SciTePress - Affiliation Profile

L3S Research Center, Germany

Context (please use complete words only)

Field

Sort by

6 Papers

EXPLOITING THE LANGUAGE OF MODERATED SOURCES FOR CROSS-CLASSIFICATION OF USER GENERATED CONTENT

Topics: Meta-Knowledge Discovery and Representation; Web Mining

Authors: Avaré Stewart and Wolfgang Nejdl

Affiliation: Forschungszentrum L3S, Germany

Digital Object Identifier: 10.5220/0003298105710576

Proceedings of WEBIST 2011, ISBN: 978-989-8425-51-5

Quick Abstract

Recent pandemics such as Swine Flu have caused concern for public health officials. Given the ever increasing pace at which infectious diseases can spread globally, officials must be prepared to react sooner and with greater epidemic intelligence gathering capabilities. However, state-of-the-art systems for Epidemic Intelligence have not kept the pace with the growing need for more robust public health event detection. Existing systems are limited in that they rely on template-driven approaches to extract information about public health events from human language text. In this paper, we propose a new approach to support Epidemic Intelligence. We tackle the problem of detecting relevant information from unstructured text from a statistical pattern recognition viewpoint. In doing so, we also address the problems associated with the noisy and dynamic nature of blogs by exploiting the language in moderated sources, to train a classifier for detecting victim reporting sentences in blog social media. We refer to this as Cross-Classification. Our experiments show that without using manually labeled data, and with a simple set of features, we are able to achieve a precision as high as 88% and an accuracy of 77%, comparable with the state-of-the-art approaches for the same task.

Related Ontology Subjects/Areas/Topics (6)

Artificial Intelligence		Knowledge-Based Systems		Symbolic Systems
Knowledge Discovery and Information Retrieval		Soft Computing		Web Mining

ANNOTATIONS AND HYPERTRAILS WITH SPREADCRUMBS - An Easy Way to Annotate, Refind and Share

Topic: Multimedia and User Interfaces

Authors: Ricardo Kawase ¹ , Eelco Herder ² and Wolfgang Nejdl ¹

Affiliations: ¹ Leibniz Universität Hannover, Germany , ² Universität Hannover, Germany

Digital Object Identifier: 10.5220/0002778100050012

Proceedings of WEBIST 2010, ISBN: 978-989-674-025-2

Quick Abstract

Annotations have been shown to be an important activity during reading, especially during “active reading”. Annotations support understanding, interpretation, sensemaking and scannability. As valuable as in paper-based contexts, digital online annotations provide several benefits for annotators and collaborators. To study the impact of these benefits we present in this paper SpreadCrumbs, a straightforward Web annotation tool. SpreadCrumbs offers simple annotation’s interactions and metaphors that support most of the users’ annotations needs in the digital environment by enhancing the web experience with “in-context” annotations and providing a unique form of social navigation support with hypertrails. The results of our studies with the tool show the importance of annotations, the empirical outperformance of “in-context” annotations over other methods, and the outcome benefits of supporting social navigation.

Related Ontology Subjects/Areas/Topics (3)

Multimedia and User Interfaces

Web Information Systems and Technologies

Web Interfaces and Applications

DECAY-BASED RANKING FOR SOCIAL APPLICATION CONTENT

Topics: XML and Data Management; Searching and Browsing; Web Site Navigation Support Systems

Authors: George Papadakis , Claudia Niederée and Wolfgang Nejdl

Affiliation: L3S Research Center, Leibniz Universität Hannover, Germany

Digital Object Identifier: 10.5220/0002772802760281

Proceedings of WEBIST 2010, ISBN: 978-989-674-025-2

Quick Abstract

Social applications are prone to information explosion, due to the proliferation of user generated content. Locating and retrieving information in their context poses, therefore, a great challenge. Classical information retrieval methods are, however, inadequate in this environment, and users inevitably drown in an information flood. In this paper, we present a novel method that facilitates user’s information quests by identifying and improving the accessibility of the most important resources. This is achieved through an information valuation method, that estimates how likely it is for each information item to be accessed in the near future. The experiments verify that our method performs significantly better than others typically used in social applications, while being more versatile, too.

