Learning Hierarchical Task Models from Input Traces

We describe HTN‐MAKER , an algorithm for learning hierarchical planning knowledge in the form of task‐reduction methods for hierarchical task networks (HTNs). HTN‐MAKER takes as input a set of planning states from a classical planning domain and plans that are applicable to those states, as well as a set of semantically annotated tasks to be accomplished. The algorithm analyzes this semantic information to determine which portion of the input plans accomplishes a particular task and constructs task‐reduction methods based on those analyses. We present theoretical results showing that HTN‐MAKER is sound and complete. Our experiments in five well‐known planning domains confirm the theoretical results and demonstrate convergence toward a set of HTN methods that can be used to solve any problem expressible as a classical planning problem in that domain, relative to a set of goal types for which tasks have been defined. In three of the five domains, HTN planning with the learned methods scales much better than a modern classical planner.     

A case study of online instructional collaborative discussion activities for problem-solving using situated scenarios: An examination of content and behavior cluster analysis

In some higher education courses that focus on case studies, teachers can provide situated scenarios (such as business bottlenecks and medical cases) and problem-solving discussion tasks for students to promote their cognitive skills. There is limited research on the content, performance, and behavioral patterns of teaching using online discussions and integrated situated scenarios. This case study empirically explored the learning process of adopting collaborative online instructional discussion activities for the purpose of problem-solving using situated scenarios in a higher education course. Thirty-two university students carried out problem-solving activities on case scenarios and problem-solving tasks assigned by the teacher on the discussion forum. Two forms of instructional activities were considered: 1) problem-solving in a given scenario and 2) problem-solving when learners play roles in a given scenario. The activities mentioned above were each implemented for a week.     

From handheld collaborative tool to effective classroom module: Embedding CSCL in a broader design framework

The field of Computer Supported Collaborative Learning (CSCL) includes designers who emphasize effectiveness, measured via experiments, as well as designers who emphasize context and conduct qualitative research on teaching and learning practices. We conjectured that these two different emphases could be fruitful combined in a research and development process aimed at producing effective CSCL practices. We explored this possibility in a project that adapted a CSCL tool from Chile to serve as the basis of an effective 3-week classroom module for primary school mathematics in the United States. To go from tool to module, we addressed curricular fit, training materials, pedagogical guidance, formative and summative assessments, and logistical support. In conducting the project, we found that effectiveness and contextual research could be conducted simultaneously and yielded complementary insight to this design process, which enabled our project to rapidly move from the base tool towards complete classroom modules. An experiment we conducted after our design iterations showed that students who used the modules learned more about the target content, fractions. A retrospective analysis of our design process suggests that the Integrative Learning Design framework is useful for organizing the complementary components of effectiveness and contextual research in our design process.     

Integration of metacognitive skills in the design of learning objects

Recent studies have demonstrated that specific instruction about metacognitive strategies improves achievement, the accuracy of knowledge monitoring, and the application of learning strategies in hypermedia environments. However, there are no models to date for instructional designers who design and develop learning objects for the incorporation of specific scaffolds to aid student reflection about their metacognitive skills; thus making it difficult to identify tasks to orientate learners in improving such skills. In this paper, we propose the use of specific ontologies as the basis for incorporating information about metacognition in learning objects so that a Learning Management System can select and recommend tasks designed for the development and/or improvement of the learners’ metacognitive skills within the context of e-learning.     

Designing computer-based rewards with and for children with Autism Spectrum Disorder and/or Intellectual Disability

Children with Autism Spectrum Disorder (ASD) tend to have an affinity for digital technologies, often preferring computer-assisted learning to human-assisted learning. Many children with ASD are also diagnosed with Intellectual Disabilities (ID), yet design studies involving children with ASD and ID are scarce. Rewards can have a positive impact on children's learning and motivation, but little is known about the nature and impact of rewards for children with ASD, and/or ID. Digital technologies are well placed to provide task-based rewards, and in combination with a better understanding of the reward preferences of children with ASD and/or ID this has significant potential to enhance learning. This paper presents two robust participatory design (PD) studies involving children with: i) ASD; ii) ID; and iii) both ASD and ID. The studies aimed to identify: i) the reward preferences of children with ASD and/or ID (RQ1) and ii) how rewards might develop throughout a task as the child progresses (RQ2). Results revealed a number of reward categories that were common to all children, as well as children's preferences for how rewards could develop as they progress through computer-based tasks, for the first time. Original implications for designing computer-based rewards embedded within digital intervention/educational technologies for children with ASD and/or ID, are discussed.     

