Online courses heavily relying on programming skills tend to be difficult and time-consuming for students, who may get frustrated when stuck in an assignment. Obviously, this may increase drop-out rate and decrease academic performance as well as students’ satisfaction with the course and the institution in general. In this context, we propose a notification, recommendation and monitoring system which is integrated into an automatic assessment tool with the aim to enhance the learning process in virtual classrooms. In particular, notifications, recommendations and visualization reports are used to show the activity, progress and performance of all students. The system is implemented in a distributed computing course in an online university. A quantitative analysis method used to collect and analyze data of students’ perceptions regarding the system showed that: (1) notifications helped students organize their time and encourage them to work more effectively; (2) recommendations allowed students to receive useful and timely scaffolding for coping with their problems and completing their assignment; and (3) visualization reports provided valuable insights toward monitoring the learning process. Moreover, the analysis of correlations showed that the reception of recommendations and the visualization reports is related to encourage students to do more executions and to start earlier the assignments. Finally, this study seeks to contribute to online teachers’ endeavor to enhance students’ engagement, performance and learning in the field of programming (and not only).

Academic work: grading student assignments or conducting literature surveys entails extensive reading, which is both a time consuming and cognitively demanding task. The challenge increases proportionally with the increase of volume of the textual content. In this paper, we propose a novel approach to visualization of textual data that depicts information on a continuum (temporal or spatial) allowing inferences to be made about thematic organization of a document and its structure. Our visualization method—termed ThemeTrack—creates a visual map: delineating key themes and tracking their presence throughout the text, highlighting their variations and relationships. It aims to make the review of textual data more efficient. To assess the viability of the proposed approach, a series of experiments were conducted using graduate-level theses and published articles in the peer-reviewed journals. The applications of the proposed method are discussed and the real-word examples are provided.

The aim of this research project is to evaluate a novel approach to providing academic integrity through behavioral pattern analysis for continuous and on-demand assessments. Our objective is to empower instructors with efficient and automated tools that promote accountability and academic integrity, while providing students with an accessible, non-invasive, privacy preserving and convenient validation of the student-generated academic content. The contributions of the proposed study are threefold: (1) the bridged anonymity gap between learners and instructors, (2) an open source learning technology that enhances academic integrity, and (3) understanding of how the behavioral-based biometric technologies are perceived by students and instructors.

Emotion awareness is becoming a key aspect in collaborative work at academia, enterprises and organizations that use collaborative group work in their activity. Due to pervasiveness of ICT's, most of collaboration can be performed through communication media channels such as discussion forums, social networks, etc. The emotive state of the users while they carry out their activity such as collaborative learning at Universities or project work at enterprises and organizations influences very much their performance and can actually determine the final learning or project outcome. Therefore, monitoring the users' emotive states and using that information for providing feedback and scaffolding is crucial. To this end, automated analysis over data collected from communication channels is a useful source. In this paper, we propose an approach to process such collected data in order to classify and assess emotional states of involved users and provide them feedback accordingly to their emotive states. In order to achieve this, a fuzzy approach is used to build the emotive classification system, which is fed with data from ANEW dictionary, whose words are bound to emotional weights and these, in turn, are used to map Fuzzy sets in our proposal. The proposed fuzzy-based system has been evaluated using real data from collaborative learning courses in an academic context.

Cognitive assessment in collaborative and social learning requires a broad perspective about learning and the involved processes. Assessment processes have a significant effect on collaborative learning because they engage learners through accountability and constructive feedback. However, in order to design a coherent and efficient assessment system for collaborative and social learning it is necessary to design an enriched learning experience that predisposes the feedback and awareness in the group. This paper focuses on e-assessment of collaborative learning and extends it with Social Network Analysis (SNA) techniques that are able to analyze and represent social network interaction during the live sessions of collaboration by using collaborative complex learning resources (CC-LR). The knowledge extracted from analyzing the large amounts of interaction data related to social and collaborative networking is then integrated into a general assessment system to produce an efficient and personalized awareness and feedback about the collaborative activity and the social behavior of the participants to ultimately enhance and improve the collaborative learning experience with CC-LRs. The conceptual and methodological research approach is provided along with the evaluation design of e-assessment applications and tools that meet the mentioned requirements and goals.

