تحلیل مفهوم رسمی برای آموزش الکترونیکی وب معنایی

We capture student interactions in an e-learning community to construct a semantic web (SW) to create a collective meta-knowledge structure guiding students as they search the existing knowledge corpus. We use formal concept analysis (FCA) as a knowledge acquisition tool to process the students virtual surfing trails to express and exploit the dependencies between web-pages to yield subsequent and more effective focused search results. We mirror social navigation and bypass the cumbersome manual annotation of webpages and at the same time paralleling social navigation for knowledge. We present our system KAPUST2 (Keeper and Processor of User Surfing Trails) which constructs from captured students trails a conceptual lattice guiding student queries. We use KAPUST as an e-learning software for an undergraduate class over two semesters. We show how the lattice evolved over the two semesters, improving its performance by exploring the relationship between ‘kinds’ of research assignments and the e-learning semantic web development. Course instructors monitored the evolution of the lattice with interesting positive pedagogical consequences. These are reported as well in this paper.

Building a semantic web (SW) is often hindered by the following two factors: users do not agree on an annotation standard that can be used to extricate web inter-dependencies and/or users feel burdened by the annotation effort. We proposed an alternative in Beydoun, Kultchitsky, and Manasseh (2007), based on indirect social navigation (Dieberger, 1997), to exploit web-pages dependencies using surfing trails left behind. These are not beneficial if individuals surfing the net have different interests, but in a given interest group individuals produce trails that are of interest to the whole group. Our earlier experiments in e-learning in Beydoun et al. (2007) indicated that processing surfing trails left by students using formal concept analysis (FCA) is possible. But lack of crossings between surfing trails lowered the usability of the resultant lattice. Our hypothesis in this paper is that the effectiveness of the resultant conceptual lattice depends on a sufficient complexity of the conceptual lattice itself on the one hand and the following factors on the other hand: the way assignments are set to ensure trails crossings, a reflective learning setting, and a sufficient number of trails. In this paper, we employ our FCA-based system for two consecutive semesters in an American University and using comparative assignments to ensure higher number of trail crossings. The conceptual lattice resultant from the first semester is used as a starting point for further collective development by students in the second semester. The number of crossings is much higher and the experiments confirm that indeed social navigation can be simulated in e-learning settings, and moreover that FCA is suitable to process the trails into a usable semantic web which supports the learning process of students. This paper is organized as follows: Section 2 overviews related work, Section 3 presents the conceptual basis of our FCA approach in e-learning, Section 4 presents our system KAPUST, Section 5 presents our experimental results, Section 6 discusses and analyses these results from both perspectives, technical and pedagogical concluding with a discussion of future work.

