Abstract Web service composition is about maximizing the benefits of different Web services by combining a certain number of Web services to deliver a fully end-to-end service. This paper presents a systematic review of the two major trends of Web service compositions: top-down composition and bottom-up composition. The top-down composition starts with a well defined goal and search criteria. On the... Web service composition is about maximizing the benefits of different Web services by combining a certain number of Web services to deliver a fully end-to-end service. This paper presents a systematic review of the two major trends of Web service compositions: top-down composition and bottom-up composition. The top-down composition starts with a well defined goal and search criteria. On the other hand, the goal and search criteria in the bottom-up composition are not well defined. The bottom-up composition is often called Web service mining. Web service mining is a new trend that aims at discovering useful and interesting compositions of existing Web services. Read More Read Less

Abstract Mental health is considered as one of today’s world’s most prominent plagues. Therefore, our work aims to use the potential of social media platforms to solve one of mental health’s biggest issues, which is depression identification. We propose a new deep learning model that we train on a depression-dedicated dataset in order to detect such mental illness from an individual’s tweets. Our main... Mental health is considered as one of today’s world’s most prominent plagues. Therefore, our work aims to use the potential of social media platforms to solve one of mental health’s biggest issues, which is depression identification. We propose a new deep learning model that we train on a depression-dedicated dataset in order to detect such mental illness from an individual’s tweets. Our main contributions lie in the three following points: (1) We trained our own word embeddings using a depression-dedicated dataset. (2) We combined a Convolutional Neural Networks model with the Message-level Sentiment Analysis model in order to improve the feature extraction process and enhance the model’s performance. (3) We analyzed through different experiments the performance of three deep learning models in order to provide more perspectives and insights for depression researches. Our model achieved a 99 % accuracy, outperforming any statistical or deep learning models found in literature currently. Read More Read Less