Acquiring causal knowledge from text using the connective marker tame
ACM Transactions on Asian Language Information Processing (TALIP)
Optimizing web search using social annotations
Proceedings of the 16th international conference on World Wide Web
ACM Transactions on Asian Language Information Processing (TALIP)
Investigating the characteristics of causal relations in Japanese text
CorpusAnno '05 Proceedings of the Workshop on Frontiers in Corpus Annotations II: Pie in the Sky
Information Processing and Management: an International Journal
An incremental method for causal network construction
WAIM'10 Proceedings of the 11th international conference on Web-age information management
Lexico-syntactic causal pattern text mining
ICCOMP'10 Proceedings of the 14th WSEAS international conference on Computers: part of the 14th WSEAS CSCC multiconference - Volume II
Hi-index | 0.00 |
In this paper, we propose a node-first causal extraction method for trend analysis. Recently, it has become more important for business leaders, politicians and academics to understand broader and longer environmental trends because of the need to develop better strategies for dealing with current and future issues. Trend analysis is often utilized to identify key factors in political, economical, social and technological trends. We propose a web mining framework that can extract a causal network of key factors underlying macro trends related to a user's interest. The main idea can be described as "node-first" approach, which recursively identifies key factors relevant to a user's query, then verifies causal relations between key factors. As the result of experiment, we demonstrate high precision of key factor identification (P@100 = 0.76) and causality verifications (F-value = 0.74).