How does desktop virtual reality enhance learning outcomes? A structural equation modeling approach

This study examined how desktop virtual reality (VR) enhances learning and not merely does desktop VR influence learning. Various relevant constructs and their measurement factors were identified to examine how desktop VR enhances learning and the fit of the hypothesized model was analyzed using structural equation modeling. The results supported the indirect effect of VR features to the learning outcomes, which was mediated by the interaction experience and the learning experience. Learning experience which was individually measured by the psychological factors, that is, presence, motivation, cognitive benefits, control and active learning, and reflective thinking took central stage in affecting the learning outcomes in the desktop VR-based learning environment. The moderating effect of student characteristics such as spatial ability and learning style was also examined. The results show instructional designers and VR software developers how to improve the learning effectiveness and further strengthen their desktop VR-based learning implementation. Through this research, an initial theoretical model of the determinants of learning effectiveness in a desktop VR-based learning environment is contributed.     

Applying Learning Style Theory to Web Page Design

ABSTRACT

Library Web sites can be instructional tools, especially for those patrons who utilize library resources from their homes. Many libraries are developing online tutorials, but there is an opportunity for Web instruction on another level. The organization and design of a Web site can act as an instructional tool in itself. This paper is a call to library Web designers to assess their work in terms of learning style preferences. Learning style theory is based on how people process information and learn new material. Applying these ideas to Web page design can make library resources more accessible and improve the patron's comprehension of how the library works.     

How do instructional designers use automated instructional design tool?

The purpose of this study was to investigate the use of an automated design tool by naive, novice, and expert instructional designers. A talk-aloud protocol, attitude survey, performance assessment, and direct observation were used to gather data. While the expert designers used the tool, they used it as a word processor with a rich database of instructional strategies. The novice designers relied on the tool for advice, guidance, and assistance in completing all the design tasks. Non-designers used the tool for learning about design.     

Inventing motivates and prepares student teachers for computer‐based learning

A brief, problem‐oriented phase such as an inventing activity is one potential instructional method for preparing learners not only cognitively but also motivationally for learning. Student teachers often need to overcome motivational barriers in order to use computer‐based learning opportunities. In a preliminary experiment, we found that student teachers who were given paper‐based course material spent more time on follow‐up coursework than teachers who were given a well‐developed computer‐based learning environment (CBLE), leading to higher learning outcomes. Thus, we tested inventing as an instructional method that may help overcome motivational barriers of teachers' use of computer‐supported tools or learning environments in our main experimental study (N = 44). As a computer‐based environment, we used the ‘Assessment of Learning strategies in Learning journals’. The inventing group produced ideas about criteria to evaluate learning strategies based on student cases prior to the learning phase. The control condition read a text containing possible answers to the inventing problem. The inventing activity enhanced motivation prior to the learning phase and assessment skills as assessed by transfer problems. Hence, the inventing activity prepared student teachers to learn from a CBLE in a motivational as well as cognitive way.     

Rethinking the evaluation of algorithm animations as learning aids: an observational study

One important aspect of creating computer programs is having a sound understanding of the underlying algorithms used by programs. Learning about algorithms, just like learning to program, is difficult, however. A number of prior studies have found that using animation to help teach algorithms had less beneficial effects on learning than hoped. Those results surprise many computer science instructors whose intuition leads them to believe that algorithm animations should assist instruction. This article reports on a study in which animation is utilized in more of a “homework” learning scenario rather than a “final exam” scenario. Our focus is on understanding how learners will utilize animation and other instructional materials in trying to understand a new algorithm, and on gaining insight into how animations can fit into successful learning strategies. The study indicates that students use sophisticated combinations of instructional materials in learning scenarios. In particular, the presence of algorithm animations seems to make a complicated algorithm more accessible and less intimidating, thus leading to enhanced student interaction with the materials and facilitating learning.     

