Machine learning in automated text categorization Export

@article{citeulike:83774, abstract = {The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last 10 years, due to the increased availability of documents in digital form and the ensuing need to organize them. In the research community the dominant approach to this problem is based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristics of the categories. The advantages of this approach over the knowledge engineering approach (consisting in the manual definition of a classifier by domain experts) are a very good effectiveness, considerable savings in terms of expert labor power, and straightforward portability to different domains. This survey discusses the main approaches to text categorization that fall within the machine learning paradigm. We will discuss in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation.}, address = {New York, NY, USA}, author = {Sebastiani, Fabrizio}, citeulike-article-id = {83774}, citeulike-linkout-0 = {http://portal.acm.org/citation.cfm?id=505282.505283}, citeulike-linkout-1 = {http://dx.doi.org/10.1145/505282.505283}, doi = {10.1145/505282.505283}, issn = {0360-0300}, journal = {ACM Comput. Surv.}, keywords = {classification, machine-learning}, month = {March}, number = {1}, pages = {1--47}, posted-at = {2008-05-06 08:29:43}, priority = {5}, publisher = {ACM}, title = {Machine learning in automated text categorization}, url = {http://dx.doi.org/10.1145/505282.505283}, volume = {34}, year = {2002} }

TY - JOUR ID - citeulike:83774 L3 - citeulike-article-id:83774 N2 - The automated categorization (or classification) of texts into predefined categories has witnessed a booming interest in the last 10 years, due to the increased availability of documents in digital form and the ensuing need to organize them. In the research community the dominant approach to this problem is based on machine learning techniques: a general inductive process automatically builds a classifier by learning, from a set of preclassified documents, the characteristics of the categories. The advantages of this approach over the knowledge engineering approach (consisting in the manual definition of a classifier by domain experts) are a very good effectiveness, considerable savings in terms of expert labor power, and straightforward portability to different domains. This survey discusses the main approaches to text categorization that fall within the machine learning paradigm. We will discuss in detail issues pertaining to three different problems, namely, document representation, classifier construction, and classifier evaluation. IS - 1 JF - ACM Comput. Surv. SN - 0360-0300 AD - New York, NY, USA EP - 47 TI - Machine learning in automated text categorization PB - ACM VL - 34 SP - 1 KW - classification KW - machine-learning AU - Sebastiani, Fabrizio PY - 2002/03// UR - http://dx.doi.org/10.1145/505282.505283 ER -