Supervised term weighting for automated text categorization

By Franca Debole, Fabrizio Sebastiani. ACM Symposium on Applied Computing, 2003

473 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f5595ec1ca0c83c6270b5dbbab600d39325efa74

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Impact of license choice on Open Source Software development activity (2009, methodology): “tfidf is a commonly used technique for term weighing in the field of information retrieval (Grossman & Frieder, 1998), and is also used in text classification (Lavelli, Sebastiani, & Zanoli, 2004; Debole & Sebastiani, 2003 ).”
Supervised and Traditional Term Weighting Methods for Automatic Text Categorization (2009, unknown): “In addition, some researchers have explored the term weighting methods by replacing the idf factor with the metrics that have been used in feature selection, such as information gain, gain ratio, 2 , and Odds Ratio [2], [3].”
Random-Walk Term Weighting for Improved Text Classification (2006, background): “It served as a standard baseline in term weighting studies [4, 13] and proved hard to beat in [7].”
Survey on supervised machine learning techniques for automatic text classification (2019, background): “The supervised word indexing influences on the learning data using weighting a word with respect to how variant its scattering may be in the negative and positive learning cases was proposed by Debole and Sebastiani (2004).”
Random-Walk Term Weighting for Improved Text Classification (2007, background): “It served as a standard baseline in term weighting studies [4, 13] and proved hard to beat in [7].”
An analysis of the relative hardness of Reuters-21578 subsets (2005, methodology): “• As for the term weighting policies, we have used a choice between a standard, cosine-normalized form of tf ∗ idf , or a supervised term weighting policy [8], consisting in replacing the idf component of tf ∗ idf with the function that, in the same experiment, has been previously used for term sele”