Online annotation – Research and practices

Annotation can be a valuable exercise when trying to understand new information. The technique can be used to create a ‘condensed’ version of the original information for later review and to add additional information into the existing document. The growth in web-based learning materials and information sources has created requirement for systems that allow annotations to be attached to these new sources and, potentially, shared with other learners. This paper discusses annotation in an educational context and introduces some of the web annotation systems currently available. It also provides an overview of the development of a new system, eLAWS, by the authors, based upon the Web Service architecture. Finally, the paper provides suggestions for the future development of e-Learning Annotation tools.     

Rough set-aided keyword reduction for text categorization

The volume of electronically stored information increases exponentially as the state of the art progresses. Automated information filtering (IF) and information retrieval (IR) systems are therefore acquiring rapidly increasing prominence. However, such systems sacrifice efficiency to boost effectiveness. Such systems typically have to cope with sets of vectors of many tens of thousands of dimensions. Rough set (RS) theory can be applied to reducing the dimensionality of data used in IF/IR tasks, by providing a measure of the information content of datasets with respect to a given classification. This can aid IF/IR systems that rely on the acquisition of large numbers of term weights or other measures of relevance. This article investigates the applicability of RS theory to the IF/IR application domain and compares this applicability with respect to various existing TC techniques. The ability of the approach to generalize, given a minimum of training data is also addressed. The background of RS theory is presented, with an illustrative example to demonstrate the operation of the RS-based dimensionality reduction. A modular system is proposed which allows the integration of this technique with a large variety of different IF/IR approaches. The example application, categorization of E-mail messages, is described. Systematic experiments and their results are reported and analyzed.     

Evolutionary computing in recommender systems: a review of recent research

One of the main current applications of intelligent systems is recommender systems (RS). RS can help users to find relevant items in huge information spaces in a personalized way. Several techniques have been investigated for the development of RS. One of them is evolutionary computational (EC) techniques, which is an emerging trend with various application areas. The increasing interest in using EC for web personalization, information retrieval and RS fostered the publication of survey papers on the subject. However, these surveys have analyzed only a small number of publications, around ten. This study provides a comprehensive review of more than 65 research publications focusing on five aspects we consider relevant for such: the recommendation technique used, the datasets and the evaluation methods adopted in their experimental parts, the baselines employed in the experimental comparison of proposed approaches and the reproducibility of the reported experiments. At the end of this review, we discuss negative and positive aspects of these papers, as well as point out opportunities, challenges and possible future research directions. To the best of our knowledge, this review is the most comprehensive review of various approaches using EC in RS. Thus, we believe this review will be a relevant material for researchers interested in EC and RS.     

Hybrid job offer recommender system in a social network

Recommender systems (RSs) play a very important role in web navigation, ensuring that the users easily find the information they are looking for. Today's social networks contain a large amount of information and it is necessary that they employ a mechanism that will guide users to the information they are interested in. However, to be able to recommend content according to user preferences, it is necessary to analyse their profiles and determine their preferences. The present work proposes a job offer RS for a career‐oriented social network. The recommendation system is a hybrid, it consists of a case‐based reasoning (CBR) system and an argumentation framework, based on a multi‐agent system (MAS) architecture. The CBR system uses a series of metrics and similar cases to decide whether a job offer is likely to be recommended to a user. Besides, the argumentation framework extends the system with an argumentation CBR, through which old and similar cases can be obtained from the CBR system. Finally, a discussion process is established amongst the agents who debate using their experience from past cases to take a final decision.     

