Ley Tobias, Lindstaedt Stefanie , Schöfegger Karin, Seitlinger Paul, Weber Nicolas, Hu Bo, Riss Uwe, Brun Roman, Hinkelmann Knut, Thönssen Barbara, Maier Ronald, Schmidt Andreas
2009
Kröll Mark, Prettenhofer P., Strohmaier M.
2009
Access to knowledge about user goals represents a critical component for realizing the vision of intelligent agents acting upon user intent on the web. Yet, the manual acquisition of knowledge about user goals is costly and often infeasible. In a departure from existing approaches, this paper proposes Goal Mining as a novel perspective for knowledge acquisition. The research presented in this chapter makes the following contributions: (a) it presents Goal Mining as an emerging field of research and a corresponding automatic method for the acquisition of user goals from web corpora, in the case of this paper search query logs (b) it provides insights into the nature and some characteristics of these goals and (c) it shows that the goals acquired from query logs exhibit traits of a long tail distribution, thereby providing access to a broad range of user goals. Our results suggest that search query logs represent a viable, yet largely untapped resource for acquiring knowledge about explicit user goals
Körner C., Kröll Mark, Strohmaier M.
2009
Understanding search intent is often assumed to represent a critical barrier to the level of service that search engine providers can achieve. Previous research has shown that search queries differ with regard to intentional explicitness. We build on this observation and introduce Intentional Query Suggestion as a novel idea that aims to make searcher’s intent more explicit during search. In this paper, we present an algorithm for Intentional Query Suggestion and corresponding data from comparative experiments with traditional query suggestion mechanisms. Our results suggest that Intentional Query Suggestion 1) diversifies search result sets (i.e. it reduces result set overlap) and 2) exhibits interesting differences in terms of click-through rates
Kröll Mark, Strohmaier M.
2009
Knowledge about human goals has been found to be an important kind of knowledge for a range of challenging problems, such as goal recognition from peoples’ actions or reasoning about human goals. Necessary steps towards conducting such complex tasks involve (i) ac-quiring a broad range of human goals and (ii) making them accessible by structuring and storing them in a knowledge base. In this work, we focus on extracting goal knowledge from weblogs, a largely untapped resource that can be expected to contain a broad variety of hu-man goals. We annotate a small sample of web-logs and devise a set of simple lexico-syntactic patterns that indicate the presence of human goals. We then evaluate the quality of our pat-terns by conducting a human subject study. Re-sulting precision values favor patterns that are not merely based on part-of-speech tags. In fu-ture steps, we intend to improve these prelimi-nary patterns based on our observations
Kröll Mark, Koerner C.
2009
Annotations represent an increasingly popular means for organizing, categorizing and finding resources on the “social” web. Yet, only a small portion of the total resources available on the web are annotated. In this paper, we describe a prototype - iTAG - for automatically annotating textual resources with human intent, a novel dimension of tagging. We investigate the extent to which the automatic analysis of human intentions in textual resources is feasible. To address this question, we present selected evidence from a study aiming to automatically annotate intent in a simplified setting, that is transcripts of speeches given by US presidential candidates in 2008
Kröll Mark
2009
Access to knowledge about common human goals has been found critical for realizing the vision of intelligent agents acting upon user intent on the web. Yet, the ac-quisition of knowledge about common human goals rep-resents a major challenge. In a departure from existing approaches, this paper investigates a novel resource for knowledge acquisition: The utilization of search query logs for this task. By relating goals contained in search query logs with goals contained in existing com-monsense knowledge bases such as ConceptNet, we aim to shed light on the usefulness of search query logs for capturing knowledge about common human goals. The main contribution of this paper consists of an empirical study comparing common human goals contained in two large search query logs (AOL and Microsoft Research) with goals contained in the commonsense knowledge base ConceptNet. The paper sketches ways how goals from search query logs could be used to address the goal acquisition and goal coverage problem related to com-monsense knowledge bases
Afzal M. T., Latif A., Us Saeed A., Sturm P., Aslam S., Andrews K., Maurer H.
