Intelligent Social Semantic Collaborative Filtering Tools in an E-learning Contexts Leyla Zhuhadar* and Sebastian Ryszard Kruk** *Knowledge Discovery and Web Mining Lab Department of Computer Engineering and Computer Science University of Louisville, Louisville, KY 40292, USA
[email protected] **Knowledge Hives sp. z o.o. Rokitnikowa 11 81-589 Gdynia, Poland
[email protected] Abstract—This paper presents the usage of the Semantic Digital Library platform, JeromeDL, as knowledge representation of an open-source learning objects repository at Western Kentucky University. The synergistic approach between the Semantic Digital Library and E-learning provides users (online learners) with enhanced information discovery features for learning objects (lectures). In addition, the platform serves as an environment to (a) author learning objects; (b) classify each learning object using proper taxonomy among different libraries, such as DMOZ, ACM, UDC, LOC, or DDC; (c) bookmark sharing and collaborative filtering; and (d) providing natural language query templates. In this study, we discuss our findings with respect to the usability of the platform by online users. This platform is currently running at WKU as a pilot project and has been experimented with online users. Index Terms—Semantic Digital Library, Ontology, E-learning, Information Retrieval
I. I NTRODUCTION Designing an open source repository of learning objects is not an easy task. In 2007, the office of distance learning at Western Kentucky University started an initiative to provide online students with an open source repository of lectures. The platform is named the HyperManyMedia1 repository. This platform is running on a local server2 at WKU3 . Our designing approach is a user-centered design which is driven by users’ needs; for more details, refer to our previous works ([1], [2], [3], [4], [5]). The objective of this design is to provide users with an easy access to online learning objects (LO) in a variety of formats (audio, video, podcast, vodcast, html, pdf, or powerpoint). Over the last two years, the growth of content in this repository became an overload factor for 1 We
proposed this term to refer to any educational material on the Web (hyper) in a format that could be a multimedia format (image, audio, video, podcast, vodcast) or a text format (Webpage, PowerPoint). 2 http://hypermanymedia.wku.edu 3 http://www.wku.edu
users (learners) to find the needed information. We noticed that searching for learning objects in this repository via classical techniques of searching and browsing or through static taxonomies was insufficient. However, Web 2.0 and Web 3.0 introduced new paradigms of tools that provided interoperability between multiple platforms, integration of folksonomies represented as social tagging (“folksonomy is an Internet-based information retrieval methodology consisting of collaboratively generated, open-ended labels that categorize Web content [6]”), social/collaborative bookmarking, dynamic taxonomies, semantic annotations, etc. Therefore, a new vision of our initiative was proposed. The main goal is to keep the interest of our online learning communities in our online learning materials without the need to duplicate the resources; in addition, we provide learners with advanced tools, such as social tagging, social bookmarking, question/answering querying based on natural language, etc. We summarize the outcome of the new architectural design as an architecture that provides dynamic taxonomies and faceted search capabilities. We note that the previous architecture of the HyperManyMedia repository was designed as an application independent and reusable. The platform was designed in a way that we separated the resources (learning objects) from the design and implementation of the platform. This separation enables us to move from platform to platform without duplicating our resources. A reusability concept is considered as a building block in our ongoing architectural design. II. BACKGROUND (S EMANTIC W EB IN E- LEARNING D OMAIN ) Why is there a need for the Semantic Web? The needs have been classified into three categories [7]: (a) Knowledge Management, (b) Web Commerce, and (c) Electronic Business. In our research we are interested is the first category only, i.e., Knowledge Management. In the following sections, the
Figure 1.
