Document-level sentiment analysis is a challenging task given the large size of the text, which leads to an abundance of words and opinions, at times contradictory, in the same document. This analysis is particularly useful in analyzing press articles and blog posts about a particular product or company, and it requires a high concentration, especially when the topic being discussed is sensitive. Nevertheless, most existing models and techniques are designed to process short text from social networks and collaborative platforms. In this paper, we propose a combination of Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) models, with Doc2vec embedding, suitable for opinion analysis in long texts. The CNN-BiLSTM model is compared with CNN, LSTM, BiLSTM and CNN-LSTM models with Word2vec/Doc2vec embeddings. The Doc2vec with CNN-BiLSTM model was applied on French newspapers articles and outperformed the other models with 90.66% accuracy.

No abstract

No abstract

<div style="’text-align: justify;"><p>Financial time series are volatile, non-stationary and non-linear data that are affected by external economic factors. There is several performant predictive approaches such as univariate ARIMA model and more recently Recurrent Neural Network. The accurate forecasting of budget data is a strategic and challenging task for an optimal management of resources, it requires the use of the most accurate model. We propose a predictive approach that uses and compares the Machine Learning ARIMA model and Deep Learning Recurrent LSTM model. The application and the comparative analysis shows that the LSTM model outperforms the ARIMA model, mainly thanks to the LSTMs ability to learn non-linear relationship from data.</p></div>

No abstract