A comparison of event models for naive bayes text classification

By Andrew McCallum, Kamal Nigam. 1998

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

FastText.zip: Compressing text classification models (2016, methodology): “Linear classiﬁers often obtain state-of-the-art performance while being scalable (Agarwal et al., 2014; Joachims, 1998; Joulin et al., 2016; McCallum & Nigam, 1998).”
Discrete Distribution Estimation under Local Privacy (2016, background): “We focus on discrete distribution estimation because it enables a variety of useful capabilities, including usage statistics breakdowns and count-based machine learning models, e.g. naive Bayes (McCallum et al., 1998).”
Is Feature Selection Secure against Training Data Poisoning? (2015, background): “Similarly, text classiﬁers for spam ﬁltering rely on the construction of a large dictionary to identify words that are mostly discriminant of spam and legitimate emails (Sahami et al., 1998; McCallum & Nigam, 1998; Graham, 2002; Robinson, 2003).”
Text Categorization as a Graph Classification Problem (2015, methodology): “In text categorization, standard baseline classiﬁers include k -nearest neighbors (kNN) (Larkey and Croft, 1996), Naive Bayes (NB) (McCallum and Nigam, 1998) and linear Support Vector Machines (SVM) (Joachims, 1998) with the latter performing the best on n-gram features as veriﬁed in our…”
Thumbs up? Sentiment Classification using Machine Learning Techniques (2002, critical): “See Nigam et al. (1999) for additional motivation.”
Graph Embedding Techniques, Applications, and Performance: A Survey (2017, methodology): “Feature-based models [11], [12], [56] generate features for nodes based on their neighborhood and local network statistics and then apply a classifier like Logistic Regression [57] and Naive Bayes [58] to predict the labels.”
Building text classifiers using positive and unlabeled examples (2003, methodology): “In devising the NB classifier, two assumptions are made [22][26]: (1) words are independent given a class, and (2) text documents are generated by a mixture model and there is a one-to-one mapping between mixture components and classes (which means that each class contains only documents of one topi”
Model-Based Multiple Instance Learning (2017, unknown): “F”
A Probabilistic Framework for the Hierarchic Organisation and Classification of Document Collections (2002, methodology): “The mixtures are based on both standard multinomial event models (McCallum and Nigam, 1998) and probabilistic latent semantic analysers (PLSA) (Hofmann, 1999; Vinokourov and Girolami, 2000).”
Investigating the Working of Text Classifiers (2018, methodology): “In contrast, a simple discriminative classifier such as Logisitic Regression performs significantly better than Naïve Bayes on the random version for all the datasets.”
Text Classification from Labeled and Unlabeled Documents using EM (2000, methodology): “Empirical comparisons show that the multinomial formulation yields classifiers with consistently higher accuracy (McCallum & Nigam, 1998).”
Learning joint query interpretation and response ranking (2012, methodology): “Because lemmas are very short, words are rarely repeated, so we can use the multivariate Bernoulli [23] distribution derived from lemma `:”
Modeling word burstiness using the Dirichlet distribution (2005, background): “( 2003 ) and McCallum and Nigam ( 1998 ) .”
Supervised and Traditional Term Weighting Methods for Automatic Text Categorization (2009, unknown): “McCallum and Nigam [12] used a multinomial event model for Naive Bayes text classification that can relax the constraint that document vectors should be binary valued.”
Eliminating noisy information in Web pages for data mining (2003, methodology): “For classification, we use the Naive Bayesian classifier (NB), which has been shown to perform very well in practice by many researchers [14][ 15 ].”
It's the way you check-in: identifying users in location-based social networks (2014, methodology): “We also develop an identification method based on a multinomial naïve Bayes model, widely used for several classification tasks, such as text classification [25].”