HyperManyMedia Open Source Repository Based on a Semantic Digital Library, JeromeDL
following questions will be addressed: How can ontologies be used effectively in E-learning? How could Semantic Web tools be used in E-learning? How do we present the semantics of the context? A. Knowledge Management in E-learning Knowledge Management in E-learning is concerned with designing, maintaining, organizing, and accessing learning objects. These learning objects are either located locally on the University server or distributed all over the Web on open source learning repositories. B. Searching and Extracting Learning Objects What will the Semantic Web add to the current Web? The Semantic Web will change the searching mechanism from keyword matching to query answering, and an ontology will be used to handle the mapping process between documents facilitating the definition and viewing of documents. Documents will be presented semantically [7]. The Semantic Web allows for (a) the reuse of materials in different contexts, and (b) personalization. C. Semantic Web in E-learning Domain “An ontology is an explicit specification and formal specification of conceptualization of a domain of interest [8].” The main goal of using an ontology is to support sharing and reusing of formally represented knowledge in AI systems. To accomplish this, a common vocabulary needed to be defined then used to represent the shared knowledge [8]. Recently, the Semantic Web has evolved as a key technology, bringing new insights and solutions to well documented problems in E-learning. The most challenging process in E-learning is related to the annotation and packaging of the learning content. The current approaches, mostly based on reusable
learning objects and learning designs methods, suffer from the poor and underutilized semi-automated and manual techniques for entering the required formal or informal semantics and metadata. The other challenge in E-learning is the very narrow conceptualizations and algorithms used for modeling of the learners’ profiles. The quest for highly effective and personalized E-learning systems must be based on a detailed specification of behavioral, learning, and systemic parameters that jointly formulate the learners’ model. The personalization must be built on top of well-defined learning contexts and then realized within an Information Retrieval Framework. The research field of Semantic E-learning covers a wide range of research problems. Below, we cover some of the Semantic Web efforts in the context of E-learning. Some work focused on the Educational Semantic Web, i.e., how authoring tools can be designed to provide educational content that is shareable, reusable, and interoperable [9]. This research proposed an ontology-driven authoring tools framework from which the educational platform can benefit. Others argued that an ontology-supported learning process enhances the activities between faculty and students in Web-based learning environments and surveyed the relationship between Artificial Intelligence in Education (AIED) and Web Intelligence (WI). This demonstrated strong evidence that the AIED field can benefit from the core components of WI techniques, such as ontologies, adaptivity, personalization, and software agents [10]. One important aspect of this benefit is that it can enhance the learner’s comfort, especially from a personalization point of view, where WI techniques can be used to create a learner model that can free the learner from the disturbance of manually discovering relevant materials in an ontologysupported learning environment. Others have demonstrated a framework for ontology-enabled annotation and knowledge
Figure 2.
Three-layered Architecture of JeromeDL [16]
management in collaborative learning environments [11]. The proposed framework provided personalization and semantic content retrieval with the personalization aspect expressed using ontologies that provided the relationship between learners and annotated content. These ontologies have been used to discover similar content and collaborators, thus realizing a query-by-annotation retrieval system. Other E-learning Web service architecture presented in [12] can provide students with the following: registration, authentication, tutoring, questionanswer query services, and an annotated feedback. The feasibility of this architecture has been tested through different scenarios in the E-learning domain, with the most interesting one being the capability of the system to provide a semantic annotation of argumentation in student essays. Three different ontologies governed the system: learning materials ontology, annotation schema ontology, and services ontology. A framework for personalized E-learning in the Semantic Web where the hypertext structures were automatically composed using the Semantic Web services is proposed in [13]. Another approach presented in [14] where a semi-automatic ontology extraction is used to create draft Topic Maps. It uses Topic Maps to encode knowledge through the design and implementation of plug-in in TM4L editor. This research exploits the concept of subject identity in learning content authoring. It uses Wikipedia articles as a source for (1) consensual naming, and (2) subject identifiers. This research is implemented in the Topic Maps for E-Learning tool [15]. III. A RCHITECTURAL D ESIGN A. Introduction HyperManyMedia repository consists of 11 departments (English, History, Mathematics, Chemistry, Management, Accounting, Engineering, Social Work, Architecture and Manufacturing Sciences, Communication Disorders, Consumer and
Family Sciences). Currently, we have 64 courses, 7,424 learning objects (lectures), and each learning object represented in seven different formats (text, powerpoint, streamed audio, streamed video, podcast, vodcast, RSS). There is a total of ~51,968 individual learning objects. These materials were created by Western Kentucky University and located on the HyperManyMedia E-learning repository and augmented with external open source resources from MIT OpenCourseWare4 . B. Redesigned Architecture A synergistic approach among the Semantic Digital Library JeromeDL and HyperManyMedia repository was proposed to provide users (online learners) with enhanced information discovery features for learning objects (lectures). The redesigned architecture serves as a platform to (a) author learning objects; (b) classify each learning object employing proper taxonomy using different libraries, such as DMOZ, ACM, UDC, LOC, or DDC; (c) bookmark sharing and collaborative filtering; and (d) provide natural language query templates. The architecture of the Semantic Digital Library, JeromeDL, consists of three components: (1) system (semantic services and social services), (2) content (multimedia resources, dynamic objects, community annotations, and semantic annotations), and (3) users (community and aggregation) [17]. This architecture assures a high level of usefulness, usability, and performance. Our main objective for redesigning HyperManyMedia repository is to provide learners with a social semantic Elearning repository where each resource is described using three types of metadata: structure, learning objects-aware ontologies, and community-aware ontologies. JeromeDL delivers the three types of metadata in one platform; therefore, users are presented with ontological representation of each learning resource. In addition, users are provided with social semantic 4 http://ocw.mit.edu/OcwWeb/web/home/home/index.htm
Figure 3.
