Hybrid Filter-Wrapper Feature Selection Method for Sentiment Classification
Hybrid Filter-Wrapper Feature Selection Method for Sentiment Classification
复制标题
DOI：
10.1007/s13369-019-04064-6
复制
发表时间：
2019-11-01
影响因子：
2.9
通讯作者：
Doja, Mohammad Najmud
中科院分区：
文献类型：
--
作者：
Ansari, Gunjan;Ahmad, Tanvir;Doja, Mohammad Najmud
特征选择是情感分类领域的最新挑战。在领域中采用了基于过滤器和包装器的特征选择方法，减少了特征集的规模，提高了分类器的准确率。本文提出了一种滤波法和包装法相结合的特征选择方法。首先使用计算快速的基于等级的FS方法从原始特征集中选择特征子集。所选功能使用两种包装器方法进一步细化。在第一种方法中，采用递归特征消除法选择最优特征集；在第二种方法中，采用基于二进制粒子群优化的进化方法来确定特征子集。在情感分析领域使用的五个不同领域数据集上对这两种技术进行了比较。我们使用简单而高效的最大似然算法(朴素贝叶斯、支持向量机和Logistic回归)来评估混合FS技术的性能。最后，我们通过将我们的结果与最先进的方法进行比较，评估了所提出的混合FS技术的性能。实验结果表明，该方法能够以较少的特征数获得较高的准确率。
The feature selection (FS) has been the latest challenge in the area of sentiment classification. The filter- and wrapper-based feature selection methods are applied in the domain to reduce feature set size and increase accuracy of the classifiers. In this paper, a hybrid of filter and wrapper method for selecting relevant features is proposed. The feature subset is first selected from the original feature set using computationally fast rank-based FS methods. The selected features are further refined using two wrapper approaches. In the first approach, recursive feature elimination is applied to select optimal feature set, and in the second approach, evolutionary method based on binary particle swarm optimization is applied for finalization of feature subset. The comparison between the two proposed techniques is conducted on five different domain datasets used in the area of sentiment analysis. We used simple and efficient ML algorithms (Naive Bayes, support vector machine and logistic regression) to evaluate the performance of the hybrid FS techniques. Finally, we assessed the performance of the proposed hybrid FS technique by comparing our results with the state-of-the-art methods. The results reveal that the proposed method is able to give better accuracy with fewer number of features.