Personalized recommendation of related content based on automatic metadata extraction

Nauerz, Andreas; Bakalov, Fedor; König‐Ries, Birgitta; Welsch, Martin

doi:10.1145/1463788.1463795

Cited by 5 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Ontologies may be constructed based on the user's browsing behavior, they may consist of user interests inferred concepts, as in the SMCA-08-11-0399.R2 8 context of web search [57]. Another bottom-up approach in constructing ontologies is based on automatic metadata extraction from folksonomies, user-annotations [58] or tags [59]. For example, user-specific annotation of content may be used to infer user's interests and preferences and used for personalized recommendations of content [58].…”

Section: Discussion and Evaluation Resultsmentioning

confidence: 99%

“…Another bottom-up approach in constructing ontologies is based on automatic metadata extraction from folksonomies, user-annotations [58] or tags [59]. For example, user-specific annotation of content may be used to infer user's interests and preferences and used for personalized recommendations of content [58]. Contrary to the bottom-up approach, the OntobUM user ontology follows a top-down approach based on the IMS LIP specification [60].…”

Section: Discussion and Evaluation Resultsmentioning

confidence: 99%

See 1 more Smart Citation

An Ontology-Based Framework for Modeling User Behavior—A Case Study in Knowledge Management

Razmerita

2011

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

This article focuses on the role of user modeling and semantic-enhanced representations for personalization. The paper presents a generic Ontology-based User Modeling framework (OntobUMf), its components and its associated user modeling processes. This framework models the behavior of the users and classifies its users according to their behavior. The user ontology is the backbone of OntobUMf and has been designed according to the Information Management System Learning Information Package (IMS LIP). The user ontology includes a behavior concept that extends IMS LIP specification and defines characteristics of the users interacting with the system. Concrete examples of how OntobUMf is used in the context of a Knowledge Management System (KMS) are provided. The paper discusses some of the implications of ontology-based user modeling for semantic-enhanced Knowledge Management (KM), and in particular for personal KM. The results of this research may contribute to the development of other frameworks for modeling user behavior, other semantic-enhanced user modeling frameworks or other semantic-enhanced information systems.

show abstract

Section: Discussion and Evaluation Resultsmentioning

confidence: 99%

Section: Discussion and Evaluation Resultsmentioning

confidence: 99%

An Ontology-Based Framework for Modeling User Behavior—A Case Study in Knowledge Management

Razmerita

2011

IEEE Trans. Syst., Man, Cybern. A

View full text Add to dashboard Cite

show abstract

“…Currently, we are working on enhancing NLP support in portals by introducing personalization features using our previous work on semantic user modeling [7], [8] and personalization of portal resources [9]. We believe that portal users can benefit more from this support if the results of NLP tools are tailored to individual users, i.e., to their interests, background, and expertise.…”

Section: Discussionmentioning

confidence: 99%

“…• Images Portlet is designed for displaying images for the 9 Google APIs are used for the geocoding and maps named entities found in the text of content providing portlets. For each detected entity, the portlet can display one or several images fetched from the web.…”

Section: A System Architecturementioning

confidence: 99%

Natural Language Processing for Semantic Assistance in Web Portals

Bakalov

Sateli

Witte

et al. 2012

2012 IEEE Sixth International Conference on Semantic Computing

Self Cite

View full text Add to dashboard Cite

Abstract-Web portals are a major class of web-based content management systems. They can provide users with a single point of access to a multitude of content sources and applications. However, further analysis of content brokered through a portal is not supported by current portal systems, leaving it to their users to deal with information overload. We present the first work examining the integration of natural language processing into web portals to provide users with semantic assistance in analyzing and interpreting content. This integration is based on the portal standard JSR286 and open source NLP frameworks. Two application scenarios, news analysis and biocuration, highlight the feasibility and usefulness of our approach.

show abstract

“…Em [20], foi apresentada uma estratégia semelhante àquela adotada em [23], ao utilizar conjuntos de termos para identificar determinadas entidades representativas em um dado conteúdo. Buscando um sistema de recomendação a partir da interação do usuário em sistemas Web, os autores propuseram um framework para anotação de conteúdos relacionados, em arquivos XHTML, que utiliza serviços de análises de dados não estruturados, tais como UIMA 1 e Calais 2 .…”

Section: Trabalhos Relacionadosunclassified

Metodologia para recomendação e agregação de Objetos de Aprendizagem no padrão SCORM

Neves

Ishitani

Brandão

2016

RBIE

View full text Add to dashboard Cite

A partir de um trabalho de revisão da literatura sobre a utilização do padrão Sharable Content Object Reference Model (SCORM) para composição de conteúdos para e-Learning, identificou-se que, embora amplamente utilizado, seu modelo de metadados para agregação de conteúdos é complexo e difícil de ser utilizado por educadores, desenvolvedores de conteúdo e designers instrucionais. Particularmente, a identificação de conteúdos relacionados entre si, a partir de grandes repositórios, tem sido alvo de consideráveis esforços por parte de pesquisadores em ciência da computação, no sentido da automatização destes processos. Todavia, abordagens anteriores estenderam ou alteraram os metadados definidos pelo SCORM. Diante disso, são apresentados neste artigo os resultados de uma pesquisa experimental na qual foi proposta e avaliada uma metodologia que emprega ontologias, anotação automática de metadados, recuperação de informação e mineração de textos para recomendação automática e agregação de conteúdos relacionados, utilizando o vocabulário da categoria de metadados relation, conforme definida pelo SCORM, sem a necessidade de extensão desses metadados, de realizar alterações no padrão, ou mesmo de implementações específicas nos Sistemas de Gerenciamento de Aprendizagem (SGA). Foi desenvolvido um protótipo de um sistema computacional que aplica a metodologia proposta sobre uma amostragem de objetos de aprendizagem, gerando os resultados para avaliação de sua eficácia. Os resultados foram analisados e avaliados com o apoio de profissionais da educação, que atuam no desenvolvimento de conteúdos para e-Learning, demonstrando que a metodologia proposta é viável e eficaz, produzindo os resultados esperados.

show abstract

Personalized recommendation of related content based on automatic metadata extraction

Cited by 5 publications

References 16 publications

An Ontology-Based Framework for Modeling User Behavior—A Case Study in Knowledge Management

An Ontology-Based Framework for Modeling User Behavior—A Case Study in Knowledge Management

Natural Language Processing for Semantic Assistance in Web Portals

Metodologia para recomendação e agregação de Objetos de Aprendizagem no padrão SCORM

Contact Info

Product

Resources

About