Learning styles and cognitive traits – Their relationship and its benefits in web-based educational systems

Different learners have different needs; they differ, for example, in their learning goals, their prior knowledge, their learning styles, and their cognitive abilities. Adaptive web-based educational systems aim to cater individual learners by customizing courses to suit their needs. In this paper, we investigate the benefits of incorporating learning styles and cognitive traits in web-based educational systems. Adaptivity aspects based on cognitive traits and learning styles enrich each other, enabling systems to provide learners with courses which fit their needs more accurately. Furthermore, consideration of learning styles and cognitive traits can contribute to more accurate student modelling. In this paper, the relationship between learning styles, in particular the Felder–Silverman learning style model (FSLSM), and working memory capacity, a cognitive trait, is investigated. For adaptive educational systems that consider either only learning styles or only cognitive traits, the additional information can be used to provide more holistic adaptivity. For systems that already incorporate both learning styles and cognitive traits, the relationship can be used to improve the detection process of both by including the additional information of learning style into the detection process of cognitive traits and vice versa. This leads to a more reliable student model.     

Securing Recommender Systems Against Shilling Attacks Using Social-Based Clustering

Recommender systems (RS) have been found supportive and practical in e-commerce and been established as useful aiding services. Despite their great adoption in the user communities, RS are still vulnerable to unscrupulous producers who try to promote their products by shilling the systems. With the advent of social networks new sources of information have been made available which can potentially render RS more resistant to attacks. In this paper we explore the information provided in the form of social links with clustering for diminishing the impact of attacks. We propose two algorithms, CluTr and WCluTr, to combine clustering with "trust" among users. We demonstrate that CluTr and WCluTr enhance the robustness of RS by experimentally evaluating them on data from a public consumer recommender system Epinions.com.     

基于分辨相似矩阵的相似粗糙集的属性约简算法

针对现实中数据局限导致等价关系弱化为相似关系,用相似关系代替等价关系建立了相似粗糙集的理论,定义了新的分辨相似矩阵,并给出了基于分辨相似矩阵的求核和属性约简算法,该算法可以有效地减少属性约简的计算量,最后通过实例验证了该算法是适用和有效的。     

纠错编译码技术在JTIDS中的应用

JTIDS系统是16号数据链系统的通信部件,将指挥控制系统、计算机及各种数据终端组成有机的无缝网络系统,实现作战信息资源共享,为保证数据信息安全可靠的进行交换,其消息传输格式采用了RS纠错编译码、CRC检错编码及交织编码等纠错编码技术.通过分析JTIDS中的RS编译纠错码原理,利用Matlab 6.5,在AWGN信道模式下,以MSK为调制方式,对JTIDS的固定消息格式在RS码和交织编码等纠错编码技术中的信号比特差错概率进行了仿真分析.分析表明利用RS码和交织编码等技术,在纠错范围内比特差错概率较不用纠错编码技术时有着明显的改善,即数据信息传输的安全性可靠性更高.     

Rough reduction in algebra view and information view

Rough set (RS) is a valid theory to deal with imprecise, uncertain, and vague information. It has been applied successfully since it was developed by Professor Z. Pawlak in 1982 in such fields as machine learning, data mining, intelligent data analyzing, control algorithm acquiring, etc. The greatest advantage of the RS is its great ability to compute the reductions of information systems. Many researchers have done a lot of work in developing efficient algorithms to compute useful reductions of information systems. There also are some researchers working on the relationship between rough entropy and information entropy. They have developed some efficient reduction algorithms based on conditional information entropy. In this article, the relationship of the definitions of rough reduction in algebra view and information view is studied. Some relationships such as inclusion relationship under some conditions and equivalence relationship under some other conditions are presented. The inclusion relationship between the attribute importance defined in algebra view and information view is presented also. Some efficient heuristic reduction algorithms can be developed further using these results. © 2003 Wiley Periodicals, Inc.     

