基于Web使用挖掘的个性化推荐系统

Web使用模式挖掘是对用户浏览Web后在服务器日志上所留信息的数据挖掘。讨论了挖掘中常用技术及流程,并提出一种Web使用模式挖掘体系结构,介绍了系统的工作原理,对系统设计中的推荐算法等关键技术作了详细讨论。关     

An empirical study of using sequential behavior pattern mining approach to predict learning styles

The learning style of a learner is an important parameter in his learning process. Therefore, learning styles should be considered in the design, development, and implementation of e-learning environments to increase learners’ performance. Thus, it is important to be able to automatically determine learning styles of learners in an e-learning environment. In this paper, we propose a sequential pattern mining approach to extract frequent sequential behavior patterns, which can separate learners with different learning styles. In this research, in order to recognize learners’ learning styles, system uses the Myers-Briggs Type Indicator’s (MBTI). The approach has been implemented and tested in an e-learning environment and the results show that learning styles of learners can be predicted with high accuracy. We show that learners with similar learning styles have similar sequential behavior patterns in interaction with an e-learning environment. A lot of frequent sequential behavior patterns were extracted which some of them have a meaningful relation with MBTI dimensions.     

两种协同过滤推荐算法的比较研究

web2.0的出现使得互联网中的数据以几何级数的形式增长,如何在浩如烟海的信息海洋中找到自己需要的内容是当前人们面临的一个挑战性问题,信息推荐系统便是为解决这个问题而出现的,而协同过滤算法是推荐系统中用途最广的一种算法.本文对基于用户的协同过滤算法和基于项目的协同过滤算法进行了介绍,然后利用Movielens中的影片数据对这两种算法的性能进行了比较,结果发现基于项目的协同过滤算法在影片信息推荐中要优于基于用户的协同过滤算法.     

人工智能视域下协同过滤推荐系统的工程训练平台

在培养人工智能类相关工科专业学生的工程综合创新能力中,为了解决学生对复杂智能工程抽象理论理解困境,提出以构建人工智能典型内核算法应用的协同推荐系统为工程综合创新实践教学平台。介绍了人工智能的相关背景,针对本科阶段人工智能复杂工程模拟教育实践特点及存在的问题,进行建设操作演示型、参与设计型以及探索创新型的系列单元实际训练项目;通过详细分析几种典型协同推荐内核算法的优劣,展示获取大量数据样本的平台视觉部分、演示基于物品的图片或用户脸部信息识别的动态分拣部分,可以让学生能够直观学习人工智能技术应用情况。通过该平台阶梯式的实践教学引导和推进,提高学生科技实践创新意识和实践动手能力。     

The effect of recommendation systems on Internet‐based learning for different learners: A data mining analysis

A general challenge facing Internet‐based learners is how to identify information objects which are helpful in expanding their understanding of important information in a domain. Recommendation systems may assist learners in identifying potentially helpful information objects. However, the recent literature mainly focuses on the technical performance, rather than on how recommendations support searching in educational contexts. This study thus investigates how recommendation systems may influence the searching behaviors and strategies of different learners, when they are used with a mind map. The results suggested two main different searching behavioral patterns, namely focused searchers and broad searchers. It is found that the recommendations may influence the searching behaviors of the two types of searchers in different ways. For the focused searchers, the recommendations may support these searchers to expand their keywords to explore the domain. Regarding the broad searchers, they did not rely on the computer recommendations. However, the mind map interface applied along with the recommendations may support them in monitoring their searching processes. Online Information Searching Strategies Inventory (OISSI) was applied to examine the participants' perceptions of how students applied information searching strategies. The results of OISSI support that both types of searchers perceived a higher level of searching strategies when they search with the recommendation system and mind maps.     

Capturing temporal and sequential patterns of self-, co-, and socially shared regulation in the context of collaborative learning

This study examined how temporal sequences of regulated learning events, such as types and processes of regulated learning, emerge during different stages of collaborative learning. Earlier research has focused on individual learning and not on the captured temporal sequences of regulation in collaborative learning. The data were collected during a two-month math didactics course taken by teacher education students who collaborated in three member groups. Twenty-two hours of video data were collected to follow how sequences of regulated learning events, along with task execution, emerged within the six groups as their collaboration advanced. The data were analyzed using qualitative content analysis and lag sequential analysis. The results showed that the groups engaged mostly in co-regulated planning and monitoring. Temporal analysis showed that collaborative interactions focusing on task execution promoted socially shared planning, indicating that task execution provided grounding for socially shared planning and regulation to occur. The sequential analysis illustrated that metacognitive monitoring played a facilitative role in the progress of task execution.     

