A Semantic-based Knowledge Acquisition Study on Hong Kong Stock Movement

摘要

Human beings usually analyze daily information with some kinds of semantic-based expectations. This helps to put the analysis in the correct context and perspective, and speed up the processing time for knowledge understanding. This paper proposes a semantic expectation-based knowledge extraction methodology (SEKE) to capitalize on this type of intelligent human behaviour for extracting causation relations from text. In particular, we study the application of a causation semantic template on the Hong Kong Stock market movement (Hang Seng Index) with English financial news from Reuters, South China Morning Post and Hong Kong Standard. With one-month data input and a six-month testing period, the system shows that it can correctly analyse single reason sentences with about 79% precision and 77% recall rates. As the proposed framework is language independent, we expect cross lingual knowledge extraction can also work well with this semantic expectation-based framework.