Understanding the multifaced factors that drive Bitcoin's price movements has been a challenging task. While past research has primarily investigated the correlation between macroeconomic indices and market prices, there is growing recognition that sentiment expressed on platforms like Twitter can also influence market behavior, particularly in the short term. Therefore, this study develops a price prediction system using sentiment analysis and deep learning techniques to explore the influence of both macroeconomic and sentiment indicators on the dynamics of Bitcoin's price. The results show that incorporating sentiment features can enhance the accuracy of the Bitcoin price prediction, particularly for the 1-week and 1-month time windows. However, when considering the longer time window, macroeconomic indices demonstrate superior performance.

A Chinese character embedded in different compound words may carry different meanings. In this paper, we aim at semantical clustering of a given family of morphologically related Chinese words. In Experiment 1, we employed linguistic features at the word, syntactic, semantic, and contextual levels in aggregated computational linguistics methods to handle the clustering task. In Experiment 2, we recruited adults and children to perform the clustering task. Experimental results indicate that our computational model achieved a similar level of performance as children.