Development of a mobile learning system based on a collaborative problem-posing strategy

In this study, a problem-posing strategy is proposed for supporting collaborative mobile learning activities. Accordingly, a mobile learning environment has been developed, and an experiment on a local culture course has been conducted to evaluate the effectiveness of the proposed approach. Three classes of an elementary school in southern Taiwan participated in the experiment. One class was the experimental group who learned with the problem-posing-based mobile learning approach, while the other two classes were the control groups who learned with the conventional mobile learning approach and the traditional problem-posing approach, respectively. The experimental results show that the new approach not only improved the students' learning achievement, but also promoted their local culture identity and group learning self-efficacy.     

基于社交网络的异步协同学习系统的设计

从分析异步协同学习中的交互行为出发,针对社交网络信息过载,内容难以沉淀等问题,提出基于社交网络实现异步协同学习系统的设计.其中包括群体交互方式的设计,协同推荐算法设计,支持概念图的内容模型设计等.     

Facilitating effective digital game-based learning behaviors and learning performances of students based on a collaborative knowledge construction strategy

Researchers have recognized the potential of educational computer games in improving students’ learning engagement and outcomes; however, facilitating effective learning behaviors during the gaming process remains an important and challenging issue. In this paper, a collaborative knowledge construction strategy was incorporated into an educational computer game to facilitate students’ knowledge sharing and organizing during the game-based learning process. An experiment was conducted to examine the students’ learning behavioral patterns, group efficacy, and problem-solving awareness. The experimental results revealed that the proposed approach improved the students’ learning achievements and awareness of problem-solving. Moreover, from the analysis of the students’ behavior sequences, it was found that, with the collaborative knowledge construction mechanism, the students revealed significantly more aggressive learning behavioral patterns, such as “comparing and observing the learning targets” and “seeking clues and answers” during the gaming process. This implies that integrating the collaborative knowledge construction mechanism into the gaming process has great potential for helping students effectively learn and organize knowledge as well as fostering their awareness of applying the acquired knowledge to dealing with problems.     

Design,development, and implementation of electronic learning environments for collaborative learning

Developments in society and business, and related changes in higher education and lifelong learning, require educators and educational designers or technologists to rethink education. Examples of such changes are the growing importance of achieving complex learning, the integration of learning and work in education, and the need for improved flexibility with regard to time, place, and individual needs. These changes cannot simply be responded to by adding technological solutions implemented according to existing educational approaches. Instead, an integrated view of e-learning is necessary, characterized by the combination of pedagogical, technical, social, and organizational factors. This two-part special issue elaborates on the different characteristics of integrated e-learning, from design through future topics for research. He would like to give special thanks to Jan Elen and Brent Wilson, who took on the task of reviewing and discussing all of the contributions, both at AECT 2003 in Anaheim and for this issue, and J. Michael Spector, Development Editor of this journal, for his faith in all of us.     

Appropriating roles and relations of power in collaborative learning

Using situated social practice theories to investigate classroom interactions highlights the mutually constitutive nature of students’ activity and classroom practices. Combined with examination of the circulation and techniques of power, students’ appropriation of roles and redistribution of power is illuminated. In this case study, a teacher’s hierarchical collaborative learning system spread rights to exercise power differentially among students. Analyses revealed the ways in which students appropriated that structure to construct a more egalitarian system, as well as the inherent tensions and contradictions that accompanied that appropriation. Their reproduction and transformation of roles and power in the collaborative learning system afforded opportunities to engage as active agents; to participate in the construction of knowledge, skills and practices; and to contribute meaningfully to the social and academic life of the classroom. The hope is to contribute to theory and practice in a way that addresses the complexity of collaborative learning and resists simplistic adoptions that may undermine student learning and agency.     

A knowledge based system for the flexible production and delivery of learning material

An Interactive Learning and Course development Environment (ILCE) is presented, which aims to enhance the flexibilization of a course in terms of tailoring it to the needs and requirements of individual students. The heart of ILCE forms a repository of units of learning material. The repository consists of a domain model, a semantic network of the content of a subject domain which is covered by the learning material. This model serves as an abstract representation of the units of learning material. The construction of a course is defined as the selection of a subset of the domain model. Attributes are used to express student characteristics and are linked to the domain model as variables. By adding if/then rules to the domain model, the consistency and the completeness of a selection is preserved. The building environment is used by a course team to fill a repository by designing, producing and revising units of learning material in accordance with the proposed knowledge representation scheme. The design approach a course team has to adopt focuses on building a course model next to the design of the learning material. This design approach is illustrated with examples taken from the ILCE prototype.     

