Metadata

This is the schema used by the metadata in the Learning Objects. In the metadata, all the association rules are generated using Tertius Rules. Click here to download a guide of Tertius Rules.

Here are some examples of Tertius Rules generated from the usage data of Learning Objects.

• takenCalculus? = no -> assessment = fail 0.27
• highestMath = precalculus -> assessment = fail 0.25
• takenCalculus? = yes AND assessmentMaxSecOnAPageAboveAvg? = yes -> assessment = pass 0.35

Software

Wrapper

LO Wrapper is developed to surround existing LOs and intercepts user interactions between the user and the Learning Management System (LMS). These user interactions are logged to the external iLOG database. The wrapper also adds metadata created by the iLOG framework to the existing LOs. This is an example of the wrapper used in Learning Object Functions.

MetaGen

The MetaGen framework uses three separate modules for automatic metadata creation: (1) data logging, (2) data extraction, and (3) data analysis. First, the data logging module of MetaGen integrates data from three sources: (1) static LO data, (2) static student data, and (3) user interactions from the LO wrapper. Next, the data extraction module creates the iLOG dataset from the database. Each record in the dataset corresponds to a particular student-LO session. This module uses the Data Imputation component to fill in the missing attribute-values for the records. Finally, the data analysis module uses a multi-step process to generate the metadata. First, this module uses the Feature Selection Ensemble component to select only the most relevant features from the database. This feature subset is then passed Association Rule Miner component which creates useful metadata for the LOs. This module also contains usage statistics specified by the content developer. These statistics are also included as metadata for the LOs. For more information, consult Riley et al. (2009). If you want to download the source code of MetaGen, please email ilog_support@cse.unl.edu.

Here is the figure (Click the figure to enlarge) of the iLOG Framework

Here is the implementation (Click the figure to enlarge) of the function of automatic Learning Object re-uploading using iMacros. Each time metadata of a Learning Object is updated, the application will zip the Learning Object again and upload it to a learning management system. Click here to download the document.

Learning Object Search Engine (Under development)

The Learning Object Search Engine searches and retrieves the Learning Object from online digital libraries based on users' query. It provides two types of search form, the general search form and the advanced search form for the users to specify general keywords and specific content in the metadata in the search query. A set of ranked learning objects will be returned as the results. Users are allowed to upload and deploy new learning objects for metadata collection. All the user behaviors are tracked to model the preference including the preference not specified in the query.