Lecture Notes in Computer Science- P110 pptx

The N of the collection in our case is learning content repository and the parameter n in this formula requires knowledge of all words within the collection that holds the text ma-terial

if it occurs frequently within text, but infrequently in the larger collection The for-mula is shown as follows:

Wij = weight of term Tj in document Di Tfij = frequency of term Tj in document Di

N = number of documents in collection

n = number of documents where Tj occurs at least once The documents of the formula must be modified as a individual package The N of the collection in our case is learning content repository and the parameter n in this formula requires knowledge of all words within the collection that holds the text ma-terial of interest

For calculating each word’s importance, we need to construct a dictionary that con-tains the information of how frequently it occurs across course packages in learning content repository

Fig 3 Construct a dictionary of weighted words

Figure 3 shows each step of constructing the dictionary of weight words from our learning content repository It begins from the content parser which fetches learning courses from the repository and extracts all the words from each course, unless the frequent stopped words such as “is”, “are”, “and”, etc

Then, each uniquely extracted word will be tagged by a counter module with a number and keeps track of the number of courses where the word occurred Once the counting is complete, the words that occurred less than a chosen threshold value across all the courses are eliminated The value is required to be tuned because it depends on the size of the repository It would conserve too many insignificant words

if the value is too large On the contrary, it is probable to remove rare words that may quite important and have the potential to become keywords The remaining words are passed through a spell checker and finally, words that have the same grammatical stem are combined into single dictionary entries For example adaptive and adapted, would share an entry in the dictionary Accordingly, the size of the dictionary will continually shrink

When the significant keywords must be extracted from a PU, all the words in the

PU are stemmed For each word, the module will search the dictionary to discover the frequency with which the word occurs in the course The word’s frequency within the course package that contains the PU is found by scanning the course package in real time Finally, these values are computed for the word’s TF/IDF weight Words with a weight beyond the chosen threshold are selected as significant

A special situation arises when a word is not in the dictionary, either because it was discarded during our dictionary-pruning phase or it was a specific word that has never been shown in other learning contents Such words are probable more rare than any of ones that survived pruning and were included in the dictionary Therefore these words are considered as special keywords in this course and as important as any of the words

we retained

Finally, notice that our implementation directly extract and store the words as im-portant ones if they are somehow highlighted with bold, italic, different color, specific punctuation marks, etc

3.2.2 Summary Sentence Extraction

Rather than summarizing the input text automatically, we can only pick up a few significant sentences to represent the text summary Because of the previously re-vealed keywords in a PU a user intends to explore the portion of the content’s sum-mary due to his/her interesting A sentence will be intuitively considered significant if

it contains one or more keywords Therefore, the method of extracting summary sen-tences is based on keyword extraction result

Fig 4 Processing of the learning content adaptation

The procedure of summary sentence extraction is as shown in figure 4 Each sen-tence in a PU will be extracted by a sensen-tence dividing manager, and then passed to the summary generator Meanwhile, the previous extracted keywords are also passed through the summary generator in which each sentence will be extracted and listed in order if it contains the matched keywords

Although the method selects the summary sentences rapidly, the number of sum-mary sentences becomes unpredictable due to the uneven distribution of keywords within a text The extreme cases occurred under the following situations;

1 Only one summary sentence identified if all keywords are included in a sentence

2 The summary sentences are exactly the same as the original text if the keywords are equally distributed in each original sentence We have found a few extreme cases in our implementation, but most others are acceptable

3.3 Image Adaptation Model

Similarly, image adaptation replies on comparing its size to a SU’s Recall the defini-tion of SU It is a rectangle displaying unit and its presentadefini-tion area is the same as a physical screen area of required handhelds An image may not be able to adapt its size

to perfectly match the proportion of a SU and reside in it Hence, a large image (its height and width are all exceed a PU’s) might be shrunk proportionately until its width is fit to display in a PU without additional horizontal scrolling action The en-tire adapted content will have the default displaying in a single column where vertical scrolling for browsing is necessary, so the height of a image beyond a SU’s is accept-able Such that the height of a PU is consequently extended for the image in our im-plementation Accordingly, a small image will be enlarged proportionately until its width, is at least fit, to display in a PU without additional scrolling actions

3.4 Presentation Adaptation Model

The presentation adaptation mode provides two main functions for user to reedit the content’s layout One is allowing users to pick up PUs to delete, the other is let users rearrange PUs’ position manually The procedure is as illustrated in figure 3.3 After the previous automatic adaptation, each PU should contain appropriate displaying content-content that has either been adapted or not A few PUs might be required to

be eliminated, because they may present relatively insignificant objects such as pic-tures decorated only for aesthetic purposes in its original content Besides, users may decide to delete certain PUs considered unnecessary for learning according to their editing experience, and consequently reduce the content’s size On the other hand, the default adapted layout rearranges PUs in an orderly single column presentation Lari Kärkkäinen [11] mentioned a design guideline for a small display screen; put as much important content as close to the top of the hierarchy as possible Each PU is a unit of presentation, such that the PU deployment manager allows users to manually rear-range each PU’s displaying position to satisfy user’s specific requirement and con-struct a preference layout

3.5 Multi-version Course Package

The purpose of the authoring tool is producing the adapted content and appropriately displaying it on specific mobile learning platforms Therefore after the editing phase, the author may create plural content versions such as pocket PC version and smart-phone version The authoring tool allows the author to save each version as an indi-vidually new SCORM course package or integrate all related versions adapted from the same content as a Common Cartridge course package

The IMS Common Cartridge defines a profile for the use of four following specifi-cations which have been widely implemented and in use across the community

z IEEE LOM v1.0[IEEE LOM, 05]

z IMS Content Package v1.1.4[CP, 04]

z IMS Question & Test Interoperability v1.2.1[QTI, 03]

z SCORM 1.2/2004 [SCORM]

The Common Cartridge can support various resource types and also be able to in-clude plural content packages such as SCORM Therefore, the authoring tool utilizes the significant characteristic of Common Cartridge to compose a multi-version course package The figure 5 shows the Common Cartridge file structure having a learning application object folder that includes three different SCORM course versions for corresponding learning platforms: pocket PC, Smartphone and regular PC

Fig 5 Multi-version course package

4 Implementation

We implemented the content adaptation Tool as a web-based application with Ajax and Microsoft NET framework technologies In figure 6, the block 2 allows the user uploading a SCORM-compliant course that is composed of html-based contents then block 1 lists the current courses are ready to execute adaptation process The uploaded course will be saved at our backend server that is responsible for conducting

Fig 6 Uploading learning contents to on-line

adaptation application

Fig 7 Adapting Content according to the

pocket PC template

the entire adaptation process The block 3 shows there are two adaptation templates

we have currently developed; the pocket PC version and the Smartphone version The user only needs to click on the icon to decide which adaptation process begins The block 4 shows the original content page and block 5 displays the aggregation tree of this course

The system will automatically accomplish the adaptation requirement according to the parameter configure of the template Figure 7 demonstrates the html-based content has been adapted properly to be displayed in a PU and arranged by a default singular column layout in block 2 Next, users can manually delete the PUs, which contain relatively significant contents that have to be determined by users themselves The adaptation result relies on configures of the template parameters as shown in the block

1 Users can adjust the adaptation parameters, including the value of the TID, size of a

PU and PU rearrangement panel for changing the layout manually The block 3 lists the included resources information of the adapted page

Fig 8 An adaptive content delivering architecture