e-Learning Blog Rotating Header Image

semantic

[publication] Social Semantic Search: A Case Study on Web 2.0 for Science #semanticweb #tugraz

The outcome of the research work of Laurens and Selver got published now in the International Journal on Semantic Web and Information Systems (IJSWIS) using the title Social Semantic Search: A Case Study on Web 2.0 for Science.

Abstract:

When researchers formulate search queries to find relevant content on the Web, those queries typically consist of keywords that can only be matched in the content or its metadata. The Web of Data extends this functionality by bringing structure and giving well-defined meaning to the content and it enables humans and machines to work together using controlled vocabularies. Due the high degree of mismatches between the structure of the content and the vocabularies in different sources, searching over multiple heterogeneous repositories of structured data is considered challenging. Therefore, the authors present a semantic search engine for researchers facilitating search in research related Linked Data. To facilitate high-precision interactive search, they annotated and interlinked structured research data with ontologies from various repositories in an effective semantic model. Furthermore, the authors‘ system is adaptive as researchers can synchronize using new social media accounts and efficiently explore new datasets.

[Preview @ Journal’s Homepage]

[Preview @ ResearchGate]

Reference: De Vocht, L., Softic, S., Verborgh, R., Mannens, E., & Ebner, M. (2017). Social Semantic Search: A Case Study on Web 2.0 for Science. International Journal on Semantic Web and Information Systems (IJSWIS), 13(4), 155-180. doi:10.4018/IJSWIS.2017100108

[publication] ResXplorer: Revealing relations between resources for researchers in the Web of Data #science #tugraz

Our publication about „ResXplorer: Revealing relations between resources for researchers in the Web of Data“ is now online available – enjoy the results of a very increasing research field.

Abstract:

Recent developments on sharing research results and ideas on the Web, such as research collaboration platforms like Mendeley or ResearchGate, enable novel ways to explore research information. Current search interfaces in this field focus mostly on narrowing down the search scope through faceted search, keyword matching, or filtering. The interactive visual aspect and the focus on exploring relationships between items in the results has not sufficiently been addressed before. To facilitate this exploration, we developed ResXplorer, a search interface that interactively visualizes linked data of research-related sources. By visualizing resources such as conferences, publications and proceedings, we reveal relationships between researchers and those resources. We evaluate our search interface by measuring how it affects the search productivity of targeted lean users. Furthermore, expert users reviewed its information retrieval potential and compared it against both popular academic search engines and highly specialized academic search interfaces. The results indicate how well lean users perceive the system and expert users rate it for its main goal: revealing relationships between resources for researchers.

[Link to full arcticle @ Journal Homepage]

[Link to full article @ ResearchGate]

Reference: De Vocht, L., Softic, S., Verborgh, R., Mannens, E., Ebner, M. (2016) ResXplorer: Revealing relations between resources for researchers in the Web of Data. Computer Science and Information Systems. (doi:10.2298/CSIS151028031D)

[publication] Finding and Exploring Commonalities Between Researchers Using the ResXplorer

Our publication about „Finding and Exploring Commonalities Between Researchers Using the ResXplorer“ at this year HCII conference in Crete, Greece is now online available.
Abstract:

Researcher community produces a vast of content on the Web. We assume that every researcher interest oneself in events, persons and findings of other related community members who share the same interest. Although research related archives give access to their content most of them lack on analytic services and adequate visualizations for this data. This work resides on our previous achievements we made on semantically and Linked Data driven search and user inter- faces for Research 2.0. We show how researchers can find and visually explore commonalities between each other within their interest domain, by introducing for this matter the user interface of “ResXplorer”, and underlying search infrastructure operating over Linked Data Knowledge Base of research resources. We discuss and test most important com- ponents of “ResXplorer” relevant for detecting commonalities between researchers, closing up with conclusions and outlook for future work.