In a collaborative e-learning environment, students are usually involved in learning activities such as collaborative writing (e.g., an essay in Wiki form) and debates in the form of a chat or asynchronous forum. Capturing students' feelings and emotional states enclosed in such textual information is important, since sentiments can influence individual behavior and consequently group dynamics as well as individual and group performance. For this reason, emotion awareness becomes an important issue for both tutors and students themselves. Especially for tutors, if they have as accurate affective information as possible about the emotional state that every individual and group is encountered, they might be able to provide more effective feedback to the students that includes not only cognitive but also affective scaffold. A first important step to this endeavor is to develop an approach that enables labeling affective behavior and then presenting the emotional information to all the actors involved in the learning process.

In previous research we proposed a new type of learning resource named Collaborative Complex Learning Resource (CC-LR) in support for teaching and learning by the virtualization of live collaborative sessions, with the aim to leverage the knowledge elicited during the collaboration and produce interactive and attractive resources to be played by engineering learners. We claimed this type of pedagogically and technologically augmented learning resources is able to overcome endemic problems found in collaborative learning of on-line courses, such as lack of authentic interactivity, user empowerment, social identity and challenge, thus having a positive effect in learner engagement. In order to enhance further learning engagement we endowed CC-LR with a multifold cognitive e-assessment approach that provided effective awareness and constructive feedback to learners from the live collaborative interaction amongst group members. In this paper we extend our e-assessment approach with innovative indicators from analyzing and representing the social network interaction from the live collaboration. These new indicators are integrated into our multi-fold assessment model to produce an efficient and personalized assessment feedback to ultimately enhance and improve the collaborative learning experience with CC-LRs.

Recent research shows that Computer Supported Collaborative Learning (CSCL) can offer many advantages to Language Teaching and Learning such as motivate students to participate in an environment where they are asked to use their skills to communicate effectively. However, teachers have to face numerous problems and complicated issues of management when dealing with such a complex pedagogy and the technologies involved. One of the most promising solutions so far is this of "orchestration", a field where there has been a thriving research activity over the last years, yet with various open issues to be discussed and little research focused on Language Learning. This is a position paper which aims at presenting the recent developments on this field and discovering the open research questions that will lead to the proposal of a context-aware orchestration framework, which will improve the orchestration of CSCL activities in a language learning environment.

Cognitive assessment in collaborative and social learning requires a broad perspective about learning and the involved processes. Assessment processes have a significant effect on collaborative learning because they engage learners through accountability and constructive feedback. However, in order to design a coherent and efficient assessment system for collaborative and social learning it is necessary to design an enriched learning experience that predisposes the feedback and awareness in the group. In this paper, collaborative learning is developed into a special environment: a Virtualized Collaborative Sessions. Two levels of assessment are incorporated, deferred and immediate time, in order to produce an efficient and personalized assessment feedback to ultimately enhance and improve the collaborative learning experience. The research reported in this paper was undertaken within the FP7 European project ALICE.

Academic programs demand a constant updating. As the reader might agree, today's societies demand a new merge of knowledge elements. Current web-infrastructure is able to support new approaches in science development. On the one hand, due to current social, scientific and technological advances, academic programs in universities are clearly under pressure to be constantly restructured and renewed in order to provide valid and up-to-date knowledge to students. On the other hand, students obviously have different academic needs and backgrounds. So every person needs to follow a specific path in its training process. Our approach aims at proposing a well-ordered method for selecting personalized contents in e-Learning environments through the use of complex network analysis. Due to the similar nature and structure of knowledge and despite the diversity of knowledge types, the proposed method could be easily extrapolated to different academic programs and even account for some diversity in human profiles.

This paper explores the role and impact of emotion on learning and specifically analyzes issues related to emotion awareness and emotional feedback in e-learning. After a detailed analysis of current research work in these issues, important research questions in emotional e-learning are set and a conceptual Emotion Analysis model is proposed to answer these questions.

The adoption of emotion awareness features in learning environments, has been put on the focus of the research agenda towards students' engagement and their authentic social interaction. In the current paper we provide a solution towards the provision of e-learning with emotion awareness features, which is based on self-reporting of emotions and affective response from the system. We also present research findings derived from two experiments with undergraduate students: in the University of Aegean (UoA) and the Open University of Catalonia (UoC). Finally, we set open questions for future research.

