Social Sciences and Humanities > Home > Modeling and Using Context > Issue
The CONTEXT conference series has brought together researchers and practitioners from a wide range of disciplines and industries to present their work related to issues of context, contextual reasoning, and context-awareness to discuss commonalities and diversities in the different disciplinary approaches. It is unique in focusing on context as a subject of study in its own right, and it has become one of the top venues for context-related research.
We argue for the centrality of a pragmatic approach to modeling and using context as a means of unifying research along all axes of context-related research: formal, cognitive, and pragmatic. After briefly discussing the evolution of the research on context in the past 25+ years, we describe the case for a focus on pragmatic research (e.g., applications) going forward. We then give three illustrative examples of pragmatic approaches leading to implementations.
Despite the potential benefits of the context-driven intelligence delivered by Context Management Platforms (CMP), the lack of efficient and effective metrics for measuring Quality and Cost of Context (QoC and CoC) hinders them from uptake and commercialisation. Furthermore, the CMPs might have limited abilities to incorporate efficient QoC drivers and a suboptimal selection of QoC-aware context providers. This paper proposes QoC and CoC metrics and introduces a conceptual architecture to achieve the QoC and CoC awareness in CMPs, aiming to improve their efficiency and consumer experience.
Little has been published on connecting contexts as they are handled in natural systems and in computer science. This article selected some natural contexts and use them as an inspiration to highlight possible improvements on how contexts are designed and used in computer science. The authors found there are beneficial lessons and inspirations which have the potential to bring practical benefits as a result of this process.
The evolution of AI systems from expert systems, knowledge-based systems, joint cognitive systems, intelligent systems, intelligent assistant systems (IASs) and the coming generation of Context-based IASs (CIASs). CIASs require a deep focus on context and its relations with the users, the task at hand, the situation and the environment in which the task is accomplished by the user; the observation of users through their action and behaviors and not a profile library; a robust conceptual framework for modeling and managing context; and a computational tool for representing in a uniform way pieces of knowledge, of reasoning and of contexts.
This paper describes the advances in the TEEC project (Technologies Éducatives pour l’Enseignement en Contexte, in English: Educational technologies for teaching in context). This multidisciplinary project is at the intersection between context in learning and educational technologies. It aims at developing and experimenting a context effects-based pedagogical model involving learners and teachers from multiple geographical contexts, collaborating on common subjects with local specificities. The project also has for objective the development of digital tools to assist and participate in the elaboration of the pedagogical projects such as a context modeller and calculator (Mazcalc), an authoring system for learning scenarios and a context aware intelligent tutoring system. The elaboration and the analyses of experiments, as well as the design and the development of tools include research in multiple fields such as Computer Supported Collaborative Learning, Artificial intelligence, Instructional Design, Intelligent Tutoring Systems, Science Education and Contextualization. Finally, the research activity relies on the Design Based Research methodology (DBR) that allows the articulation of the project between all those disciplines and stakeholders.
L’intégration du contexte dans l’éducation est importante pour permettre aux enseignants et aux étudiants de découvrir la diversité, l’importance et le rôle du contexte dans l’enseignement et l’apprentissage. Pour ce faire, un modèle pédagogique basé sur les effets de contexte et appelé le ’modèle Clash’ a été développé et expérimenté. Pour faciliter les activités de recherche et les expérimentations autour de ce modèle, plusieurs outils numériques sont nécessaires. Le Mazcalc (calculateur de contexte) est un outil numérique qui permet de modéliser un objet étudié dans plusieurs contextes géographiques distincts et de calculer les écarts entre les contextes de l’objet en fonction de plusieurs paramètres et thèmes. L’objectif est d’utiliser ce calcul pour fournir des informations sur les différences et les similitudes entre les deux instanciations contextuelles de l’objet d’étude. Le Mazcalc communiquera ensuite avec un CEM (Gestionnaire d’effet de contextes) qui fournira des informations sur la pertinence de la mise en place d’une expérimentation pédagogique collaborative sensible au contexte impliquant des apprenants des deux contextes modélisés. Le Mazcalc a déjà été développé et cet article se concentre sur les travaux en cours concernant les avancées du projet TEEC1 sur la création du CEM et du système auteur pour assister la scénarisation.
Most of intelligent tutoring systems orient the learner towards learning objectives that fit an a priori profile. In AI terms, the teacher establishes a task model that the learner must realize according to a given frame of knowledge, methods and tools. The unique feedback from learners comes from their evaluation. For including the learner in the training-design loop, the task model must be replaced by an activity model of the learner realizing the task. This approach improves the acquisition of new knowledge, competences and skills by the learner This acquisition phase depends essentially on the learner’s background. Making the learning context explicit facilitates this knowledge acquisition. Three frames of references are proposed: for learner modeling, for training specifications and for learning activities. Each frame of reference is described by contextual elements usable for all the learners, but instantiable with a specific value for each learner and each step in the training session. This "learner-driven" training is more relevant than the usual “profile-driven” training.
Explicitly representing an agent’s context has been shown to have many benefits, which should also apply to machine learning. In this paper, we describe an approach to do this called context-dependent deep learning (CDDL), which is based on earlier work in context-mediated behavior (CMB) that uses contextual schemas (c-schemas) to represent classes of situations along with knowledge useful in them. These c-schemas are then recalled and guide reasoning in the corresponding contexts. CDDL stores knowledge about deep neural network structure and weights in c-schemas, which allows context-specific learning. Our work is being developed in the domain of seabird detection in aerial images of islands for use by biologists.
It has long been thought by cognitive science researchers that context plays a large role in human cognition – from memory recall to linguistics and problem solving. However, the role of context in identifying the emotional state of a human interlocutor, while thought to be important, has never been evaluated experimentally. This paper describes a study involving human test subjects that sought to gauge how well they could identify the emotion being expressed by a speaker using only paralinguistic signals (i.e., speech without understanding the spoken words), with and without knowing the speaker’s context. The first part of the study entailed asking the test subjects to identify the emotion expressed by a speaker who utters unintelligible sounds in a context-free basis. The test subjects were provided with knowledge about the context in which the speaker(s) uttered the same sounds heard before on a context-free basis. This allowed for the measurement of the impact of knowing the context upon their ability to correctly identify the expressed emotion. The results of our study indicate that knowing the context under which the speakers uttered the expressions indeed improved the ability of the test subjects to infer the correct emotion being expressed by the speakers. This paper describes the study and its results.
This paper defends a vision of good management that is rational, practical, and responsible. Managers are rational insofar as they link their actions to reasons, practical insofar as they situate their actions in context and consider the consequences, and responsible insofar as they are prepared to answer questions about the appropriateness of their actions. This paper presents a general empirical method for practicing management in this manner, together with a toolbox of good management concepts, contexts, and precepts. Attention is drawn to the role of modelling and using context in good management. The method is applied to a business case study.
Volume 17- 1Issue 1
Volume 18- 2Issue 1
Volume 19- 3Issue 1
Volume 21- 4CONTEXT-21 Special Issue