Reference: Softic, S., De Vocht, L., Mannens, E., Van de Walle, R., Ebner, M. (2014). Finding and Exploring Commonalities Between Researchers Using the ResXplorer. Learning and Collaboration Technologies. Technology-Rich Environments for Learning and Collaboration. Panayiotis, Z., Ioannou, A. (Ed.) Lecture Notes in Computer Science, Volume 8524. Springer, pp. 486-494

[presentation] Finding and Exploring Commonalities between Researchers Using the ResXplorer

Our presentation at this year HCII Conference in Crete, Greece about „Finding and Exploring Commonalities between Researchers Using the ResXplorer“ is now online available – enjoy the slides 🙂

[publication] A Search Interface for Researchers to Explore Affinities in a Linked Data Knowledge Base

Our publication about „A Search Interface for Researchers to Explore Affinities in a Linked Data Knowledge Base“ at this year International Semantic Web Conference (ISWC 2013) described the research work of our PhD-students Laurens and Selver. The application is called ResXplorer and can be tested here.
Abstract:

Research information is widely available on the Web. Both as peer-reviewed research publications or as resources shared via (micro)blogging platforms or other Social Media. Usually the platforms supporting this information exchange have an API that allows access to the structured content. This opens a new way to search and explore research information. In this paper, we present an approach that visualizes interactively an aligned knowledge base of these resources. We show that visualizing resources, such as conferences, publications and proceedings,expose anities between researchers and those resources. We characterize each anity, between researchers and resources, by the amount of shared interests and other commonalities

Reference: De Vocht, L., Mannes, E., Van de Walle, R., Selver, S., Ebner, M. (2013) A Search Interface for Researchers to Explore Affinities in a Linked Data Knowledge Base. Proceedings of the ISWC 2013 Posters & Demonstrations Track a track within the 12th International Semantic Web Conference (ISWC 2013). Blomqvist, E., Groza, T. (ed.) Vol-1035, pp. 21-24, ISSN 1613-0073
[Full Article]

[publication] Monitoring Learning Activities in PLE UsingSemantic Modelling of Learner Behaviour

At this year SouthCHI conference in Maribor we published a contribution titled „Monitoring Learning Activities in PLE Using Semantic Modelling of Learner Behaviour„.
Abstract:

n this paper we report about the reflection of learning activities and revealing hidden information based on tracked user behaviour in our widget based PLE (Personal Learning Environment) at Graz University of Technology. Our reference data set includes information of more then 4000 active learners logs for a period of around two years. For the purpose of trend tracking and analytics collected logs have been used to model activity and usage traces with domain specific ontologies like Activity Ontology and Learning Context Ontology which have been created within the IntelLEO EU project. Generally we distinguish three different metrics: user centric, learning object (widget) centric and activity centric. We used Semantic Web query languages like SPARQL and representation formats like RDF to implement a human and machine readable web service along with a learning analytics dashboard for metrics visualization. The results o↵er a quick overview of learning habits, preferred set-ups of learning objects (widgets) and overall reflection of usages and activity dynamics in the PLE platform over time. The architecture delivers insights for intervening and recommending as closure of a learning analytics cycle with aim to optimize confidence in the PLE.

Reference: Selver, S.; Tarahi, B.; Ebner, M.; De Vocht, L.;Mannens, E. & Van De Walle, R. (2013) Monitoring Learning Activities in PLE Using SemanticModelling of Learner Behaviour. In: Human Factors in Computing and Informatis. Holzinger, A.;Ziefle, M.; Hitz, M & Debevc, M. (Ed.). Springer. Berlin, Heidelberg. p. 74-90

[publication] A Framework Concept for Profiling Researchers on Twitter using the Web of Data

Our contribution to this year WEBIST Conference about „A Framework Concept for Profiling Researchers on Twitter using the Web of Data“ is now online as draft version available.
Abstract:

Based upon findings and results from our recent research (De Vocht et al., 2011) we propose a generic frame- work concept for researcher profiling with appliance to the areas of ”Science 2.0” and ”Research 2.0”. Intensive growth of users in social networks, such as Twitter generated a vast amount of information. It has been shown in many previous works that social networks users produce valuable content for profiling and recommendations (Reinhardt et al., 2009; Java et al., 2007; De Vocht et al., 2011). Our research focuses on identifying and locating experts for specific research area or topic. In our approach we apply semantic technologies like (RDF, SPARQL), common vocabularies (SIOC, FOAF, MOAT, Tag Ontology) and Linked Datah (GeoNames, COLINDA) (Berners-Lee, 2006; Bizer et al., 2012).