Collected results are evidence for suitability of reasoning over user traces using KAPUST. Our FCA algorithm used to construct the matrix table and lattice performed well in our domain. The method we use to query the lattice provides recommendations for the students in a categorized way and that gave the students a way to share their knowledge with their fellow students. Querying for a set of naming keywords where none of the concepts in the lattice structure contains an exact match, we take each keyword individually and leave it to the user to judge, this is like an ordinary keyword search thus not fully benefiting from the conceptual lattice. After semester 1, most concepts in the lattice were at level 2 which is too general. This is due to similarity in keywords and the fact that a new topic, and that a research topic was introduced each week. Deploying KAPUST for another semester a more complex lattice was constructed and comparative research assignments produced a deeper lattice. Students in the following semester had more benefit from the tool, as they searched an existing lattice structure. This illustrated benefits of this approach in an E-Learning environment through knowledge sharing among students across sessions. Pathways in the lattice are automatically captured. When a sufficient number of these is captured, the generated knowledge base is more and more informative to the students. However, in its early development the knowledge base may not be as informative. The interface allows the students the ability to comment on any webpage they visit and these comments are made available to the whole student body. These comments may offer insight and save students’ time, of course these comments may also mislead; in the early stages of the evolution knowledge base, these comments may supersede the utility of the knowledge base to the students. As the knowledge base evolves, it better reflects the holistic view of the group and it becomes more accurate, the comments become less important. The knowledge base evolves as the same related set of webpages is traced (websurfed) more than once by more than one student and the same webpages within the same set are visited by multiple students as well. The evolution and the completion of the knowledge base are topic related, that is it may become mature for one topic but highly inaccurate for another. Formal concept analysis generated conceptual structures provide to the students a user friendly natural presentation of the semantic web evolved. The conceptual lattice structures the data from the most general to the most specific concept. It relates concepts to each other based on their intents and extents, thus providing a means for creating new data that was not directly perceived from the user trails. Moreover, querying the lattice is an easy task and it can vary between approaches to make the most out of the structure. For instance, in our method, if a user is searching for a certain concept, we provide him with a categorized result formed of the upper and lower levels of the concept itself in order to gain more insights about the extents constituting the concept. In its current form, KAPUST provided an e-learning environment which in turn provided the students and the professor involved means of sharing information and experiences without requiring any paper work. Even during the early stage of evolution of the semantic web for the class, the tool contributed to the learning process. It assisted in collecting web pages under the domain of IT, public administration, and political science and created a structure out of these web pages which accelerated the learning of the class. At the pedagological level use of KAPUST merges the reading and writing processes; and a whole new dimension of implicit discourse between students evolves on top of the original documents that lend themselves to new multiple reading pathways, and non-hierarchical and polyarchic structures without ruining the integrity of any original research texts. 6.1. Pedagogical reflections on KAPUST Whilst this paper is about the development and use of an innovative web browser, it is an instructive validation to do an educational exploration of learning using this browser as this browsing activity contributes to student learning within the EU learning environment. The students were set a sequence of comprehension assignments on the topic of IT policies in public administration where the lecturer in charge made available to the students a collection of hypertext body of text based on experts resources. In each of their assignments, they had to browse this body of text to produce written answers for their assignments. This browsing activity is key activity in the environment of synthesis of their assignments. In this process, students collectively learnt and produced KAPUST knowledge base and in some instances left useful notes on webpages for their colleagues. Biggs (1999) distinguishes between problem-based learning (required for maths like subjects) and consumption of large body of information (e.g. in legal studies). Using Biggs classification of university courses (Biggs, 1999), KAPUST is a tool which is not recommended for problem-based courses, it is more suited for courses requiring synthesis of large body of information where the lecturer is able to design assignments and unleash students as a group on the text body using KAPUST. Indeed KAPUST can be seen as an Education Technology (ET) tool with a purpose to provide low level interactivity between students. It enhances presentation of material and overcomes a problem highlighted by Biggs (1999) that students often have problems zooming in on the relevant material on the web. Biggs urges lecturers to ensure that students are taught skills to discriminate between the useful and so useful on the web. He suggests training students to be selective and use keywords that cross-classify. These problems are hugely reduced with KAPUST, as the success of keywords is supported by the effort of the whole class and the relationships between the keywords is automatically discovered by KAPUST. For some assignments the students were required to do comparative analysis between various approaches. By more efficient and more effective searching the students were able to explore deeper and broader in the body of hypertext made available to them more than otherwise possible given their time constraints. Alternatively, for the same time, KAPUST may make it possible for students (as a group) to delve into more difficult text, e.g. research papers, simply because they can do it together as a group. This is clearly an advantage to enrich and break the monotonicity of the presentation in large lecture classes (Biggs, 1999), which is a well-cited reason for computer-based learning (Barker, 2004 and Biggs, 1999). KAPUST is not a typical online discussion which is fundamentally interactive, student–student, teacher–students. Using KAPUST the students rather browse the holistic view of the pathways as the semantic web emerges. They are able to influence its evolution and they are encouraged to allow themselves to be influenced by it. In comparison with a direct online discussion, the result here is slower and perhaps is more inviting for a deeper reflection. The recommendations of KAPUST, based on the pathways of all students are to be taken with a grain of salt by students and students are encouraged to its evolution. As this indirect form of social navigation simulated with KAPUST does not involve direct communication between students, it raises a number of issues: – Confirming or assessing the reliability of any single source [considered in isolation] is not possible. Instead, that is possible with KAPUST by comparing various views on the same pages and also having access to the original data perused by the users. – Good will is helpful, but is not essential. In the student environment, there is no incentive to mislead by any of the participants. – There are no privacy concerns by students who leave behind useful surfing tracks. Association between individuals and webpages is not required and can be destroyed outside an e-learning environment where privacy is of concern and users should be assured of this anonymity to allay any privacy concerns.