We present a new approach to the automated classification of document-level argument stance, a relatively under-researched sub-task of Sentiment Analysis. In place of the noisy online debate data currently used in stance classification research, a corpus of student essays annotated for essay-level stance is constructed for use in a series of classification experiments. A novel set of features designed to capture the stance, stance targets, and topical relationships between the essay prompt and the student's essay is described. Models trained on this feature set showed significant increases in accuracy relative to two high baselines.

The purpose of this track is to bring new insights in the design of the different types of culture- aware systems: Culture-aware intelligent tutoring systems, culture-aware educational systems, cross-cultural decision-making support systems.

Current research suggests that using multiple can improve affect detection accuracy. Combining facial expression and physiological signals is one of the most common approaches in multimodal affect detection. Several methods and devices have been proposed for measuring physiological signals with simplicity and have been used widely in affective computing applications. Out of the various approaches, contact-less sensors which can measure physiological signals remotely are more desirable for everyday use and naturalistic applications. In this paper we proposed a novel fusion model for affect detection, which combines facial expression features and heart rate using a single video recording sensor. To our knowledge this is the first attempt to use physiological sensor remotely for affect detection. Results suggest that fusion of these features (facial expression and heart rate) can improve the accuracy of affect detection systems.

Strategy mining is a new area of research about discovering strategies for decision-making. It is motivated by how similarity is assessed in retrospect in law. In the legal domain, when both case facts and court decisions are present, it is often useful to assess similarity by accounting for both case facts and case outcomes. In this paper, we formulate the strategy mining problem as a clustering problem with the goal of finding clusters that represent disparate conditional dependency of decision labels on other features. Existing clustering algorithms are inappropriate to cluster dependency because they either assume feature independence, such as K-means, or only consider the co-occurrence of features without explicitly modeling the special dependency of the decision label on other features, such as Latent Dirichlet Allocation (LDA). We propose an Expectation Maximization (EM) style unsupervised learning algorithm for dependency clustering. Like EM, our algorithm is grounded in statistical learning theory. It minimizes the empirical risk of decision tree learning. Unlike other clustering algorithms, our algorithm is irrelevant-feature resistant, and its learned clusters modeled by decision trees are strongly interpretable and predictive. We systematically evaluate both the convergence property and solution quality of our algorithm using a common law dataset comprised of actual cases. Experimental results show that our algorithm significantly outperforms K-means and LDA on clustering dependency

We propose a technique of training models for feature extraction using prior expectation of regions of importance in an instrument's timbre. Over a dataset of training examples, we extract significant spectral peaks, calculate their ratio to fundamental frequency, and use $k$-means clustering to identify a set of windows of spectral prominence for each instrument. These windows are used to extract amplitude values from training data to use as features in classification tasks. We test this approach on two databases of 17 instruments, cross evaluate between datasets, and compare with MFCC features.

In general, the goal of the track is to bring together an international group of scientists to present current research, design, and empirical evaluations of their tutoring systems. This track is meant to inform researchers on the recent developments in both the design and evaluation of tutoring sys- tems.

Electronic discovery is an interesting subproblem of information retrieval in which one identifies documents that are potentially relevant to issues and facts of a legal case from an electronically stored document collection (a corpus). In this paper, we consider representing documents in a topic space using the well-known topic models such as latent Dirichlet allocation and latent semantic indexing, and solving the information retrieval problem via finding document similarities in the topic space rather doing it in the corpus vocabulary space. We also develop an iterative SMART ranking and categorization framework including human-in-the-loop to label a set of seed (training) documents and using them to build a semi-supervised binary document classification model based on Support Vector Machines. To improve this model, we propose a method for choosing seed documents from the whole population via an active learning strategy. We report the results of our experiments on a real dataset in the electronic discovery domain.

Adverse Drug Reactions (ADRs) represent troublesome and potentially fatal side effects of medication treatment. To address the burden induced by ADRs, a preventive approach is necessary whereby clinicians are provided with new data-driven decision-support systems to foresee the factors leading to ADRs and plan precautionary activities effectively. We develop a multi-agent system which monitors the factors leading to the onset of ADRs using information found in the patient records in a hospital setting. The system uses a fuzzy rule-based reasoning engine utilising decision rules developed by clinicians. We evaluate the ability of the framework to identify the cause of ADRs from patient records in a case study involving records of metal health patients. Our work is the first preventive agent-based aid tool.

Healthcare informatics focuses on the efficient and effective acquisition, management, and use of information in healthcare.

This paper presents a study where semantic frames are used to mine financial news so as to quantify the impact of news on the stock market. We represent news documents in a novel semantic tree structure and use tree kernel support vector machines to predict the change of stock price. We achieve an efficient computation through linearization of tree kernels. In addition to two binary classification tasks, we rank news items according to their probability to affect change of price using two ranking methods that require vector space features. We evaluate our rankings based on receiver operating characteristic curves and analyze the predictive power of our semantic features. For both learning tasks, the proposed semantic features provide superior results.