HyperManyMedia Open Source Repository Based on a Semantic Digital Libray (JeromeDL)
collaborative filtering which enables learners to actively participate in the process of knowledge representation [16]. In the following section we provide the methodology we pursued to redesign HyperManyMedia repository. IV. I MPLEMENTATION A. Methodology JeromeDL, the Semantic Digital Library, consists of a threelayered architecture of metadata management [16], as shown in Figure 2. 1) We used the bottom layer (Digital Library Services) to represent the HyperManyMedia resources (learning objects); it uses ontology to define each learning object. This method provides flexibility for other services to interact with those resources and to provide links to other resources. 2) The middle layer, the main objective of this layer is to provide bibliography for existing resources in the digital library, such as a book, chapter, article, etc. We modified the usage of this layer to provide the semantic description of the learning materials, such as audio, video, podcast, vodcast, or a text document. Therefore, the main purpose of this layer is to (a) store the resource; (b) deliver metadata about the resource using popular existing format (Dublin Core5 , MARC216 , or BibTEX7 ); (c) manage the resource; (d) information retrieval services, such as semantic search, natural language search, etc.; and (e) provide social networking using FOAF ontology [18]. 5 Dublin
Core: http://dublincore.org/documents/dcq-html/ http://www.loc.gov/marc/bibliographic/ 7 BibTEX: http://www.bibtex.org/
3) The upper layer provides community-oriented services, such as tagging, blogging, and collaborative filtering for the online students. Figure 1 represents the HyperManyMedia platform. The platform is located on a local server8 at Western Kentucky University. The methodology used to construct the learning objects is the following: • Cover: represents a thumbnail picture of the lecture • Abstract: represents a snippet from the lecture • Author information: (author, and/or editor, and/or publisher) • Domains: suggests the taxonomies to which the lecture belongs • Keywords: provides an easy way to search for the learning object • RDF: presents each learning object with its own RDF • Bookmarks: provides methods for social bookmarking • Resource: links each resouras URI (Our main goal was not to duplicate the already existing resources, so we provided a direct link to our learning objects in the HyperManyMedia repository) (for example, Figure 3 represents an instance of adding a resource to the College of History) B. Adding Resources to the Semantic HyperManyMedia Figure 4 describes the process of uploading a resource. This process divided into two sections: 1) Providing general information: In this section, we define a) The digital type of the learning object: This can be one of the following (URI, xslfo, xml, pdf, rtf, or
6 MARC21:
8 http://161.6.105.165:8080/jeromedl/
Figure 4. Uploading a Resource to HyperManyMedia Using the Semantic Digital Libray, JeromeDL (Part-I)
swf). In Figure 4 we define the type as URI and we provide the actual location of the learning object. b) The type of the resource: As we mentioned in section III-A, we predefined 11 types of resources; in this special case, the resource belongs to the History resources and it is a document (lecture). Therefore, we select “History Lectures”. c) Belong to Collection: In this section, we emphasize to which collection from the College of History this resource belongs, more specifically, to which course in History. In this special case, we define it under the course “Western Civilization since 1648”. d) Title: We provide the lecture’s title e) Abstract: A small meaningful snippet from the lecture f) Cover: Thumbnail picture from the real lecture g) Creator, publisher, and editor. 2) Providing additional information: This section is the most important element in defining the resource. Figure 5 illustrates this section: a) Folksonomies: It links the resource to specific taxonomies to which this resoure belongs. JeromeDL provides five different folksonomies libraries from which that we can choose (ACM, UDC, DMOZ, LOC, DDC). This definition is very essential since it is linked to the way the user links the resource to other services in the library. It provides the