2009
In numerous contexts and environments, it is necessary to identify and assign (potential) experts to subject fields. In the context of an academic journal for computer science (J.UCS), papers and reviewers are classified using the ACM classification scheme. This paper describes a system to identify and present potential reviewers for each category from the entire body of paper’s authors. The topical classification hierarchy is visualized as a hyperbolic tree and currently assigned reviewers are listed for a selected node (computer science category). In addition, a spiral visualization is used to overlay a ranked list of further potential reviewers (high-profile authors) around the currently selected category. This new interface eases the task of journal editors in finding and assigning reviewers. The system is also useful for users who want to find research collaborators in specific research areas.
Schoefegger K., Weber Nicolas, Lindstaedt Stefanie , Ley Tobias
2009
The changes in the dynamics of the economy and thecorresponding mobility and fluctuations of knowledge workers within organizationsmake continuous social learning an essential factor for an organization.Within the underlying organizational processes, KnowledgeMaturing refers to the the corresponding evolutionary process in whichknowledge objects are transformed from informal and highly contextualizedartifacts into explicitly linked and formalized learning objects.In this work, we will introduce a definition of Knowledge (Maturing)Services and will present a collection of sample services that can be dividedinto service functionality classes supporting Knowledge Maturingin content networks. Furthermore, we developed an application of thesesample services, a demonstrator which supports quality assurance withina highly content based organisational context.
Beham Günter, Lindstaedt Stefanie , Kump Barbara, Resanovic D.
2009
Jeanquartier Fleur, Kröll Mark, Strohmaier M.
2009
Getting a quick impression of the author's intention of a text is a task often performed. An author's intention plays a major role in successfully understanding a text. For supporting readers in this task, we present an intentional approach to visual text analysis, making use of tag clouds. The objectiveof tag clouds is presenting meta-information in a visually appealing way. However there is also much uncertainty associated with tag clouds, such as giving the wrong impression. It is not clear whether the author's intent can be grasped clearly while looking at a corresponding tag cloud. Therefore it is interesting to ask to what extent, with tag clouds, it is possible to support the user in understanding intentions expressed. In order to answer this question, we construct an intentional perspective on textual content. Based on an existing algorithm for extracting intent annotations from textual content we present a prototypical implementation to produce intent tag clouds, and describe a formative testing, illustrating how intent visualizations may support readers in understanding a text successfully. With the initial prototype, we conducted user studies of our intentional tag cloud visualization and a comparison with a traditional one that visualizes frequent terms. The evaluation's results indicate, that intent tag clouds have a positive effect on supporting users in grasping an author's intent.
Granitzer Michael, Rath Andreas S., Kröll Mark, Ipsmiller D., Devaurs Didier, Weber Nicolas, Lindstaedt Stefanie , Seifert C.
2009
Increasing the productivity of a knowledgeworker via intelligent applications requires the identification ofa user’s current work task, i.e. the current work context a userresides in. In this work we present and evaluate machine learningbased work task detection methods. By viewing a work taskas sequence of digital interaction patterns of mouse clicks andkey strokes, we present (i) a methodology for recording thoseuser interactions and (ii) an in-depth analysis of supervised classificationmodels for classifying work tasks in two different scenarios:a task centric scenario and a user centric scenario. Weanalyze different supervised classification models, feature typesand feature selection methods on a laboratory as well as a realworld data set. Results show satisfiable accuracy and high useracceptance by using relatively simple types of features.
Latif A., Afzal M. T., Höfler Patrick, Us Saeed A.
2009
The Semantic Web strives to add structure and meaning to the Web, thereby providing better results and easier interfaces for its users. One important foundation of the Semantic Web is Linked Data, the concept of interconnected data, describing resources by use of RDF and URIs. Linked Data (LOD) provides the opportunity to explore and combine datasets on a global scale -- something which has never been possible before. However, at its current stage, the Linked Data cloud yields little benefit for end users who know nothing of ontologies, triples and SPARQL. This paper presents an intelligent technique for locating desired URIs from the huge repository of Linked Data. Search keywords provided by users are utilized intelligently for locating the intended URI. The proposed technique has been applied in a simplified end user interface for LOD. The system evaluation shows that the proposed technique has reduced user's cognitive load in finding relevant information.
Pammer-Schindler Viktoria, Serafini L., Lindstaedt Stefanie
2009
Lindstaedt Stefanie , Aehnelt M., de Hoog R.