Multiple peer-assessment modes to augment online student question-generation processes

In view of the current theoretical and empirical support for a student-generated questions approach to learning along with the advantageous features of network technology, several online student question-generation learning systems with a peer-assessment component have been developed. Despite this, all existing systems are limited in terms of the types of communication modes permissible for peer-assessment. Online discourse experience and the quantity and quality of interaction may vary as a result of the specific interaction mode students are exposed to. Because of this and the fact that versatile learning spaces are both possible and potentially desirable during the various stages of learning and teaching, multiple peer-assessment modes were created, and the overall attitudes of learners toward peer-assessment as well as their preferences toward respective peer-assessment modes were examined. The collected data confirmed the perceived usefulness of peer-assessment for developing higher-order thinking and cognitive elaboration. Support was demonstrated for student question-generation activities, for which learners typically have limited prior experience. Additionally, in light of the apparent overwhelming preference for and superiority of the more interactive two-way and multi-way modes over the one-way mode and the perceived learning potential of these modes, it is suggested that designers of similar systems should consider their inclusion. Finally, even though multi-way learning was found to be both the preferred and most supportive mode for learning, students also revealed distinct reasons for their preferences for respective interaction modes. In general, these reasons supported the premise that multiple peer-assessment modes are needed in order to accommodate individual preferences and needs. Suggestions and implications for instructional implementation, system development, and future studies are offered.     

Design patterns for monitoring and evaluating CSCL processes

Both quantitative and qualitative methods are being increasingly used to investigate the learning dynamics that take place within CSCL environments. Since such practices are a crucial aspect of the CSCL field, Design Patterns (DPs) can be used for capitalizing on experience and sharing know-how among practitioners. This paper describes three DP instances that have been developed and fine tuned by a community of practice consisting of researchers, instructional designers and tutors with the aim of supporting monitoring and evaluation of CSCL interactions. The DP solutions are based on a set of indicators, some of quantitative and some of qualitative nature, as well as on the methods to gauge these indicators, starting from data tracked by the e-learning system. The process of development of these DPs is described and examples of use are reported and discussed in order to advance the instructional design field and inform the development of CSCL systems. The proposed DPs belong to a Language, aimed at describing tracking problems in different types of e-learning systems and at capturing in their solutions the know-how developed by communities of experts in the different fields.     

CLPL: Providing software infrastructure for the systematic and effective construction of complex collaborative learning systems

Over the last decade, e-Learning and in particular Computer-Supported Collaborative Learning (CSCL) needs have been evolving accordingly with more and more demanding pedagogical and technological requirements. As a result, high customization and flexibility are a must in this context, meaning that collaborative learning practices need to be continuously adapted, adjusted, and personalized to each specific target learning group. These very demanding needs of the CSCL domain represent a great challenge for the research community on software development to satisfy.This contribution presents and evaluates a previous research effort in the form of a generic software infrastructure called Collaborative Learning Purpose Library (CLPL) with the aim of meeting the current and demanding needs found in the CSCL domain. To this end, we experiment with the CLPL in order to offer an advanced reuse-based service-oriented software engineering methodology for developing CSCL applications in an effective and timely fashion. A validation process is provided by reporting on the use of the CLPL platform as the primary resource for the Master's thesis courses at the Open University of Catalonia when developing complex software applications in the CSCL domain.The ultimate aim of the whole research is to yield effective CSCL software systems capable of supporting and enhancing the current on-line collaborative learning practices.     

“I'm a Visual Learner so I like this”: Investigating Student and Faculty Tutorial Preferences

Online tutorials are useful for reinforcing information literacy concepts addressed in library instruction. A wide range of tutorial types cater to different learning styles and feature varying levels of interactivity. In this study, students and faculty reported experiences using two types of tutorials teaching basic search strategies—an interactive tutorial, and a video tutorial. Although both groups favored the video, faculty were split about which tutorial they would rather assign, a discrepancy suggesting questions about how tutorial developers should balance user preferences with learning needs. These findings provide valuable insights for librarians and instructional designers considering creating information literacy tutorials.     

