Intelligent Content Assembly Workbench (I-CAW)
[ Capturing real world experiences from open and closed social spaces and tailoring their use for learners, trainers and scriptwriters]

Overview

In order to address the needs of adult learners effectively, simulators should offer relevant learning experiences tailored to the way adults learn in the real-world, namely self-directed and experienced-based. The current simulators fall short of these expectations due to a number of reasons:

• These environments have a static or limited variation of content (Welsh et al. 2003) as they are based on the experience of a small contingent of domain experts.
• The complexity of the real-world environment requires considerable amount of time to develop and update a representation, which is actionable by a simulated environment.
• The underlying representations or models omit many of the cognitive, social and emotional factors of activities found in real-life.

A set of semantic services and an interface to demonstrate and validate the benefits of such semantic services - an Intelligent Content Assembly Workbench (I-CAW) is being developed as part of the ImREAL project to address the shortcomings outlined above by:

• Extending the sources for real-world observation (content) from social and local spaces: The surge in social media has brought abundance of content and can provide rich resources for finding real-world activities that can augment understanding of interpersonal communication domains (Want et al, 2007). I-CAW offers mechanisms for assembling user-generated content in social media and stories from a local, social media-inspired, storytelling environment.
• Developing Multi-layered ontologies (Thakker et al, 2011) for modelling real-world activities underpinned by social science theory of Activity (Leont'ev, 1978). Ontological representation grounded in activity theory allows enhancing simulated environments by connecting the simulated learning experiences with real-world practice. An a priori ontology modularisation methodology is developed to allow iterative development and management of the underlying representation in AMOn. Semantic services described in previous sections utilise such ontologies along with external datasets (such as Linked Data Cloud (Bizer et al. 2009)) to annotate and augment real-world content. I-CAW relies on semantic services for providing intelligent mechanisms to utilise such content
• In addition to the activity theory, our underlying representation (AMOn ontology) will also take into account the pedagogical model on self regulated learning (SRL) (Zimmerman et al. 1989, Hetzner et al. 2011) where the simulator users are supported in forethought and reflection phases.

Users

Potential users of I-CAW are:

• Tutors : who manage the training and help linking the experience in the simulator with performance in the real-world
• Learners : who are being trained; we consider mainly the persons in charge of the interpersonal communication such as interviewer
• Scriptwriters or Subject matter experts: who develop content for simulators and may use the I-CAW and its' real-world examples.

Architecture

Overview Architecture

UML Diagram of I-CAW architecture

The UML Diagram shows the main architectural elements of the currently implemented I-CAW workbench and their interactions. The user interface is implemented in PHP, Java script and HTML. I-CAW is a consumer of semantic augmentation and semantic query services. The interface also consumes social web data via social web APIs (at the moment, You Tube Data API ) and internal storytelling API.

I-CAW retrieves YouTube metadata based on a video URL and allows selecting textual comments around the video that contributors would like to contribute. The semantic augmentation service automatically tags these comments. This service also augments the tags with the concepts from external ontologies. The content is tagged on the fly and stored in a semantic knowledge base driven by high-performance OWLIM semantic repository. Then I-CAW, using the semantic query service, allows browsing and retrieval of heterogeneous content (comments, videos, and stories). Similar process is performed for semantically augmenting and browsing stories.

Services and Outputs

• Activity Model ONtology (AMOn) is computer-processable representation of the concepts from the activity model. [More details]
• Semantic Augmentation Service is a generic service designed to link content with the concepts from the ontological knowledge bases in order to fully benefit from the reasoning capabilities of semantic technologies. [More details]
• Semantic Query Service provides a mechanism for querying and browsing using semantically augmented content. This content is collected with the I-CAW, annotated with the semantic augmentation service and stored in the semantic repository. [More details]
• Semantic Viewpoint Extraction service is designed to capture users' (learners or tutors) viewpoint & experience on the effect of emotions and body language during interpersonal communications [More details]
• Storyboarding service ImREAL Storyboarding module to support instructional designers creating simulation contents. [More details]

Demonstration

Overview Presentation I-CAW

I-CAW Overview on Prezi

I-CAW for Trainers - Trainers using I-CAW for contributing content

I-CAW for Trainers on Vimeo

Learners at Forethought stage of SRL - using I-CAW with Storytelling

Learners using I-CAW with Storytelling on Vimeo

Learners at Forethought stage of SRL - using Search functionality

Learners using Search functionality on Vimeo

Learners at Forethought stage of SRL - using Browsing/Tag Cloud Functionality

Learner using Browsing/Tag Cloud Functionalit on Vimeo

Testing Interactive User Modeling Dialogue (WP4) within I-CAW.

Interactive User Modeling Dialogue on Vimeo

Pulling real life experiences from I-CAW for scriptwriting - Storyboarding Service for Scriptwriters

Storyboarding ImREAL on YouTube

Publications

• Thakker, D; Yang-Turner, F; Lau, L; Dimitrova, V Socio-technical Ontology Development for Modelling Sensemaking in Heterogeneous Domains in the proceedings of the Workshop on "Ontologies Come of Age in the Semantic Web" [OCAS2011] at the 10th International Semantic Web Conference (ISWC).
• Karanasios,S., Mishra, J., Allen, D., Norman, A., Thakker, D., Lau, L. Capturing Real World Activity: A Socio-Technical Approach. In the proceedings of the E-challenges conference. 26-28 October 2011 Florence, Italy.
• Thakker, D., Dimitrova, V., Lau, L., Denaux, R., Karanasios, S., Yang-Turner, A Priori Ontology Modularisation in Ill-defined Domains. In the proceedings of 7th International Conference on Semantic Systems, I-SEMANTICS, 7-9 September, 2011.
• Despotakis, D., Lau, L., Dimitrova, V. A Semantic Approach to Extract Individual Viewpoints from User Comments on an Activity. In the proceedings of the International Workshop on Augmenting User Models with Real World Experiences to Enhance Personalization and Adaptation in conjunction with UMAP 2011, Girona, Spain, July 11-15 2011.
• Despotakis, D., Lau, L., Dimitrova, V. Capturing the semantics of individual viewpoints on social signals in interpersonal communication. Semantic Web Journal - Special Issue on The Personal and Social Semantic Web. (submitted)

References

• Bizer, C., Heath, H., Berners-Lee, T: Linked Data - The Story So Far. In: IJSWIS, 5(3),1-22 (2009)
• Hetzner, S., Steiner, C., Dimitrova, V., Brna, P., Conlan, O: Adult Self-regulated Learning through Linking Experience in Simulated and Real World: A Holistic Approach. Accepted for ECTEL 2011. Palermo (2011)
• Leont'ev, A.N., Activity, Consciousness, and Personality. 1978: Prentice-Hall.
• Thakker, D., Dimitrova, V., Lau, L., Denaux, R., Karanasios, S., Yang-Turner, F: A Priori Ontology Modularisation in Ill-defined Domains. Accepted for the I-Semantics 2011: 7th International Conference on Semantic Systems. Graz, Austria (2011)
• Welsh, E., Wanberg, C., Brown, K., Simmering, M.:E-learning: Emerging uses, empirical results and future directions. International Journal of Training and Development. 7(4),245-258 (2003)
• Wang, F.-Y., Carley, K.M., Zeng, D., Mao, W: Social Computing: From Social Informatics to Social Intelligence. IEEE Intelligent Systems 22(2), 79-83 (2007)
• Zimmerman, BJ: A social cognitive view of self-regulated academic learning. J. Educational Psychology. 81, 329--339 (1989)