اثربخشی یک سیستم به اشتراک گذاری حاشیه نویسی هوشمند بر آموزش الکترونیکی

Reading is a very important part in learning process. When reading the teaching materials of textbooks in a traditional way, students usually underline the main points and take notes to help memorizing, thinking and understanding the contents of the teaching materials. With the progress of network technology, e-learning has gradually become a new learning trend. However, the digital e-teaching materials of e-learning are always the texts that cannot be changed by students as an easier reading format. In this paper, we propose an algorithm named Expert Keywords Annotation Alignment Algorithm (EKAAA) and based on which we have developed an Intelligent Annotation Sharing System (IASS) as an auxiliary tool for students to read the e-teaching materials. Based on the cluster to which a student belongs, the annotation sharing system adaptively provides the student a suitable sharing model. The models serve as a “scaffolding” to guide the students’ learning, intending to achieve the purposes of auxiliary learning and knowledge sharing. Finally, we use statistics to analyze the effectiveness of the Intelligent Annotation Sharing System on e-learning.

Traditionally, when we are reading the teaching materials of textbooks, we usually have the habit of underlining and notetaking to help ourselves with memorizing, thinking and understanding the contents of the teaching materials. However, with the progress of network technology, e-learning has gradually become a new learning trend. Although the acquisition, transmission and storage of electronic documents enjoy obvious advantages when compared with the traditional paper documents, students find it unavailable to conduct any annotation act on the electronic documents while reading them. However, annotation is a traditional learning strategy commonly used by general students. Therefore, the reading pattern with annotation unavailability is the greatest obstacle to e-learning. Although some websites provide students with single-sided annotation act, such an interactive pattern is of limited help to students. This is because the students of low-score cluster with poorer learning ability are always incapable to rearrange the main points, the contents they have learned and the notes, and the students of high-score cluster are unable to share with other students the annotation process of their reading. Therefore, the students of low-score cluster cannot acquire the knowledge of the students of high-score cluster through the knowledge sharing mechanism. In view of this, the study attempts to develop an Intelligent Annotation Sharing System (IASS) as an auxiliary tool for students to read the e-teaching materials. According to different clusters of students, adaptive annotation sharing patterns are provided to them for learning and sharing knowledge by themselves, hoping to achieve the purpose of adaptive learning. Based on the above phenomena, the study is undertaken with the following aims: (1) Scaffolding theory is employed as the foundation to construct an Intelligent Annotation Sharing System (IASS) as an auxiliary tool and adaptive sharing platform for students to read the teaching materials. (2) Expert Keywords Annotation Alignment Algorithm (EKAAA) is proposed to examine whether the annotation contents of students contain the keywords selected by experts, and evaluate the annotation act of students in a more objective and reasonable way. (3) Taking EKAAA as the foundation and by means of Data Mining, the study establishes adaptive Annotation Patterns, and recommends intelligent annotation sharing model (IASM) to different clusters of students for reference. (4) Statistical methods are employed to analyze different clusters of students. After the students have been guided by IASM, the paper studies whether it is helpful to enhance the learning effects of students.

A complete e-teaching system not only provides suitable teaching materials for students, but is also requested to be a mechanism allowing students to undergo annotation act and online sharing of annotation. Hence, the study develops an Intelligent Annotation Sharing System (IASS) that is suitable for students to use, and can serve as an auxiliary tool for students in reading the teaching materials. The three main contributions deduced from the study are: 1. An Intelligent Annotation Sharing System (IASS) is developed for students as an auxiliary tool for the reading of teaching materials and for knowledge sharing, with an aim to compensate the insufficiency of traditional annotation system. 2. Expert Keywords Annotation Alignment Algorithm (EKAAA) is proposed to inspect whether the annotation contents of students contain the keywords selected by experts in order to rule out the unreasonable annotation contents of students, such as full-text annotation or random annotation, etc. 3. The Annotation Pattern of high-score cluster acquired through the annotation association rules of Data Mining serves as a scaffolding of learning to guide the students of different clusters. Thus, the study also discovers that except the students of “high-score cluster,” having used “Annotation Pattern” to guide their learning, the students of “experimental group” in “medium-score cluster” and “low-score cluster” have significant improvement. Therefore, the researcher further interviewed the students of high-score cluster, and found that most of the students of high-score cluster belonged to field dependence since they had their own ways of learning and less depended on external assistance. Although the results acquired from the statistical analysis of “medium-score cluster” and “low-score cluster” show that “experimental group” has more significant difference than “control group,” the P-value of “low-score cluster” is less than 0.001, whereas the P-value of “medium-score cluster” is 0.037, implying that the students of “low-score cluster” have a greater need of learning guidance by “Annotation Pattern” than the students of “medium-score cluster.” Therefore, when a majority of students encounter difficulties in the process of active construction of knowledge, the learning effects of students resulted from the guidance of adaptive “Annotation Pattern” are significantly different from the learning effects of students without the guidance of adaptive “Annotation Pattern.” Finally, there is one noteworthy thing that after the students of low-score cluster have been guided by “Intelligent Annotation Sharing Model” (IASM), if their learning effects have been significantly enhanced, the instructor can also suggest the students of “low-score cluster” to try to take the IASM of “medium-score cluster” for reference. However, they are not suggested to use the IASM of high-score cluster because the learning of students has to follow in order and advance step by step.