Paper: Text Classification from Positive and Unlabeled Data using Misclassified Data Correction

ACL ID P13-2084
Title Text Classification from Positive and Unlabeled Data using Misclassified Data Correction
Venue Annual Meeting of the Association of Computational Linguistics
Session Short Paper
Year 2013
Authors

This paper addresses the problem of deal- ing with a collection of labeled training documents, especially annotating negative training documents and presents a method of text classification from positive and un- labeled data. We applied an error detec- tion and correction technique to the re- sults of positive and negative documents classified by the Support Vector Machines (SVM). The results using Reuters docu- ments showed that the method was compa- rable to the current state-of-the-art biased- SVM method as the F-score obtained by our method was 0.627 and biased-SVM was 0.614.