Sentiment classification is an interesting and crucial research topic in the field of natural language processing (NLP). Data-driven methods, including machine learning and deep learning techniques, provide one direct and effective solution to solve the sentiment classification problem. However, the classification performance declines when the input includes review comments for multiple tasks. The most appropriate way of constructing a sentiment classification model under multi-tasking circumstances remains questionable in the related field. In this study, aiming at the multi-tasking sentiment classification problem, we propose a multi-task learning model based on a multi-scale convolutional neural network (CNN) and long short term memory (LSTM) for multi-task multi-scale sentiment classification (MTL-MSCNN-LSTM). The model comprehensively utilizes and properly handles global features and local features of different scales of text to model and represent sentences. The multi-task learning framework improves the encoder quality, simultaneously improving the results of emotion classification. Six different types of commodity review datasets were employed in the experiment. Using accuracy and F1-score as the metrics to evaluate the performance of the proposed model, comparing with methods such as single-task learning and LSTM encoder, the proposed MTL-MSCNN-LSTM model outperforms most of the existing methods.INDEX TERMS Sentiment classification, multi-task learning model, long short term memory, multi-scale convolutional neural network.

Recent development of artificial intelligence (AI) technology enquires the traditional power grid system involving additional information and connectivity of all devices for the smooth transit to the next generation of smart grid system. In an AI-enhanced power grid system, each device has its unique name, function, property, location, and many more. A large number of power grid devices can form a complex power grid knowledge graph through serial and parallel connection relationships. The scale of power grid equipment is usually extremely large, with thousands and millions of power devices. Finding the proper way of understanding and operating these devices is difficult. Furthermore, the collection, analysis, and management of power grid equipment become major problems in power grid management. With the development of AI technology, the combination of labeling technology and knowledge graph technology provides a new solution understanding the internal structure of a power grid. As a result, this study focuses on knowledge graph construction techniques for large scale power grid located in China. A semiautomatic knowledge graph construction technology is proposed and applied to the power grid equipment system. Through a series of experimental simulations, we show that the efficiency of daily operations, maintenance, and management of the power grid can be largely improved.

No abstract

No abstract