The enrichment of Computer Supported Collaborative (CSCL) Systems with emotion awareness features (detect emotion patterns and respond effectively) opens a window to the future of learner-to-computer interaction. In the current paper we present a system's design that attempts to evaluate the learner's affective state while he/she is taking part into collaborative tasks, in three different time-points: (i) before the task, (ii) in real-time (while collaborating) and (iii) retrospective (after the task). For the emotion assessment process, self-reporting and sentiment analysis are explored. Based on effective production rules that correlate emotions or emotion sequences to affective feedback techniques, the system will provide emotion scaffolds corresponding to user needs and feelings.

Collaborative and social learning assessment requires a broad perspective about learning and the involved processes. Assessment processes have a significant effect on CSCL because they engage learners through accountability and constructive feedback. However, in order to design a coherent and efficient assessment system for collaborative and social learning it is necessary to design an enriched learning experience that predisposes the feedback and awareness in the group. A complex set of simultaneously applied assessment approaches, each reinforcing and/or complementing the other is the main tool to enhance collaborative learning and social interaction amongst group members. In this paper, collaborative learning will be developed into a special environment: a Storyboard Learning Object. Collaborative learning using a storyboard may develop partners' collaborative and social abilities and competences through a sequential of integrated process where the interaction moves are continuously evaluated to determine the storyboard sequence and the use of the resources. To this end, two levels of assessment are proposed: deferred and immediate. Both are combined with contextual information about the user in order to produce an efficient and personalized assessment feedback to ultimately enhance and improve the collaborative learning experience. The research reported in this paper is currently undertaken within a FP7 European project called ALICE.

Informal learning in public spaces like museums and location-based entertainment venues is increasingly popular during the last years. Especially in technology-enhanced museums such properties as Virtual Reality, Game-Based Collaboration, and Immersive Displays are considered to bear significant educational value. After extensive literature review we have come to the conclusion that little to no research has been carried out on the learning outcomes of these powerful properties. Thus, the scope of our research is to investigate the learning efficacy of an integrated schema of audience collaboration and game design in immersive virtual reality environments. In order to achieve this, we are going to build and evaluate a theoretical framework that supports collaboration within an audience of 9--14 years old children.

This paper aims to explore two crucial aspects of collaborative work and learning: on the one hand, the importance of enabling collaborative learning applications to capture and structure the information generated by group activity and, on the other hand, to extract the relevant knowledge in order to provide learners and tutors with efficient awareness, feedback and support with regards to group performance and collaboration. To this end, in this paper we first propose a conceptual model for data analysis and management that identifies and classifies the many kinds of indicators that describe collaboration and learning into high-level aspects of collaboration. Then, we provide a computational platform that, at a first step, collects and classifies both the event information generated asynchronously from the users' actions and the labeled dialogues from the synchronous collaboration according to these indicators. This information is then analyzed in next steps to eventually extract and present to participants the relevant knowledge about the collaboration. The ultimate aim of this platform is to efficiently embed information and knowledge into collaborative learning applications. We eventually suggest a generalization of our approach to be used in diverse collaborative learning situations and domains.

This work presents a position paper that describes a conceptual framework for dasialearning designpsila-based e-learning systems focusing on the role of the development of learnerspsila cognitive and critical thinking. Within this framework, teacherspsila active involvement is viewed as essential. To this end, an attempt has been also made to map basic dimensions of thinking to dasialearning designpsila through the proposal of an innovative dasialearning designpsila environment which includes various features.

