Search

Virtual Learning Environments (VLEs) feature rich textual data which lend itself naturally to the identification and monitoring of aspects of students’ interactions. While reducing attrition and improving performance remain the primary objectives of learning analytics, we contend that student contributed text can be used to learn about emotions and other extra-rational features. This would help provide a response to the recent cries for help from the sector, seeking a system looking to address the worrying mental health crisis trends. This paper addresses these issues by discussing the necessary mechanisms within a conceptual framework which would sit in a VLE and capture emotional state changes in the students’ interaction style or tone. For such a framework, the aim would be to help educators to carry out timely interventions when a potential cause of distress is identified. Experimental results on available datasets from education and psychology serve as a feasibility study for these tasks, and offer a perspective on the potential of the approach.

Ontology reuse is a complex process that requires the support of methodologies and tools to minimise errors and to keep the ontologies consistent and coherent. Although the vast majority of ontology engineering methodologies include a reuse phase, and reuse has been investigated for different tasks and purposes (e.g.ontology integration), this body of work does not seem to translate into practice, neither in the form of strict criteria for reuse, nor as a set of community proposed guidelines. In this paper, we report the salient results from a study aimed at ontology developers and practitioners, whose objective is to gain an insight into the gap between the theory and the practice of ontology reuse. Thefocus of our study is to gain practitioners' views on i) their preferred reuse approaches; ii) the types of ontologies they tend to reuse (e.g. specific domain ontologies or upper-level ontologies)iii) what reporting information they deem useful when deciding which ontology to reuse; iv) what are the main reasons deterring them from reusing an ontology. Our findings confirm and extend established results from the literature, but in addition, the study provides a fresh view on the practice of reuse with an explicit focus on highly experienced developers and moderately experienced ones. The study corroborates the need for a comprehensive set of recommendations, that are widely accepted by the community, and are possibly implemented in development tools.

Assessment quality and validity is heavily reliant on the quality of items included in an assessment or test. Difficulty is an essential factor that can determine items and tests’ overall quality. Therefore, item difficulty prediction is extremely important in any pedagogical learning environment. Data-driven approaches to item difficulty prediction are gaining more and more prominence, as demonstrated by the recent literature. In this paper, we provide a systematic review of data-driven approaches to item difficulty prediction. Of the 148 papers that were identified that cover item difficulty prediction, 38 papers were selected for the final analysis. A classification of the different approaches used to predict item difficulty is presented, together with the current practices for item difficulty prediction with respect to the learning algorithms used, and the most influential difficulty features that were investigated.

Financial analysts constitute an important element of financial decision-making in stock exchanges throughout the world. By leveraging on argumentative reasoning, we develop a method to predict financial analysts' recommendations in earnings conference calls (ECCs), an important type of financial communication. We elaborate an analysis to select those reliable arguments in the Questions Answers (QA) part of ECCs that analysts evaluate to estimate their recommendation. The observation date of stock recommendation update may variate during the next quarter: it can be either the day after the ECC or it can take weeks. Our objective is to anticipate analysts' recommendations by predicting their judgment with the help of abstract argumentation. In this paper, we devise our approach to the analysis of ECCs, by designing a general processing framework which combines natural language processing along with abstract argumentation evaluation techniques to produce a final scoring function, representing the analysts' prediction about the company's trend. Then, we evaluate the performance of our approach by specifying a strategy to predict analysts recommendations starting from the evaluation of the argumentation graph properly instantiated from an ECC transcript. We also provide the experimental setting in which we perform the predictions of recommendations as a machine learning classification task. The method is shown to outperform approaches based only on sentiment analysis.

This paper proposes a general mental model for an agent capable to engage in rhetorical argumentation. The model is grounded in works in the philosophy of mind, and is inspired by research in contextual reasoning. The issues that are dealt with in this paper are mainly ontological, as we leave aside the problem of knowledge representation and reasoning, and concentrate on the conceptualisation of the model.

Digital behavior intervention is a growing area of research which investigates how interactive systems can encourage and support people to change their behavior. Personalization plays an important role in this, as the most effective persuasive and motivational strategies are likely to depend on user characteristics such as the user’s personality, affective state, existing attitudes, behaviors, knowledge, and goals. Example application areas include healthcare (e.g., encouraging people to eatmore healthily and exercise more), education (e.g., motivating learners to study more), environment (e.g., encouraging people to use less energy and more public transport), and collaborative content development (e.g., incentivizing people to annotate resources). The idea that a system may be used to motivate people on the basis of a user model is certainly not novel. As early as the 1980s, intelligent tutoring systems encouraged students to learn by means of tailored feedback and hints (Sleeman and Brown 1982), and in the 90s patient education systems attempted to address compliance to a medical regimen by means of information and personalized advice (De Carolis et al. 1996) or encouraged people to adopt healthier lifestyles (Reiter et al. 2003). However, it is only recently that a number of seemingly non correlated, extensive research efforts