Non_Linear Approach for Automatic Extraction of Field Association Words

Field association (FA) terms are used to identify the subject of text by extracting specific words in that text. This paper uses FA terms to discuss the effect of time change on specific terms by calculating the frequency of terms that are related to the domain or field of the document. Moreover, in this work, a new approach for the automatic valuation of the stabilization classes using a non-linear approach is used. From this study, we have observed that this new non-linear approach improves the performance of the decision tree when compared to the linear approaches. The corpus used in this approach for validation has 1,356 files, and it is about 7.49 MB size. When compared with traditional approaches such as the linear approaches, we concluded about this new nonleaner approach enhanced the F-measure for increment, steady, decrement classes by 7.7%, 3.1%, 2.2%, respectively.