Searching for Significant Word Associations in Text Documents Using Genetic Algorithms
| Authors | |
|---|---|
| Year of publication | 2003 |
| Type | Article in Proceedings |
| Conference | Computional Linguistics and Intelligent Text Processing |
| MU Faculty or unit | |
| Citation | |
| Field | Informatics |
| Keywords | machine learning; text document processing; genetic algorithms; naive Bayes method |
| Description | The paper describes experiments that used Genetic Algorithms for looking for important word assocoations (phrases) in unstructured text documents obtained from the Internet in the area of a specialized medicine branch. Genetic alforithms can evolve sets of word associations with assigned significance weights from the document categorization point of view (relevant and irrelevant documents). The categorization is similarly reliable like the naive Bayes classification based on individual words. In addition, genetic algorithms provided phrases consisting of one, two, and three words. The phrases were quite meaningful from the human point of view. |
| Related projects: |