Text Mining using Nonnegative Matrix Factorization and Latent Semantic Analysis
This work addresses text clustering challenges for data mining applications, representing an incremental improvement over existing methods like Latent Semantic Analysis.
The authors tackled the problem of clustering text data by proposing a new feature agglomeration method based on Nonnegative Matrix Factorization to create a more suitable feature space, along with a deterministic initialization for spherical K-Means, resulting in either significantly improved clustering performance or maintained performance with better stability compared to existing methods.
Text clustering is arguably one of the most important topics in modern data mining. Nevertheless, text data require tokenization which usually yields a very large and highly sparse term-document matrix, which is usually difficult to process using conventional machine learning algorithms. Methods such as Latent Semantic Analysis have helped mitigate this issue, but are nevertheless not completely stable in practice. As a result, we propose a new feature agglomeration method based on Nonnegative Matrix Factorization, which is employed to separate the terms into groups, and then each group's term vectors are agglomerated into a new feature vector. Together, these feature vectors create a new feature space much more suitable for clustering. In addition, we propose a new deterministic initialization for spherical K-Means, which proves very useful for this specific type of data. In order to evaluate the proposed method, we compare it to some of the latest research done in this field, as well as some of the most practiced methods. In our experiments, we conclude that the proposed method either significantly improves clustering performance, or maintains the performance of other methods, while improving stability in results.