Reference: Softic, S., Ebner, M., De Vocht, L., Mannens, E., Van de Walle, R.: A Framework Concept for Profiling Researchers on Twitter using the Web of Data. Proceedings of the 9th International Conference on Web Information Systems and Technologies (WEBIST) 2013, SciTePress 2013, Karl-Heinz Krempels, Alexander Stocker (Eds.), pp.447-452, ISBN 978-989-8565-54-9, Aachen, Germany, 8 – 10 May, 2013.

[publication] Semantically driven Social Data Aggregation Interfaces for Research 2.0

At this year iKNOW’11 conference we did a publication on „Semantically driven Social Data Aggregation Interfaces for Research 2.0“ and explained our research efforts on Semantic Social Media by developing a browser for finding out similar person of interest.
First the presentation:

Abstract:

We propose a framework to address an important issue in thecontext of the ongoing adoption of the “Web 2.0” in science and research, often referred to as “Science 2.0” or “Research 2.0”. Agrowing number of people are linked via acquaintances and onlinesocial networks such as Twitter allows indirect access to a hugeamount of ideas. These ideas are contained in a massive humaninformation flow. That users of these networks producerelevant data is being shown in many studies. The problem however lies in discovering and verifying such a streamof unstructured data items. Another related problem is locating anexpert that could provide an answer to a very specific researchquestion. We are using semantic technologies (RDF, SPARQL3) ,common vocabularies (SIOC, FOAF, SWRC) and Linked Data(DBpedia, GeoNames, CoLinDa) to extract and minethe data about scientific events out of context of microblogs. Hereby we are identifying persons and organization related tothem based on entities of time, place and topic. The framework provides an API that allows quick access to the information that isanalyzed by our system. As a proof-of-concept we explain, implement and evaluate such a researcher profiling use case. It involves the development of a framework that focuses on the proposition of researches based on topics and conferences theyhave in common. This framework provides an API that allow quick access to the analyzed information. A demonstrationapplication: “Researcher Affinity Browser” shows how the APIsupports developers to build rich internet applications for Research 2.0. This application also introduces the concept“affinity” that exposes the implicit proximity between entities andusers based on the content users produced. The usability of ademonstration application and the usefulness of the framework itself are investigated with an explicit evaluation questionnaire.This user feedback led to important conclusions about successfulachievements and opportunities to further improve this effort.

Semantically driven Social Data Aggregation Interfaces for Research 2.0



Reference: De Vocht, L.; Selver, S.; Ebner, M.; Mühlburger, H. (2011) Semantically driven Social Data AggregationInterfaces for Research 2.0. – in: 11th International Conference on Knowledge Management and Knowledge Technologies (2011), S. 43:1 -43:10, International Conference on Knowledge Management (iKNow), ACM New York

[article] Weaving Social E-learning Platforms Into The Web of Linked Data

My colleague Behnam Taraghi and his friend also contributed to this year i-Know Conference and presented a publication on „Weaving Social E-learning Platforms Into the Web of Linked Data„. I think who is interested in this topic it’s worth to take a look.
Abstract:

In this paper we present an approach for interlinking and RDFising social e-Learning Web 2.0 platforms like ELGG based on semantic tagging and Linked Data principles. A special module called SID (Semantically Interlinked Data) was developed to allow existing tagged and published user generated content an easy entrance into the Web of Data and to enrich it semantically on the other hand. Our approach uses commonly known vocabularies (FOAF, SIOC, MOAT and Tag Ontology) for modelling and generation tasks along with DBPedia as reference dataset for interlinking.

[video] Semantisches Web und neuronale Netzwerke

Stefen Büffel hat ein Interview mit mit Dr. Klaus Holthausen und Roy Uhlmann geführt – hier das Ergebnis:

(via Dresden Future Forum)