P2P systems are nowadays being used not only for file sharing but also for developing large-scale distributed applications. As an emerging paradigm for distributed computing, P2P systems are raising important issues as many novel aspects have to be dealt with in such systems. One key issue in P2P distributed computing is the efficient discovery and selection of peers, which is needed for many purposes such as efficient allocation of jobs to peers, load balancing, efficient file transfer, etc. Existing P2P distributed applications use ad hoc ways to discover and select peers, usually without any performance guarantee. In this paper we address the problem of the efficient peer selection in P2P distributed platforms. To this end, we have developed a P2P distributed platform using Sun's JXTA technology, which is endowed with resource brokerage strategies to efficiently select peers using four selection models: (a) economic scheduling model; (b) priced-based model; (c) peer-priority selection model;and, (d) random selection model. These different models are aimed to match different needs of P2P applications. Next, we have deployed the P2P JXTA platform in a real network using nodes of the PlaneLab - a planetary scale distributed infrastructure- and have experimentally evaluated the performance of the peer selection models by using a distributed application for processing large size log files of a virtual campus, which requires both efficient file transmission and processing in P2P nodes. The results of our work showed the need to develop, implement and evaluate appropriate models for efficient peer selection to match the different requirements of large-scale P2P distributed applications. Although we have used a concrete technology such as JXTA, our approach is applicable in a more general context of P2P and grid computing domain. Finally, our approach to peer selection through brokerage services is very flexible allowing extensions with other models.

Collaborative activity performed over specific platforms, designed for such purpose, can provide a deep knowledge about the roles, intentions and effects regarding participants and their interaction among themselves and with the knowledge objects available. This study aims at proposing a structured process for gathering the semantics of the activity hidden behind the raw data collected in log files from CSCL platforms. The proposal is based on exploring the semantic elements (activity awareness) through a social networks analysis (SNA). The main focus of our work is to match different behavioral profiles detected in the collaborative activity from CSCL with the formal profiles identified inside a complex concept-network. This network defines an ontology that describes the behavior expected when collaborating in different scenarios and types of activity. When a certain activity sequence matches with a predefined pattern, the concepts related to the pattern are then bound to the real activity sequence.

On the one hand, natural language is the main communication media for humans. It has a complex construction, based on the diversity of meaning for words and expressions according to the context. On the other hand, computers are not prepared to handle this ambiguity. The present work aims at presenting a multi-agent approach for dealing with the problem of discovering the meaning of expressions written in Spanish, based on a flexible recovery system and Bayesian principles. At a first stage, agents are supposed to identify the role of the words composing a sentence. At a second stage, a second set of agents is supposed to coordinate among them in order to assemble a meaning. Our research forms part and contributes to the analysis of collaborative conversations among participants in a web-based collaborative learning environment.

Due to their potential advantages, the use of Grid technologies toward the development of collaborative and personalized learning frameworks has been considerably increased. These learning frameworks can be constructed based on the distributed learning services and resources available in a learning Grid environment. A problem still unsolved is how to use and integrate low-level learning services to compose more complex high-level services or tools that can be useful to both tutors and learners. In that sense, on the one hand, semantic description of Grid learning services appears to be a powerful tool that can be used to discover suitable learning services depending on the system’s semantic capabilities. On the other hand, it can be employed to carry out a matching process among the learning services located in a learning framework to obtain the best fit according to specific functional parameters. These parameters represent significant characteristics of a learning Grid environment. This paper presents an initial effort that integrates schema and ontology matching methods that aim to develop a model to cope with the complex problem of automatic composition of Grid based learning tools and their portals.

In this paper we address the issue of monitoring studentspsila and groupspsila activity in online collaborative learning environments. This issue is especially important in the collaborative e-learning context, since an efficient monitoring process can provide valuable information to online instructors who may guide and support the development of collaborative learning projects. We have developed and tested an information system model which facilitates the automatic generation of weekly monitoring reports derived from data contained in server log files. These reports provide online instructors with visual information regarding studentspsila and groupspsila activity, thus allowing for a quick and easy classification of students and groups according to their activity level. Therefore, entities with a low activity level are identified as soon as possible and just-in-time assistance can be established for them. Furthermore, instructors can use these monitoring reports to forecast potential problems -such as studentspsila dropouts or possible conflicts inside the groups due to unbalanced distribution of tasks- and take operational and tactical decisions oriented to avoid them.

File sharing is among the most important features of the today's Internet-based applications. Most of such applications are server-based approaches inheriting thus the disadvantages of centralized systems. Advances in P2P systems are allowing to share huge quantities of data and files in a distributed way. In this paper, we present extensions of JXTA protocols to support filesharing in P2P systems with the aim to overcome limitations of server-mediated approaches. Our proposal is validated in practice by deploying a P2P file sharing system in a real P2P network. The empirical study revealed the benefits and drawbacks of using JXTA protocols for P2P file sharing systems.

