Using Differential Evolution for Fine Tuning Naïve Bayesian Classifiers and its Application for Text Classification
, Diab Diab, Khalil El Hindi . 2017
The Naive Bayes (NB) learning algorithm is simple and effective in many domains including text classification. However, its performance depends on the accuracy of the estimated conditional probability terms. Sometimes these terms are hard to be accurately estimated especially when the training data is scarce. This work transforms the probability estimation problem into an optimization problem, and exploits three metaheuristic approaches to solve it. The approaches are Genetic Algorithms (GA), Simulated Annealing (SA), and Differential Evolution (DE). We create an initial population by manipulating the solution generated by a method used for fine tuning the NB. We propose three different methods to select the final solution. We also propose a novel DE algorithm that uses a multi-parent mutation operation (NB-MPDE). We evaluate and compare the proposed methods with NB and Fine-Tuning Naïve Bayesian (FTNB) algorithm, using 53 UCI benchmark data sets. We also evaluate the NB-MPDE for text-classification using 18 text-classification data sets and compare its results with the results of FTNB, classical NB, Bernoulli NB (BNB) and Multinomial NB (MNB). The experimental results show that using DE in general and the proposed multi-parent DE algorithm in particular achieve significant improvement over FTNB, classical NB. Our results also show that DE outperform the two other metaheuristic approaches (GA and SA) for many data sets. The text-classification results also indicate that the proposed multi-parent DE method achieves significant improvement, compared with MNB, and BNB methods, for many data sets.
The problem of dealing with noisy data in neural network-based models has been receiving more attention by researchers with the aim of mitigating possible consequences on learning.
Text classification has many applications in text processing and information retrieval. Instance-based learning (IBL) is among the top-performing text classification methods. However, its…
Analyzing social data as a participatory sensing system (PSS) provides a deep understanding of city dynamics, such as people’s mobility patterns, social patterns, and events detection. In a PSS,…