Text Mining Using Non-Negative Matrix Factorizations

By V. P. Pauca, Farial Shahnaz, Michael W. Berry, Robert J. Plemmons. SDM, 2004

365 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1aa082404c2bac38b0553456308b66028eb196e6

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

In Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

Citations in the corpus

Improving molecular cancer class discovery through sparse non-negative matrix factorization (2005, neutral): “…with respect to H then reversing the roles of the variables and iterating until convergence was originally proposed by Paatero and Tapper (1994) and subsequently described by others (Hoyer, 2002, 2004; Pauca et al., 2004; Shahnaz et al., 2004 and derived parts-based representation of whole images.”
Text Classification Algorithms: A Survey (2019, methodology): “zation (NMF) Non-negative matrix factorization (NMF) or non-negative matrix approximation has been shown to be a very powerful technique very high dimensional data such as text and sequences analysis [79]. This technique is a promising method for dimension reduction [80]. This section a brief overvi”
Robust nonnegative matrix factorization using L21-norm (2011, background): “, environmetrics [19], chemometrics [25], pattern recognition [14], multimedia data analysis [3], text mining [20] and DNA gene expression analysis [1].”
Manifold Regularized Discriminative Nonnegative Matrix Factorization With Fast Gradient Descent (2011, methodology): “NMF and its extensions have been successfully applied to various tasks in biometrics [26], image processing [46], computer vision [24], and document analysis [35].”
Algorithms and applications for approximate nonnegative matrix factorization (2007, background): “, 2004) and on text mining (Pauca et al., 2004; Shahnaz et al., 2006) will also be continued.”
Document clustering using nonnegative matrix factorization (2006, methodology): “Originally written in MATLAB (see [11] and Figure 1) the proposed NMF algorithm or GD-CLS has been converted to C in this study for scalability.”
A Block Coordinate Descent Method for Regularized Multiconvex Optimization with Applications to Nonnegative Tensor Factorization and Completion (2013, methodology): “It has been widely applied in data mining such as text mining [55] and image mining [41], dimension reduction and clustering [16,73], hyperspectral endmember extraction, as well as spectral data analysis [54].”
Convex and Semi-Nonnegative Matrix Factorizations (2010, background): “This can be derived in a manner similar to Eq. ( 8 ), replacing F by XW ;”
On the Equivalence of Nonnegative Matrix Factorization and Spectral Clustering (2005, background): “A number of researches on further developing NMF computational methodologies [12, 11, 10], and applications on text mining [9, 14, 11].”
Beyond News Contents: The Role of Social Context for Fake News Detection (2017, background): “Recently, it has been shown that nonnegative matrix factorization (NMF) algorithms are very practical and popular to learn document representations [20, 28, 38].”
On the equivalence between Non-negative Matrix Factorization and Probabilistic Latent Semantic Indexing (2008, background): “Later works (Xu et al., 2003; Pauca et al., 2004) show the usefulness of NMF for clustering with experiments ∗ Corresponding author.”
Nonnegative Matrix Factorization Based on Alternating Nonnegativity Constrained Least Squares and Active Set Method (2008, methodology): “Applications of the NMF are numerous including image processing [20], text data mining [30], subsystem identification [18], cancer class discovery [4, 8, 17], etc.”
Nonnegative Matrix Factorization: An Analytical and Interpretive Tool in Computational Biology (2008, background): “Other applications include [20, 21 ] and references therein.”
Exploring Topic Coherence over Many Models and Many Topics (2012, methodology): “2 Traditionally, LSA has used the Singular Value Decomposition, but we also consider Non-negative Matrix Factorization as we’ve seen NMF applied in similar situations (Pauca et al., 2004) Table 1: Top 10 words from several high and low quality topics when ordered by the UCI Coherence Measure.”
Nonnegative matrix factorization for spectral data analysis (2006, background): “A similar constraint may be placed on H via J2(H) to enforce, for example, statistical sparseness [11], which is useful in certain text clustering applications [22].”