With the development of Internet and big data, it is more convenient for investors to share opinions or have a discuss with others via the web, which creates massive unstructured data. These data reflect investors' emotions and their investment intentions, and it will further affect the movement of the stock market. Although researchers have been attempted to use sentiment information to predict the market, the sentiment features used are driven by outdated emotion extraction systems. In this article, we proposed a new sentiment analysis system with deep neural networks for stock comments and applied estimated sentiment information to the stock movement forecasting. The empirical results showed that our deep sentiment classification method achieved a 9% improvement over the logistic regression algorithm, and provided an accurate sentiment extractor for the next predicting step. In addition our new hybrid features that mix stock trading data and sentiment information achieved 1.25% improvement among 150 Chinese stocks in the testing dataset. For American stocks, the sentiment information would reduced the predicting results. We found that emotion features extracted from comments are indeed effective for stocks with a higher price to book value and a lower beta risk value in China. K E Y W O R D S deep learning, financial comments, sentiment analysis, stock movement prediction 1 INTRODUCTION Sentiment analysis is one of the most important research directions in artificial intelligence and has been applied in many fields, such as stock predicting, political science, and health science. 1,2 Among these applications, stock movement prediction has wide commercial potential and market prospects. However, the fluctuation of the stock market is closely related to the development of the national economy, and the market itself is also a complex nonlinear dynamic system that is susceptible to many factors. 3 Due to the complexity of market rules, the volatility of prices and the diversity of factors also affect the market. Generally, there are approximately two basic methods for stock prediction. The first is a kind of qualitative analysis method in which the effectiveness of forecasts depends largely on the capabilities and experience of experts. The other is the technical analysis method, which contains statistical methods and a data mining algorithm. According to academic studies and practical applications, methods relying solely on expert strategic analysis are insufficient to improve the prediction accuracy. Therefore, researchers have begun to pay more attention to the multisource heterogeneous data and to introduce deep learning methods into this field. In recent decades, the rapid development of the mobile Internet and online applications has brought the whole world into the big data era. It is more convenient for investors to share their opinions or have a discussion with others by pushing messages. People are also likely to browse the web before making investment decisions. All these activities provide multisource ...

Precipitation nowcasting is extremely important in disaster prevention and mitigation, and can improve the quality of meteorological forecasts. In recent years, deep learning-based spatiotemporal sequence prediction models have been widely used in precipitation nowcasting, obtaining better prediction results than numerical weather prediction models and traditional radar echo extrapolation results. Because existing deep learning models rarely consider the inherent interactions between the model input data and the previous output, model prediction results do not sufficiently meet the actual forecast requirement. We propose a Modified Convolutional Gated Recurrent Unit (M-ConvGRU) model that performs convolution operations on the input data and previous output of a GRU network. Moreover, this adopts an encoder–forecaster structure to better capture the characteristics of spatiotemporal correlation in radar echo maps. The results of multiple experiments demonstrate the effectiveness of the proposed model. The balanced mean absolute error (B-MAE) and balanced mean squared error (B-MSE) of M-ConvGRU are slightly lower than Convolutional Long Short-Term Memory (ConvLSTM), but the mean absolute error (MAE) and mean squared error (MSE) of M-ConvGRU are 6.29% and 10.25% lower than ConvLSTM, and the prediction accuracy and prediction performance for strong echo regions were also improved.

Self-similar growth and fractality are important properties found in many real-world networks, which could guide the modeling of network evolution and the anticipation of new links. However, in technology-convergence networks, such characteristics have not yet received much attention. This study provides empirical evidence for self-similar growth and fractality of the technology-convergence network in the field of intelligent transportation systems. This study further investigates the implications of such fractal properties for link prediction via partial information decomposition. It is discovered that two different scales of the network (i.e., the micro-scale structure measured by local similarity indices and the scaled-down structure measured by community-based indices) have significant synergistic effects on link prediction. Finally, we design a synergistic link prediction (SLP) approach which enhances local similarity indices by considering the probability of link existence conditional on the joint distribution of two scales. Experimental results show that SLP outperforms the benchmark local similarity indices in most cases, which could further validate the existence and usefulness of the synergistic effect between two scales on link prediction.