Author Identification Using Semi-supervised Learning - Notebook for PAN at CLEF 2011

Author identification models fall into two major categories according to the way they handle the training texts: profile-based models produce one representation per author while instance-based models produce one representation per text. In this paper, we propose an approach that combines two well-known representatives of these categories, namely the Common nGrams method and a Support Vector Machine classifier based on character ngrams. The outputs of these classifiers are combined to enrich the training set with additional documents in a repetitive semi-supervised procedure inspired by the co-training algorithm. The evaluation results on closed-set author identification are encouraging, especially when the set of candidate authors is large.

• Type: Journal
• Year: 2011
• Where: CLEF
• Authors: Ioannis Kourtis, Efstathios Stamatatos
• Keywords: Author Identification, Classifiers, CLEF 2011, Information Technology, Support Vector Machine