An effective ensemble deep learning framework for text classification

Deep-kidney: an effective deep learning framework for chronic kidney disease prediction

Chronic kidney disease (CKD) is one of today's most serious illnesses. Because this disease usually does not manifest itself until the kidney is severely damaged, early detection saves many people's lives. Therefore, the contribution of the current paper is proposing three predictive models to predict CKD possible occurrence within 6 or 12 months before disease existence namely; convolutional neural network (CNN), long short-term memory (LSTM) model, and deep ensemble model. The deep ensemble model fuses three base deep learning classifiers (CNN, LSTM, and LSTM-BLSTM) using majority voting technique. To evaluate the performance of the proposed models, several experiments were conducted on two different public datasets. Among the predictive models and the reached results, the deep ensemble model is superior to all the other models, with an accuracy of 0.993 and 0.992 for the 6-month data and 12-month data predictions, respectively.

An enhanced approach for sentiment analysis based on meta-ensemble deep learning

Sentiment analysis, commonly known as “opinion mining,” aims to identify sentiment polarities in opinion texts. Recent years have seen a significant increase in the acceptance of sentiment analysis by academics, businesses, governments, and several other organizations. Numerous deep-learning efforts have been developed to effectively handle more challenging sentiment analysis problems. However, the main difficulty with deep learning approaches is that they require a lot of experience and hard work to tune the optimal hyperparameters, making it a tedious and time-consuming task. Several recent research efforts have attempted to solve this difficulty by combining the power of ensemble learning and deep learning. Many of these efforts have concentrated on simple ensemble techniques, which have some drawbacks. Therefore, this paper makes the following contributions: First, we propose a meta-ensemble deep learning approach to improve the performance of sentiment analysis. In this approach, we train and fuse baseline deep learning models using three levels of meta-learners. Second, we propose the benchmark dataset “Arabic-Egyptian Corpus 2” as an extension of a previous corpus. The corpus size has been increased by 10,000 annotated tweets written in colloquial Arabic on various topics. Third, we conduct several experiments on six benchmark datasets of sentiment analysis in different languages and dialects to evaluate the performance of the proposed meta-ensemble deep learning approach. The experimental results reveal that the meta-ensemble approach effectively outperforms the baseline deep learning models. Also, the experiments reveal that meta-learning improves performance further when the probability class distributions are used to train the meta-learners.