A novel field learning algorithm for dual imbalance text classification

Fish-net algorithm is a novel field learning algorithm which derives classification rules by looking at the range of values of each attribute instead of the individual point values. In this paper, we present a Feature Selection Fish-net learning algorithm to solve the Dual Imbalance problem on text classification. Dual imbalance includes the instance imbalance and feature imbalance. The instance imbalance is caused by the unevenly distributed classes and feature imbalance is due to the different document length. The proposed approach consists of two phases: (1) select a feature subset which consists of the features that are more supportive to difficult minority class; (2) construct classification rules based on the original Fish-net algorithm. Our experimental results on Reuters21578 show that the proposed approach achieves better balanced accuracy rate on both majority and minority class than Naive Bayes MultiNomial and SVM.

An institutional study of the influence of ‘onlineness’ on student evaluation of teaching in a dual mode Australian university

Student evaluation of teaching (SET) is now commonplace in many universities internationally. The most common criticism of SET practices is that they are influenced by a number of non-teaching-related factors. More recently, there has been dramatic growth in online education internationally, but only limited research on the use of SET to evaluate online teaching. This paper presents a large-scale and detailed investigation, using the institutional SET data from an Australian university with a significant offering of wholly online units, and whose institutional SET instrument contains items relating to student perceptions of online technologies in teaching and learning. The relationship between educational technology and SET is not neutral. The mean ratings for the ‗online‘ aspects of SET are influenced by factors in the wider teaching and learning environment, and the overall perception of teaching quality is influenced by whether a unit is offered in wholly online mode or not.

Supervised subspace learning with multi-class Lagrangian SVM on the Grassmann manifold

Learning robust subspaces to maximize class discrimination is challenging, and most current works consider a weak connection between dimensionality reduction and classifier design. We propose an alternate framework wherein these two steps are combined in a joint formulation to exploit the direct connection between dimensionality reduction and classification. Specifically, we learn an optimal subspace on the Grassmann manifold jointly minimizing the classification error of an SVM classifier. We minimize the regularized empirical risk over both the hypothesis space of functions that underlies this new generalized multi-class Lagrangian SVM and the Grassmann manifold such that a linear projection is to be found. We propose an iterative algorithm to meet the dual goal of optimizing both the classifier and projection. Extensive numerical studies on challenging datasets show robust performance of the proposed scheme over other alternatives in contexts wherein limited training data is used, verifying the advantage of the joint formulation.