Learning to classify text using support vector machines - methods, theory and algorithms

By Thorsten Joachims. The Kluwer International Series in Engineering and Computer Science, 2002

1,633 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/2c4986b03ab15bdad01f808a6786bee01e3800a1

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

Nonextensive Information Theoretic Kernels on Measures (2009, methodology): “We also used the tf-idf (term frequency-inverse document frequency) representation, which penalizes terms that occur in many documents (Joachims, 2002; Baeza-Yates and Ribeiro-Neto, 1999).”
Text Mining Infrastructure in R (2008, background): “s 6= 0 only for substrings that start and end with a white space character gives the “bag of words” kernel (Joachims 2002).”
Kernel Methods for Relation Extraction (2002, methodology): “Kernel methods have enjoyed successful applications for other related problems such as text categorization (Joachims, 2002) and bioinformatics (Furey et al., 2000).”
Co-Training for Cross-Lingual Sentiment Classification (2009, methodology): “In this study, we adopt the widely-used SVM classifier (Joachims, 2002).”
Finding correct protein–protein docking models using ProQDock (2016, positive): “The Support Vector Regression module in the SVM light package (Joachims, 2002) was used to train ProQDock using 5-fold crossvalidation with radial basis function (RBF) kernel.”
Prediction of protein stability changes for single‐site mutations using support vector machines (2005, methodology): “We choose to use SVMs in this study because they are not susceptible to local minima and a general high-quality implementation of SVMs (SVM-light [37, 38]) is publicly available.”
Bilingual Co-Training for Sentiment Classification of Chinese Product Reviews (2011, methodology): “The SVM classiﬁer (Joachims 2002) is adopted as the basic classiﬁer in the proposed approach.”
Effect of Non-linear Deep Architecture in Sequence Labeling (2013, background): “Joachims concluded in his seminal work: “non-linear SVMs do not provide any advantage for text classiﬁcation using the standard kernels” (Joachims, 2004, p. 115).”
Speech emotion recognition (2018, neutral): “Alternatively, bag-of-word approaches are highly popular, where each textual entity in the vocabulary of all meaningful entities—from now on referred to as words—seen during vocabulary construction usually forms a textual feature.(18) Then, the frequency of occurrence of the words is used as actual ”