Figure 5. Uploading a Resource to HyperManyMedia Using the Semantic Digital Libray, JeromeDL (Part-II)
ontology of this resource. b) Keywords: Users can add keywords that present this resource, such as (most frequent keywords used in the lecture, the name of the professor, the name of the course, etc.) V. E VALUATION A. Usability and Functionality of Search Engines HyperManyMedia is built based on the Semantic Web technologies provided by JeromeDL. Therefore, it supports the enhanced legacy of information and numbers of social features. In addition to the semantic searching [6]. As we noted in section IV-B, our platform defines folksonomies to each resource. Also, in the domain and keywords properties, it defines taxonomies; these taxonomies are defined with controlled vocabulary, such as hasCreator (Leyla Zhuhadar), hasDomain (History), hasKeyword (Western Civilization since 1648, History, Civilization, etc). Therefore, when a user conducts a search for a specific keyword, this information is semantically interpreted and linked to varies resources. The system provides three types of search facets: (a) simple search, (b) advanced search, (c) and semantic search. We examined each one of them as follows: 1) Simple Search Engine: We tested the simple search engine with keywords extracted from the contents of the learning objects. The search engine was able to retrieve documents with high accuracy.
Figure 6.
Advanced Search Engine
(an open source learning objects repository at Western Kentucky University). As the synergistic approach between the Semantic Digital Library, JeromeDL, and E-learning, HyperManyMedia, provides users (online learners) with enhanced information discovery features for learning objects (lectures). In addition, the platform serves as an environment to author the learning objects; classify each learning object using proper taxonomy among different libraries, such as DMOZ, ACM, UDC, LOC, or DDC; and provide bookmark sharing and collaborative filtering (in addition to a natural language query facility). In this study, we discussed our findings with respect to the usability of the platform by online users. R EFERENCES
Figure 7.
Semantic Search Engine
2) Advanced Search Engine: In this type of search, users can search by titles, authors, editors, publishers, dates, etc. Figure 6 illustrates the results retrieved for keywords search “Russian Civil War”, with additional properties (search by title). The retrieved results present the following information: title, authors, abstract, and the URI for the actual document that contains the query term as title. 3) Semantic Search Engine/Natural Language Search Engine: The Semantic search engine provides the user with two types of search: (1) based on Natural Language Query (in this case, additional help is provided to tweak the query, as shown in Figure 7, the user can search the entire library or by publications (resources) written (uploaded by) specific user, or written by friends, etc.), and (2) by RDF Query (in this case the user can choose one of the following query languages, such as SERQL, SRQL, or RDQL). VI. C ONCLUSION We conclude that each faceted search interface serves the purpose for which it is designed, and users were able to adapt quickly to the search process. Overall, this paper presented the usage of the Semantic Digital Library platform, JeromeDL, as knowledge representation for the HyperManyMedia repository
[1] Zhuhadar, L., Nasraoui, O., Wyatt, R.: Dual representation of the semantic user profile for personalized web search in an evolving domain. In: Proceedings of the AAAI 2009 Spring Symposium on Social Semantic Web, Where Web 2.0 meets Web 3.0. (2009) 84–89 [2] Zhuhadar, L., Nasraoui, O., Wyatt, R.: Metadata as seeds for building an ontology driven information retrieval system. Int. J. Hybrid Intell. Syst. 6(3) (2009) 169–186 [3] Zhuhadar, L., Nasraoui, O., Wyatt: Multi-language Ontology-Based Search Engine. In: 2010 Third International Conference on Advances in Computer-Human Interactions, IEEE (2010) 13–18 [4] Zhuhadar, L., Nasraoui, O., Wyatt, R.: