten Witt",
• isbn13 = "978-1-4503-0072-8",
• pages = "1299--1306",
• keywords = "genetic algorithms, genetic programming, NLP, Natural Language Processing, Text analysis, SVM",
• month = "7-11 " # jul,
• organisation = "SIGEVO",
• address = "Portland, Oregon, USA",
• DOI = "doi:10.1145/1830483.1830714",
• publisher = "ACM",
• publisher_address = "New York, NY, USA",
• abstract = "Feature space design is a critical part of machine learning. This is an especially difficult challenge in the field of text classification, where an arbitrary number of features of varying complexity can be extracted from documents as a preprocessing step. A challenge for researchers has consistently been to balance expressiveness of features with the size of the corresponding feature space, due to issues with data sparsity that arise as feature spaces grow larger. Drawing on past successes with genetic programming in similar problems outside of text classification, we propose and implement a technique for constructing complex features from simpler features, and adding these more complex features into a combined feature space which can then be used by more sophisticated machine learning classifiers. Applying this technique to a sentiment analysis problem, we show encouraging improvement in classification accuracy, with a small and constant increase in feature space size. We also show that the features we generate carry far more predictive power than any of the simple features they contain.",
• notes = "Also known as \cite{1830714} GECCO-2010 A joint meeting of the nineteenth international conference on genetic algorithms (ICGA-2010) and the fifteenth annual genetic programming conference (GP-2010)",

}

Genetic Programming entries for Elijah Mayfield Carolyn Penstein Rose

Citations