Due to the rapid development of Internet-based applications such as social media, sentiment analysis has become one of the most widely used research areas of natural language processing and an important tool for extracting opinions from texts. Because a huge number of comments and reviews are generated today through social media, and these comments are very significant. However, manually analyzing and summarizing them requires a lot of time and money. Therefore, sentiment analysis has entered the field to organize and analyze them by creating an automated system. In recent years, the use of deep learning in sentiment analysis has shown powerful results. However, creating a model alone may not provide the best predictions and lead to errors such as bias and high variance. To reduce these errors and improve the efficiency of model predictions, combining several models known as ensemble learning may provide better results. Therefore, the main purpose of this article is to create a model based on ensemble learning using Several convolutional neural networks and majority voting classifiers to enhance sentiment analysis in Persian reviews. The proposed model was evaluated on two datasets of reviews of electronic products and movies by 5-fold and 10-fold cross-validation. The results indicate that this new approach increases the efficiency of the sentiment analysis model in Persian language.
The Private Aggregation of Teacher Ensembles (PATE) framework is one of the most promising recent approaches in differentially private learning. Existing theoretical analysis shows that PATE consistently learns any VC-classes in the realizable setting, but falls short in explaining its success in more general cases where the error rate of the optimal classifier is bounded away from zero. We fill in this gap by introducing the Tsybakov Noise Condition (TNC) and establish stronger and more interpretable learning bounds. These bounds provide new insights into when PATE works and improve over existing results even in the narrower realizable setting. We also investigate the compelling idea of using active learning for saving privacy budget, and empirical studies show the effectiveness of this new idea. The novel components in the proofs include a more refined analysis of the majority voting classifier - which could be of independent interest - and an observation that the synthetic "student" learning problem is nearly realizable by construction under the Tsybakov noise condition.
The aim of this paper is to propose an application of mutual information-based ensemble methods to the analysis and classification of heart beats associated with different types of Arrhythmia. Models of multilayer perceptrons, support vector machines, and radial basis function neural networks were trained and tested using the MIT-BIH arrhythmia database. This research brings a focus to an ensemble method that, to our knowledge, is a novel application in the area of ECG Arrhythmia detection. The proposed classifier ensemble method showed improved performance, relative to either majority voting classifier integration or to individual classifier performance. The overall ensemble accuracy was 98.25%.