Related Ontology Subjects/Areas/Topics (5)

Internet Technology		Web Information Systems and Technologies		XML and Data Management
Searching and Browsing		Web Interfaces and Applications

A STRAIGHTFORWARD APPROACH FOR ONLINE ANNOTATIONS: SPREADCRUMBS - Enhancing and Simplifying Online Collaboration

Topics: Searching and Browsing; Multimedia and User Interfaces; Social Networks and Organizational Culture

Authors: Ricardo Kawase and Wolfgang Nejdl

Affiliation: Leibniz Universität Hannover, Germany

Digital Object Identifier: 10.5220/0001824804070410

Proceedings of WEBIST 2009, ISBN: 978-989-8111-81-4

Quick Abstract

Countless user studies and everyday observations have shown that individuals make annotations while reading - highlighting, circling and underlining important parts of the text, moreover adding written comments. Since the Web became the biggest accessible source of information, many of the reading activities happens online in the browser. In this sense, it is expected that the individuals would keep their annotation behaviors, provided that the appropriate tools are available. Although several Web annotation projects currently exist, it is difficult to identify the most prominent in the field. With SpreadCrumbs, we simplify the annotations actions and the social navigation support. SpreadCrumbs users can add in-context annotations to any webpage with minimum cognition load, as they would do when reading a paper; in addition SpreadCrumbs enhances online collaboration and provides mechanisms to support social navigation by means of existing social networks. It allows the users to freely express themselves and to add any desirable substance to the resources. Technically, annotations carry valuable information about the content, more than bookmarks or tags, having a greater impact on collaboration and search for re-finding. SpreadCrumbs exploits all these advantages with an intuitive and easy-to-use user interface.

Related Ontology Subjects/Areas/Topics (6)

Multimedia and User Interfaces		Social Networks and Organizational Culture		Web Information Systems and Technologies
Searching and Browsing		Society, e-Business and e-Government		Web Interfaces and Applications

INCREMENTAL END-USER QUERY CONSTRUCTION FOR THE SEMANTIC DESKTOP

Topics: Searching and Browsing; Multimedia and User Interfaces; Metadata and Metamodeling; Ontology and the Semantic Web

Authors: Ricardo Kawase ¹ , Enrico Minack ¹ , Wolfgang Nejdl ¹ , Samur Araújo ² and Daniel Schwabe ²

Affiliations: ¹ Leibniz Universität Hannover, Germany , ² Catholic University of Rio de Janeiro, Brazil

Digital Object Identifier: 10.5220/0001825902700275

Proceedings of WEBIST 2009, ISBN: 978-989-8111-81-4

Quick Abstract

This paper describes the design and implementation of a user interface that allows end-users to incrementally construct a query over the information in the Personal Information Management (PIM) domain. It allows semantically enriched keyword queries, implemented in the Semantic Desktop of the NEPOMUK Project. The Semantic Desktop user is able to explicitly articulate machine-processable knowledge, as described by its metadata. Therefore, searching this semantic information space can also benefit from the knowledge articulation within the query. Contrary to keyword queries, where it is not possible to provide semantic information, structured query languages as SPARQL enable exploiting this knowledge explicitly.

Related Ontology Subjects/Areas/Topics (6)

Metadata and Metamodeling		Ontology and the Semantic Web		Web Information Systems and Technologies
Multimedia and User Interfaces		Searching and Browsing		Web Interfaces and Applications

COMPARING PEOPLE IN THE ENTERPRISE

Topics: Strategic Decision Support Systems; Verification and Validation of Knowledge-Based Systems; Semantic Web Technologies; Knowledge Management

Author: Gianluca Demartini

Affiliation: L3S Research Center, Leibniz Universität Hannover, Germany

Digital Object Identifier: 10.5220/0001688404550458

Proceedings of ICEIS 2008, ISBN: 978-989-8111-37-1

Quick Abstract

Enterprise Search Systems are requested to provide more and more functionalities for supporting decision at the management level. An important aspect to consider is the human power and the knowledge which is available. For this reason, in this paper, after extracting a list of requirements out of a specific scenario, and presenting the previous work, we describe an improved approach to compare experts in order to retrieve and present to the user the most appropriate candidates for a given project.

Related Ontology Subjects/Areas/Topics (16)

Artificial Intelligence and Decision Support Systems	Information Systems Analysis and Specification	Society, e-Business and e-Government
Biomedical Engineering	Knowledge Management	Software Agents and Internet Computing
Cloud Computing	Ontologies and the Semantic Web	Strategic Decision Support Systems
Data Engineering	Semantic Web Technologies	Verification and Validation of Knowledge-Based Systems
Enterprise Information Systems	Services Science	Web Information Systems and Technologies
Health Information Systems

Topic(s):

Title:
ISBN:
Year:
Acronym:
Subject:

Title:
Author:
Affiliation:
Subject:

Name:
Affiliation:
Country:
Conference:
Subject:

Name:
Country:
Subject:

Affiliation

Filter listed results, by