Towards personalization in digital libraries through ontologies

Ferrán-Ferrer, Núria; Mor, Enric; Minguillón, Julià

doi:10.1108/01435120510596062

Cited by 29 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Navigational data between fellow researchers can be considered for giving importance to a particular page [11]. Two types of behaviour on users navigation are identified; exploratory navigation and goal-oriented navigation.…”

Section: ) Navigational Historymentioning

confidence: 99%

Re-ranking for personalization using concept hierarchy in DL environment

Potey

Pawar²,

Sinha

2013

2013 15th International Conference on Advanced Computing Technologies (ICACT)

View full text Add to dashboard Cite

In Digital Library (DL) system, users interact with the system to search for books or research papers. Users can search through metadata or search for information in the pages by querying using keywords. In both cases, a huge amount of results are returned; however, the relevant ones to the user are not often amongst the top few. Re-ranking of the search results based on the user's interest has received wide attention in information retrieval. This work presents extending conventional search engine to searching digital library data of user's interests. The proposed system improve information access by building knowledge about a user, acquired using the user's interaction with the system, in order to customize information access. User profiling is done using a hybrid approach by taking into consideration login details and click-through data. This system mapping framework automatically maps Dmoz Open Directory Project (ODP) topics to users' interests and takes advantage of manually edited data available in ODP, to categorize and personalize search results, according to user interests. Reranking of the results is done based on user interests. This makes it easy to find relevant DL pages faster than normal search engines. Performance has been evaluated for online DL systems. System's performance improves by 16.55% if the average per query is calculated and approximately 10% if per user average is calculated over baseline (Google CSE) after re-ranking.

show abstract

Section: ) Navigational Historymentioning

confidence: 99%

Re-ranking for personalization using concept hierarchy in DL environment

Potey

Pawar²,

Sinha

2013

2013 15th International Conference on Advanced Computing Technologies (ICACT)

View full text Add to dashboard Cite

show abstract

“…The concept of ontology introduced by the Semantic Web is a promising path to extend DL formalisms with meaningful annotations (Kruk, Decker, & Zieborak, 2005). Several authors have proposed ontologies for describing the relationships between all the elements which comprise a DL scenario (Ferrán, Mor, & Minguillón, 2005) which go beyond different standards of DLs description formats such as MARC21, Dublin Core and BibTeX.…”

Section: Digital Libraries: Been There Done Thatmentioning

confidence: 99%

Digital libraries and Web 3.0. The CallimachusDL approach

García-Crespo

Gómez-Berbís

Colomo‐Palacios

et al. 2011

Computers in Human Behavior

View full text Add to dashboard Cite

a b s t r a c tThe constantly increasing volume of information available on the Internet is changing the forms of clas sification and access to data. Given the immense collection of information stored on the Internet, digital libraries constitute a fundamental subject of research. Among the challenges of classifying, locating and accessing knowledge in digital libraries tackling with the huge amount of resources the Web provides, improving digital libraries by means of different strategies, particularly, using semantics remains a prom ising and interesting approach. In this paper, CallimachusDL is presented, a semantics based digital library which provides faceted search, enhanced access possibilities and a proof of concept implementa tion. CallimachusDL represents a novel approach to digital libraries, integrating social web and multime dia elements in a semantically annotated repository. The results of the implementation indicate that the features proposed in CallimachusDL are encouraging and extendable in the use of digital libraries.

show abstract

“…Following the ideas presented in Ferran et al (2005), we propose to use an ontology for describing the learning process, as the core of the intelligent tutoring system. This ontology will use other sub-ontologies for handling all the interactions with the learning object repository, the interactions with other services and the user profiles.…”

Section: Usage Data Harvesting and Analysismentioning

confidence: 99%

Enriching e‐learning metadata through digital library usage analysis

Ferrán-Ferrer

Casadesús

Krakowska

et al. 2007

The Electronic Library

Self Cite

View full text Add to dashboard Cite

PurposeIn this paper we propose an evaluation framework for analyzing learning objects usage, with the aim of extracting useful information for improving the quality of the metadata used to describe the learning objects, but also for personalization purposes, including user models and adaptive itineraries. MethodologyWe present experimental results from the log usage analysis during one academic semester of two different subjects, 350 students. The experiment looks into raw server log data generated from the interactions of the students with the classroom learning objects, in order to find relevant information that can be used to improve the metadata used for describing both the learning objects and the learning process. FindingsPreliminary studies have been carried out in order to obtain an initial picture of the interactions between learners and the virtual campus, including both services and resources usage. These studies try to establish relationships between user profiles and their information and navigational behavior in the virtual campus, with the aim of promoting personalization and improving the understanding of what learning in virtual environments means. Research limitationsDuring the formal learning process, students use learning resources from the virtual classroom provided by the academic library, but they also search for information outside the virtual campus. Not all of these usage data are considered in the model we propose. Further research needs to be done in order to get a complete view of the information search behavior of students for improving the users' profile and creating better personalized services. Practical implicationsIn this paper we suggest how a selection of fields used in the LOM standard could be used for enriching the description of learning objects, automatically in some cases, from the learning objects usage performed by an academic community. OriginalityEver since the beginnings of libraries, they have been a "quiet storage place". With the development of digital libraries, they become a meeting place where explicit and implicit recommendations about information sources can be shared among users. Social and learning process interactions, therefore, can be considered another knowledge source.

show abstract

Towards personalization in digital libraries through ontologies

Cited by 29 publications

References 15 publications

Re-ranking for personalization using concept hierarchy in DL environment

Re-ranking for personalization using concept hierarchy in DL environment

Digital libraries and Web 3.0. The CallimachusDL approach

Enriching e‐learning metadata through digital library usage analysis

Contact Info

Product

Resources

About