Effects of group experience and information distribution on collaborative learning

Instructional Science - Collaborative learning is a widely used instructional technique, but factors determining its effectiveness still are unclear. Cognitive load theory was used to examine the...     

Wiki和QQ在网络协作学习中的作用

网络协作学习中人际交互畅便与否影响成员间的协作深度,也在很大程度上决定了网络协作学习的效果.本文首先分析了wiki和QQ的功能,然后探讨了二者对促进网络协作学习中人际交互的作用.     

基于行动导向的协同学习在高职公共英语合班教学中的应用

高职英语课程旨在培养学生实际运用语言的能力,增强学生人际沟通和解决问题的能力。在英语教学中采用行动导向教学法并通过协同学习的教学组织形式满足该课程的要求。本文旨在将行动导向和协同学习理念引入到英语合班教学中,以解决公共英语教学中课堂互动的困境,促进师生的共同提高。     

Decoding learning in law: collaborative action towards the reshaping of university teaching and learning

At the University of the Free State (UFS) in South Africa, professional development is characterised by its focus on the advancement of scholarly teaching in the disciplines. Practices followed are informed by the scholarship of teaching and learning movement. Within learning communities, special attention is given to the motivational conditions for optimal development, which are intentionally and collaboratively created or enhanced. An action research approach is adhered to, with action learning always an underlying ingredient. The approach has already shown promising signs in advancing personal growth and scholarly teaching practices among lecturers in the Decoding Learning in Law project. The decoding idea originated in the USA and follows a process of identifying and addressing the discipline-specific learning problems of undergraduate students. As precursor to the more formal phase of decoding, the Centre for Teaching and Learning at the UFS has embarked on a process of empowering a group of lecturers in law to address the challenges they experience in their teaching environment. During meetings and workshops, the members of the newly established learning community act as collaborators in the construction of new knowledge on the theory and practice of good teaching and learning (with a special focus on student engagement); they reflect critically on obstacles in their own courses and take part actively in conversations on the application of innovative strategies in law teaching. Special attention is given to the use of educational technology. In the project, development of relevant technological skills was preceded by a technology-needs survey and discussions in which prevailing perceptions about the use of technology in law education were brought to light. Although the project is still in its first year, the motivational context of community and collaboration has already given rise to a synergy that promises to reshape the teaching and learning environment in law at the UFS. In an informal way, progress has also been made with the decoding process of identifying “bottlenecks” in the teaching and learning of law at the institution.     

Understanding the mediating effect of learning approach between learning factors and higher order thinking skills in collaborative inquiry-based learning

Educational technology research and development - Collaborative inquiry-based learning (CIBL) is a notable instructional method used to nurture students’ higher order thinking skills. Few...     

Differential effects of problem-solving demands on individual and collaborative learning outcomes

The effectiveness and efficiency of individual versus collaborative learning was investigated as a function of instructional format among 140 high school students in the domain of biology. The instructional format either emphasized worked examples, which needed to be studied or the equivalent problems, which needed to be solved. Because problem solving imposes a higher cognitive load for novices than does studying worked examples it was hypothesized that learning by solving problems would lead to better learning outcomes (effectiveness) and be more efficient for collaborative learners, whereas learning by studying worked examples would lead to better learning outcomes and be more efficient for individual learners. The results supported these crossover interaction hypothesis. Consequences of the findings for the design of individual and collaborative learning environments are discussed.     

Detecting substance-related problems in narrative investigation summaries of child abuse and neglect using text mining and machine learning

BackgroundState child welfare agencies collect, store, and manage vast amounts of data. However, they often do not have the right data, or the data is problematic or difficult to inform strategies to improve services and system processes. Considerable resources are required to read and code these text data. Data science and text mining offer potentially efficient and cost-effective strategies for maximizing the value of these data.ObjectiveThe current study tests the feasibility of using text mining for extracting information from unstructured text to better understand substance-related problems among families investigated for abuse or neglect.MethodA state child welfare agency provided written summaries from investigations of child abuse and neglect. Expert human reviewers coded 2956 investigation summaries based on whether the caseworker observed a substance-related problem. These coded documents were used to develop, train, and validate computer models that could perform the coding on an automated basis.ResultsA set of computer models achieved greater than 90% accuracy when judged against expert human reviewers. Fleiss kappa estimates among computer models and expert human reviewers exceeded .80, indicating that expert human reviewer ratings are exchangeable with the computer models.ConclusionThese results provide compelling evidence that text mining procedures can be a cost-effective and efficient solution for extracting meaningful insights from unstructured text data. Additional research is necessary to understand how to extract the actionable insights from these under-utilized stores of data in child welfare.