The use of innovative ICT in the active pursuit of literacy

This paper investigates classroom interventions using a particular form of multimedia information and communication technology (ICT), and looks to study gains in pupil learning that accrue from its use. The research takes place in eight UK schools with 219, 11‐year‐old children (eight Year 6 classes). Work within the Literacy Hour is detailed in order to evaluate the effectiveness of a multimedia broadband educational communications system. The Literacy Hour is part of the UK Government's National Literacy Strategy: guideline requirements of schools to spend an hour a day on literacy to meet centrally established and monitored targets. The research data include pre‐ and post‐test assessments, along with 48 interviews with classroom teachers and pupils. The children are presented with a series of journalistic tasks and classroom activities that they resolve through the use of a compact and coordinated information system. The outcomes demonstrate that children can become self‐directive and very active – exploratory – learners in a very short period of time. They quickly enjoy the freedom and control that the system permits and through which they can be shown to enhance particular literacy skills. The lessons to be learned relate to the management and organisation of classroom teaching in the face of systems that promote rapid devolution of learning to the learner.     

Supporting teachers in adaptive educational systems through predictive models: A proof of concept

Adaptive educational systems (AESs) guide students through the course materials in order to improve the effectiveness of the learning process. However, AES cannot replace the teacher. Instead, teachers can also benefit from the use of adaptive educational systems enabling them to detect situations in which students experience problems (when working with the AES). To this end the teacher needs to monitor, understand and evaluate the students’ activity within the AES. In fact, these systems can be enhanced if tools for supporting teachers in this task are provided. In this paper, we present the experiences with predictive models that have been undertaken to assist the teacher in PDinamet, a web-based adaptive educational system for teaching Physics in secondary education. Although the obtained models are still very simple, our findings suggest the feasibility of predictive modeling in the area of supporting teachers in adaptive educational systems.     

Using second-hand information in collaborative recommender systems

Building recommender systems (RSs) has attracted considerable attention in the recent years. The main problem with these systems lies in those items for which we have little information and which cause incorrect predictions. One accredited solution involves using the items’ content information to improve these recommendations, but this cannot be applied in situations where the content information is unavailable. In this paper we present a novel idea to deal with this problem, using only the available users’ ratings. The objective is to use all possible information in the dataset to improve recommendations made with little information. For this purpose we will use what we call second-hand information: in the recommendation process, when a similar user has not rated the target item, we will guess his/her preferences using the information available. This idea is independent from the RS used and, in order to test it, we will employ two different collaborative RS. The results obtained confirm the soundness of our proposal.     

A recommender agent based on learning styles for better virtual collaborative learning experiences

Almost unlimited access to educational information plethora came with a drawback: finding meaningful material is not a straightforward task anymore. Based on a survey related to how students find additional bibliographical resources for university courses, we concluded there is a strong need for recommended learning materials, for specialized online search and for personalized learning tools. As a result, we developed an educational collaborative filtering recommender agent, with an integrated learning style finder. The agent produces two types of recommendations: suggestions and shortcuts for learning materials and learning tools, helping the learner to better navigate through educational resources. Shortcuts are created taking into account only the user’s profile, while suggestions are created using the choices made by the learners with similar learning styles. The learning style finder assigns to each user a profile model, taking into account an index of learning styles, as well as patterns discovered in the virtual behavior of the user. The current study presents the agent itself, as well as its integration to a virtual collaborative learning environment and its success and limitations, based on users’ feedback.     

Provision of awareness of learners’ emotions through visualizations in a computer interaction-based environment

One of the challenges of intelligent systems for education is to use low-level data collected in computer environments in the form of events or interactions to infer information with high-level significance using artificial intelligence techniques, and present it through visualizations in a meaningful and effective way. Among this information, emotional data is gaining track in by instructors in their educational activities. Many benefits can be obtained if an intelligent systems can bring teachers with knowledge about their learner’s emotions, learning causes, and learning relationships with emotions. In this paper, we propose and justify a set of visualizations for an intelligent system to provide awareness about the emotions of the learners to the instructor based on the learners’ interactions in their computers. We apply these learner’s affective visualizations in a programming course at University level with more than 300 students, and analyze and interpret the student’s emotional results in connection with the learning process.     

