Differential Reward Mechanism Based Online Learning Algorithm for URL-based Topic Classification

In this paper, we propose a differential reward based online learning algorithm for classifying web pages into predefined topics based on minimal text available in the URLs. It is then compared with two baseline methods, i.e., Support Vector Machine (SVM) and a state-of-the-art Reinforcement Learning Algorithm using recall, precision and F-measure scores. We conducted experiments on large scale Open Directory Project dataset and demonstrate an improvement of 0.08-0.10 in terms of macro-averaged F-measure over the baseline algorithms in different settings where there is an imbalance between the training and test sets.