A classifier system for author recognition using synonym-based features
MICAI'07 Proceedings of the artificial intelligence 6th Mexican international conference on Advances in artificial intelligence
Hi-index | 0.00 |
An approach for identifying the human source of a text by leveraging the significance of synonyms in language is presented. While others have attempted to identify authors in the past, they have focused on purely statistical approaches such as word length distribution, number of distinct words, and language models. We claim that an author's choice of synonyms is idiosyncratic and can be used in determining the identity of an author, which we demonstrate via our algorithm for recognizing authors. This algorithm uses synonym sets from the WordNet lexical database to give more weight to words that have many common synonyms. The results of this method applied to the task of identifying the authors of classic literature show that there is a correlation between an author's synonym choice and the author's identity. With this new author recognition technology, we may now explore new avenues of intelligent and meaningful interaction with users.