Visual Ontology-Based Information Retrieval System. In: Proceedings of the 2009 13th International Conference Information Visualisation, IEEE Computer Society (2009) 419–426 [5] Zhuhadar, L., Nasraoui, O., Wyatt, R.: Multi-model ontology-based hybrid recommender system in e-learning domain. Web Intelligence and Intelligent Agent Technology, IEEE/WIC/ACM International Conference on 3 (2009) 91–95 [6] Kruk, S., McDaniel, B.: Semantic digital libraries. Springer Verlag (2008) [7] Fensel, D., Hendler, J., Lieberman, H., Wahlster, W.: Spinning the semantic Web. MIT Press (2003) [8] Gruber, T.: A translation approach to portable ontology specifications. KNOWLEDGE ACQUISITION 5 (1993) 199–199 [9] Aroyo, L., Dicheva, D.: The new challenges for e-learning: The educational semantic web. Educational Technology & Society 7(4) (2004) 59–69 [10] Devedži´c, V.: Web Intelligence and Artificial Intelligence in Education. Educational Technology & Society 7(4) (2004) 29–39 [11] Yang, S., Chen, I., Shao, N.: Ontology Enabled Annotation and Knowledge Management for Collaborative Learning in Virtual Learning Community. Educational Technology & Society 7(4) (2004) 70–81 [12] Moreale, E., Vargas-Vera, M.: Semantic Services in e-Learning: an Argumentation Case Study. Educational Technology & Society 7(4) (2004) 112–128 [13] Henze, N., Dolog, P., Nejdl, W.: Reasoning and Ontologies for Personalized E-Learning in the Semantic Web. Educational Technology & Society 7(4) (2004) 82–97 [14] Roberson, S., Dicheva, D.: Semi-automatic ontology extraction to create draft topic maps. In: Proceedings of the 45th annual southeast regional conference, ACM New York, NY, USA (2007) 100–105 [15] Dichev, C., Dicheva, D., Fischer, J.: Identity: How To Name It, How To Find It. In: Workshop on I3: Identity, Identifiers, Identification, 16th Intl Conference on World Wide Web, WWW 2007, May 8-12, 2007. (2007) [16] Kruk, S., Cygan, M., Gzella, A., Woroniecki, T., Dabrowski, M.: JeromeDL: The Social Semantic Digital Library. Semantic Digital Libraries 139–150 [17] Kruk, S., Westerki, A., Kruk, E.: Architecture of Semantic Digital Libraries. Semantic Digital Libraries 77–85 [18] Kruk, S., Samp, K., O Nuallain, C., Davis, B., McDaniel, B., Grzonkowski, S.: Search interface based on natural language query templates. In: Proceedings of the poster session of IADIS International Conference WWW/Internet 2006. (2006)
Leyla Zhuhadar received the Ph.D. degree in Computer Engineering and Computer Science from the University of Louisville, Louisville, in 2009. Currently, she is a Research Scientist at Western Kentucky University and an Adjunct Assistant Professor at the Department of Computer Engineering and Computer Science (CECS), at the University of Louisville. Her research interests are in Knowledge Acquisition from the Web, Information Retrieval, Ontology Engineering, Semantic Web, Metadata for Accessible Learning Objects. She designed and implemented two working research platforms in the e-learning domain, HyperManyMedia and the Semantic Repository. She is a member of IEEE, IEEE Women in Engineering, IEEE Computer Society, IEEE Education Society, the ACM, SIGKDD, SIGACCESS, SIGIR, Web Intelligence Consortium (WIC), and the AIED.
Sebastian Ryszard Kruk is the co-founder and CEO of KnowledgeHives.com, a Web 3.0 startup. Previously, he was a PhD student, researcher, and project manager (Corrib.org) affiliated with DERI, National University of Ireland, Galway and the Gdansk University of Technology (GUT). His main areas of interest cover Semantic Web and social networking technologies, digital libraries, knowledge management, information retrieval, security and distributed computing. He published two books on Semantic Digital Libraries. He was invited to give five tutorials (at ICSD, JCDL, ESWC, WWW) on Semantic Digital Libraries and one on tutorials on Web 3.0 (Autumn Meetings of PTI). In 2007, he organized the Irish Digital Libraries Summit and co-organized a Workshop on Web Archiving and NKOS Workshop (at ESWC 2006). He received the best paper award for the paper "Semantically Enhanced Search Services in Digital Libraries" at the International Conference on Internet and Web Applications and Services, 2006.
