Information extraction and data mining from Chinese financial news.

Ng Anny.Thesis (M.Phil.)--Chinese University of Hong Kong, 2002.Includes bibliographical references (leaves 139-142).Abstracts in English and Chinese.Chapter 1 --- Introduction --- p.1Chapter 1.1 --- Problem Definition --- p.2Chapter 1.2 --- Thesis Organization --- p.3Chapter 2 --- Chinese Text Summarization Using Genetic Algorithm --- p.4Chapter 2.1 --- Introduction --- p.4Chapter 2.2 --- Related Work --- p.6Chapter 2.3 --- Genetic Algorithm Approach --- p.10Chapter 2.3.1 --- Fitness Function --- p.11Chapter 2.3.2 --- Genetic operators --- p.14Chapter 2.4 --- Implementation Details --- p.15Chapter 2.5 --- Experimental results --- p.19Chapter 2.6 --- Limitations and Future Work --- p.24Chapter 2.7 --- Conclusion --- p.26Chapter 3 --- Event Extraction from Chinese Financial News --- p.27Chapter 3.1 --- Introduction --- p.28Chapter 3.2 --- Method --- p.29Chapter 3.2.1 --- Data Set Preparation --- p.29Chapter 3.2.2 --- Positive Word --- p.30Chapter 3.2.3 --- Negative Word --- p.31Chapter 3.2.4 --- Window --- p.31Chapter 3.2.5 --- Event Extraction --- p.32Chapter 3.3 --- System Overview --- p.33Chapter 3.4 --- Implementation --- p.33Chapter 3.4.1 --- Event Type and Positive Word --- p.34Chapter 3.4.2 --- Company Name --- p.34Chapter 3.4.3 --- Negative Word --- p.36Chapter 3.4.4 --- Event Extraction --- p.37Chapter 3.5 --- Stock Database --- p.38Chapter 3.5.1 --- Stock Movements --- p.39Chapter 3.5.2 --- Implementation --- p.39Chapter 3.5.3 --- Stock Database Transformation --- p.39Chapter 3.6 --- Performance Evaluation --- p.40Chapter 3.6.1 --- Performance measures --- p.40Chapter 3.6.2 --- Evaluation --- p.41Chapter 3.7 --- Conclusion --- p.45Chapter 4 --- Mining Frequent Episodes --- p.46Chapter 4.1 --- Introduction --- p.46Chapter 4.1.1 --- Definitions --- p.48Chapter 4.2 --- Related Work --- p.50Chapter 4.3 --- Double-Part Event Tree for the database --- p.56Chapter 4.3.1 --- Complexity of tree construction --- p.62Chapter 4.4 --- Mining Frequent Episodes with the DE-tree --- p.63Chapter 4.4.1 --- Conditional Event Trees --- p.66Chapter 4.4.2 --- Single Path Conditional Event Tree --- p.67Chapter 4.4.3 --- Complexity of Mining Frequent Episodes with DE-Tree --- p.67Chapter 4.4.4 --- An Example --- p.68Chapter 4.4.5 --- Completeness of finding frequent episodes --- p.71Chapter 4.5 --- Implementation of DE-Tree --- p.71Chapter 4.6 --- Method 2: Node-List Event Tree --- p.76Chapter 4.6.1 --- Tree construction --- p.79Chapter 4.6.2 --- Order of Position Bits --- p.83Chapter 4.7 --- Implementation of NE-tree construction --- p.84Chapter 4.7.1 --- Complexity of NE-Tree Construction --- p.86Chapter 4.8 --- Mining Frequent Episodes with NE-tree --- p.87Chapter 4.8.1 --- Conditional NE-Tree --- p.87Chapter 4.8.2 --- Single Path Conditional NE-Tree --- p.88Chapter 4.8.3 --- Complexity of Mining Frequent Episodes with NE-Tree --- p.89Chapter 4.8.4 --- An Example --- p.89Chapter 4.9 --- Performance evaluation --- p.91Chapter 4.9.1 --- Synthetic data --- p.91Chapter 4.9.2 --- Real data --- p.99Chapter 4.10 --- Conclusion --- p.103Chapter 5 --- Mining N-most Interesting Episodes --- p.104Chapter 5.1 --- Introduction --- p.105Chapter 5.2 --- Method --- p.106Chapter 5.2.1 --- Threshold Improvement --- p.108Chapter 5.2.2 --- Pseudocode --- p.112Chapter 5.3 --- Experimental Results --- p.112Chapter 5.3.1 --- Synthetic Data --- p.113Chapter 5.3.2 --- Real Data --- p.119Chapter 5.4 --- Conclusion --- p.121Chapter 6 --- Mining Frequent Episodes with Event Constraints --- p.122Chapter 6.1 --- Introduction --- p.122Chapter 6.2 --- Method --- p.123Chapter 6.3 --- Experimental Results --- p.125Chapter 6.3.1 --- Synthetic Data --- p.126Chapter 6.3.2 --- Real Data --- p.129Chapter 6.4 --- Conclusion --- p.131Chapter 7 --- Conclusion --- p.133Chapter A --- Test Cases --- p.135Chapter A.1 --- Text 1 --- p.135Chapter A.2 --- Text 2 --- p.137Bibliography --- p.13