出版社：SISSA, Scuola Internazionale Superiore di Studi Avanzati
摘要：Encouraged by the feasibility demonstration that a relatively low-cost grid environment can
speed up the processing of continuous text streams of financial news in English, we have
attempted to replicate our methods for automatic sentiment analysis in two major languages of
the world – Arabic and Chinese. We show that our local grammar approach, developed on an
archive of English (Indo-European language) texts, works equally on the typologically different
Chinese (Sino-Asiatic) and Arabic (Semitic) languages.
