Arabic Sentiment analysis research field has been progressing in a slow pace compared to English and other languages. In addition to that most of the contributions are based on using supervised machine learning algorithms while comparing the performance of different classifiers with different selected stylistic and syntactic features. In this paper, we presented a novel framework for using the Concept-level sentiment analysis approach which classifies text based on their semantics rather than syntactic features. Moreover, we provided a lexicon dataset of around 69 k unique concepts that covers multi-domain reviews collected from the internet. We also tested the lexicon on a test sample from the dataset it was collected from and obtained an accuracy of 70%. The lexicon has been made publicly available for scientific purposes.

This study predicts future values of energy consumption demand from a novel dataset that includes the energy consumption during COVID-19 lockdown, using up-to-date deep learning algorithms to reduce peer-to-peer energy system losses and congestion. Three learning algorithms, namely Random Forest (RF), Bi-LSTM, and GRU, were used to predict the future values of a building’s energy consumption. The results were compared using the RMSE and MAE evaluation metrics. The results show that predicting the future energy demand with accurate results is achievable, and that Bi-LSTM and GRU perform better, especially when trained as univariate models with only the energy consumption values and no other features included.