The efficient file searching is an essential feature in P2P systems. While many current approaches use brute force techniques to search files by meta information (file names, extensions or user-provided tags), the interest is in implementing techniques that allow content-based search in P2P systems. Recently, clustering techniques have been used for searching text documents to increase the efficiency of document discovery and retrieval. Integrating such techniques into P2P systems is important toenhance searching in P2P file sharing systems. While some effort has been done for content-based searching for text documents in P2P systems, there has been few research work for applying these techniques for multimedia content in P2P systems. In this paper we introduce two P2P content-based clustering techniques for multimedia documents. These techniques are an adaptation of the existing Class-based Semantic Search (CSS) algorithm for text documents. The proposed algorithms have been integrated into a JXTA-based overlay P2P platform, and some initial evaluation results are provided. The JXTA-Overlay together with the considered clustering techniques is thus very useful for developing P2P multimedia applications requiring efficient searching of multimedia contents in peer nodes.

User modelling in on-line distance learning is an important research field focusing on two important aspects: describing and predicting students' actions and intentions as well as adapting the learning process to students' features, habits, preferences, and so on. The aim is to greatly stimulate and improve the learning experience. Indeed, on the one hand, students' intentions may change during the realization of learning activities and thus their actions evolve accordingly as the learning process moves forward. On the other hand, adaptive systems can effectively plan and design appropriate learning tasks according to students' features, habits and interests with the aim of facilitating the achievement of the learning goal. In this context, user modelling implies a continuous processing and analysis of user interaction data during long-term learning activities, which produces large and considerably complex information. As a consequence, processing this information is costly and could require computational capacity beyond that of a single computer. In this paper, we show how a Grid approach can considerably decrease the processing time of log data of on-line distance educational web-based systems. Our prototype is based on the masterworker paradigm and is implemented using a peer-topeer platform running on the Planetlab nodes. The results of our study show the feasibility of using Grid middleware to speed and scale up the processing of log data and thus achieve an efficient and dynamic user modeling in on-line distance learning.

Problem determination in today's computing environments consumes between 30 and 70% of an organization's IT resources and represents from one third to one half of their total cost of ownership. The first step to cutting down costs and to enable autonomic computing systems is to have all parts of the system report status in a common log data format and semantics. The generic log adapter (GLA) is a generic parsing engine shipped with the IBM's Autonomic Computing Toolkit that has been conceived to convert proprietary log data into a standard log data event-based format in real time. However, in order to provide generic support for parsing the majority of today's unstructured log data formats the GLA makes heavy use of regular expressions that incur in performance limitations. Current approaches proposed to increase GLA's performance have revolved around fine-tuning the set of regular expressions used to configure the GLA for a particular log data format or writing specific parsing code. In this work we propose a very new approach consisting in transparently parallelizing the GLA by taking advantage of its internal architecture and the fact that structuring log data is a task that lends itself very well to parallelization. We present a master-worker strategy that "gridifies" the GLA efficiently in a completely transparent way for the user

The goal of this paper is to explore the possibility of using CSCL component-based software under a Grid infrastructure. The merge of these technologies represents an attractive, but probably quite laborious enterprise if we consider not only the benefits but also the barriers that we have to overcome. This work presents an attempt toward this direction by developing a generic platform of CSCL components and discussing the advantages that we could obtain if we adapted it to the Grid. We then propose a means that could make this adjustment possible due to the high degree of genericity that our library component is endowed with by being based on the generic programming paradigm. Finally, an application of our library is proposed both for validating the adequacy of the platform which it is based on and for indicating the possibilities gained by using it under the Grid.

In this paper, the authors explore the different processes involved in constructing effective virtual collaborative learning groups, especially why, when and how these processes affect group formation and to which degree they guarantee the creation of well-functioning and successful learning groups. A student can benefit from collaborative learning only if he/she participates in supportive learning teams. For this reason, their research interest is to aid and provide the means for the configuration of learning groups that are appropriate for different learning situations. A key issue in this process is to make the educational function and structure of collaborative learning groups clear, by identifying and making explicit both the individual and group learning and social goals, as well as the relationships, interaction processes and roles that determine the nature and idiosyncrasy of the group.