Evaluating recommender systems from the user’s perspective: survey of the state of the art

A recommender system is a Web technology that proactively suggests items of interest to users based on their objective behavior or explicitly stated preferences. Evaluations of recommender systems (RS) have traditionally focused on the performance of algorithms. However, many researchers have recently started investigating system effectiveness and evaluation criteria from users?? perspectives. In this paper, we survey the state of the art of user experience research in RS by examining how researchers have evaluated design methods that augment RS??s ability to help users find the information or product that they truly prefer, interact with ease with the system, and form trust with RS through system transparency, control and privacy preserving mechanisms finally, we examine how these system design features influence users?? adoption of the technology. We summarize existing work concerning three crucial interaction activities between the user and the system: the initial preference elicitation process, the preference refinement process, and the presentation of the system??s recommendation results. Additionally, we will also cover recent evaluation frameworks that measure a recommender system??s overall perceptive qualities and how these qualities influence users?? behavioral intentions. The key results are summarized in a set of design guidelines that can provide useful suggestions to scholars and practitioners concerning the design and development of effective recommender systems. The survey also lays groundwork for researchers to pursue future topics that have not been covered by existing methods.     

Practical guidelines for designing and evaluating educationally oriented recommendations

There is a need for designing educationally oriented recommendations that deal with educational goals as well as learners' preferences and context in a personalised way. They have to be both based on educators' experience and perceived as adequate by learners. This paper compiles practical guidelines to produce personalised recommendations that are meant to foster active learning in online courses. These guidelines integrate three different methodologies: i) user centred design as defined by ISO 9241-210, ii) the e-learning life cycle of personalised educational systems, and iii) the layered evaluation of adaptation features. To illustrate guidelines actual utility, generality and flexibility, the paper describes their applicability to design educational recommendations in two different contexts, which in total involved 125 educators and 595 learners. These applications show benefits for learners and educators. Following this approach, we are targeting to cope with one of the main challenges in current massive open online courses, which are expected to provide personalised education to an increasing number of students without the continuous involvement of educators in supporting learners during their course interactions.     

学习网站生成系统的关键技术分析

现代信息技术的发展,网络技术在教育领域的应用,深刻改变着人们的教育观念,并将引发教育内容、教学过程、教学手段和教育体制的根本变革,促进了教育的一场深刻革命。很多学校和企业开始了学习网站建设的实践研究,该文重点对学习网站生成系统的关键技术进行了分析。     

Artificial intelligence in educational assessment: ‘Breakthrough? Or buncombe and ballyhoo?’

Artificial Intelligence is at the heart of modern society with computers now capable of making process decisions in many spheres of human activity. In education, there has been intensive growth in systems that make formal and informal learning an anytime, anywhere activity for billions of people through online open educational resources and massive online open courses. Moreover, new developments in Artificial Intelligence-related educational assessment are attracting increasing interest as means of improving assessment efficacy and validity, with much attention focusing on the analysis of the large volumes of process data being captured from digital assessment contexts. In evaluating the state of play of Artificial Intelligence in formative and summative educational assessment, this paper offers a critical perspective on the two core applications: automated essay scoring systems and computerized adaptive tests, along with the Big Data analysis approaches to machine learning that underpin them.     

Learning to Think and Communicate with Diagrams: 14 Questions to Consider

This paper looks at the particular role which diagrammatic representations, and external representations more generally, play within an educational context. In particular, it considers the way in which the demands on diagrammatic representational systems in educational settings differ with respect to other settings (e.g. professional): in some instances, these demands are increased, while in others, the demands are markedly different.The paper considers three key issues: the question of whether diagrams make certain tasks easier (and whether this is desirable from an educational point of view), the generalisation and transfer of diagrammatic skills once learnt, and the possible problems associated with simultaneously learning domain knowledge and a novel representational system.The paper then considers a number of sub-issues, and concludes by highlighting areas of particular interest for future AI research.