COMBINING MULTI‐AGENT PARADIGM AND MEMETIC COMPUTING FOR PERSONALIZED AND ADAPTIVE LEARNING EXPERIENCES

Learning is a critical support mechanism for industrial and academic organizations to enhance the skills of employees and students and, consequently, the overall competitiveness in the new economy. The remarkable velocity and volatility of modern knowledge require novel learning methods offering additional features as efficiency, task relevance and personalization. Computational Intelligence methodologies can support e‐Learning system designers in two different aspects: (1) they represent the most suitable solution able to support learning content and activities, personalized to specific needs and influenced by specific preferences of the learner and (2) they assist designers with computationally efficient methods to develop “in time” e‐Learning environments. This article attempts to achieve both results by exploiting an ontological representations of learning environment and memetic approach of optimization, integrated into a cooperative distributed problem solving framework. This synergy enables multi‐island memetic approach managing a collection of models and processes for adapting an e‐Learning system to the learner expectations and to formulate objectives in an effective and dynamic intelligent way. More precisely, our proposal exploits ontological representations of learning environment and a memetic distributed problem‐solving approach to generate the best learning presentation and, at the same time, minimize the computational efforts necessary to compute optimal learning experiences.     

The role of scaffolding and motivation in CSCL

Recent findings from research into Computer-Supported Collaborative Learning (CSCL) have indicated that not all learners are able to successfully learn in online collaborative settings. Given that most online settings are characterised by minimal guidance, which require learners to be more autonomous and self-directed, CSCL may provide conditions more conducive to learners comfortable with greater autonomy. Using quasi-experimental research, this paper examines the impact of a redesign of an authentic CSCL environment, based upon principles of Problem-Based Learning, which aimed to provide a more explicit scaffolding of the learning phases for students. It was hypothesised that learners in a redesigned ‘Optima’ environment would reach higher levels of knowledge construction due to clearer scaffolding. Furthermore, it was expected that the redesign would produce a more equal spread in contributions to discourse for learners with different motivational profiles.     

Learning multi-tasks with inconsistent labels by using auxiliary big task

Multi-task learning is to improve the performance of the model by transferring and exploiting common knowledge among tasks. Existing MTL works mainly focus on the scenario where label sets among multiple tasks (MTs) are usually the same, thus they can be utilized for learning across the tasks. However, the real world has more general scenarios in which each task has only a small number of training samples and their label sets are just partially overlapped or even not. Learning such MTs is more challenging because of less correlation information available among these tasks. For this, we propose a framework to learn these tasks by jointly leveraging both abundant information from a learnt auxiliary big task with sufficiently many classes to cover those of all these tasks and the information shared among those partially-overlapped tasks. In our implementation of using the same neural network architecture of the learnt auxiliary task to learn individual tasks, the key idea is to utilize available label information to adaptively prune the hidden layer neurons of the auxiliary network to construct corresponding network for each task, while accompanying a joint learning across individual tasks. Extensive experimental results demonstrate that our proposed method is significantly competitive compared to state-of-the-art methods.     

Authority and convergence in collaborative learning

Teachers and students have established social roles, norms and conventions when they encounter Computer-Supported Collaborative Learning (CSCL) systems in the classroom. Authority, a major force in the classroom, gives certain people, objects, representations or ideas the power to affect thought and behavior and influences communication and interaction. Effective computer-supported collaborative learning requires students and teachers to change how they understand and assign authority. This paper describes two studies in which students' ideas about authority led them to converge on what they viewed as authoritative representations and styles of representation too early, and the early convergence then hindered their learning. It also describes a third study that illustrates how changes to the CSCL system CAROUSEL (Collaborative Algorithm Representations Of Undergraduates for Self-Enhanced Learning) improved this situation, encouraging students to create representations that were unique, had different styles and emphasized different aspects of algorithms. Based on this research, methods to help students avoid premature convergence during collaborative learning are suggested.