2009
Gras R., Devaurs Didier, Wozniak A., Aspinall A.
2009
We present an individual-based predator-prey model with, for the first time, each agent behavior being modeled by a fuzzy cognitive map (FCM), allowing the evolution of the agent behavior through the epochs of the simulation. The FCM enables the agent to evaluate its environment (e.g., distance to predator or prey, distance to potential breeding partner, distance to food, energy level) and its internal states (e.g., fear, hunger, curiosity), and to choose several possible actions such as evasion, eating, or breeding. The FCM of each individual is unique and is the result of the evolutionary process. The notion of species is also implemented in such a way that species emerge from the evolving population of agents. To our knowledge, our system is the only one that allows the modeling of links between behavior patterns and speciation. The simulation produces a lot of data, including number of individuals, level of energy by individual, choice of action, age of the individuals, and average FCM associated with each species. This study investigates patterns of macroevolutionary processes, such as the emergence of species in a simulated ecosystem, and proposes a general framework for the study of specific ecological problems such as invasive species and species diversity patterns. We present promising results showing coherent behaviors of the whole simulation with the emergence of strong correlation patterns also observed in existing ecosystems.
Lindstaedt Stefanie , de Hoog R., Aehnelt M.
2009
This contribution shortly introduces the collaborative APOSDLE environmentfor integrated knowledge work and learning. It proposes a video presentation and thepresentation of the third APOSDLE prototype.
Lex Elisabeth, Granitzer Michael, Juffinger A., Seifert C.
2009
Text classification is one of the core applications in data mining due to the huge amount of not categorized digital data available. Training a text classifier generates a model that reflects the characteristics of the domain. However, if no training data is available, labeled data from a related but different domain might be exploited to perform crossdomain classification. In our work, we aim to accurately classify unlabeled blogs into commonly agreed newspaper categories using labeled data from the news domain. The labeled news and the unlabeled blog corpus are highly dynamic and hourly growing with a topic drift, so a trade-off between accuracy and performance is required. Our approach is to apply a fast novel centroid-based algorithm, the Class-Feature-Centroid Classifier (CFC), to perform efficient cross-domain classification. Experiments showed that this algorithm achieves a comparable accuracy than k-NN and is slightly better than Support Vector Machines (SVM), yet at linear time cost for training and classification. The benefit of this approach is that the linear time complexity enables us to efficiently generate an accurate classifier, reflecting the topic drift, several times per day on a huge dataset.
Pellegrini T., Auer S., Schaffert S.
2009
Schmidt A., Hinkelmann K., Ley Tobias, Lindstaedt Stefanie , Maier R., Riss U.
2009
Effective learning support in organizations requires a flexible and personalizedtoolset that brings together the individual and the organizational perspectiveon learning. Such toolsets need a service-oriented infrastructure of reusable knowledgeand learning services as an enabler. This contribution focuses on conceptualfoundations for such an infrastructure as it is being developed within the MATUREIP and builds on the knowledge maturing process model on the one hand, and theseeding-evolutionary growth-reseeding model on the other hand. These theories areused to derive maturing services, for which initial examples are presented.
Weber Nicolas, Ley Tobias, Lindstaedt Stefanie , Schoefegger K., Bimrose J., Brown A., Barnes S.
2009
Lindstaedt Stefanie , Beham Günter, Ley Tobias, Kump Barbara
2009
Work-integrated learning (WIL) poses unique challenges for usermodel design: on the one hand users’ knowledge levels need to be determinedbased on their work activities – testing is not a viable option; on the other handusers do interact with a multitude of different work applications – there is nocentral learning system. This contribution introduces a user model and correspondingservices (based on SOA) geared to enable unobtrusive adaptabilitywithin WIL environments. Our hybrid user model services interpret usage datain the context of enterprise models (semantic approaches) and utilize heuristics(scruffy approaches) in order to determine knowledge levels, identify subjectmatter experts, etc. We give an overview of different types of user model services(logging, production, inference, control), provide a reference implementationwithin the APOSDLE project, and discuss early evaluation results.
Lindstaedt Stefanie , Rospocher M., Ghidini C., Pammer-Schindler Viktoria, Serafini L.
2009
Enterprise modelling focuses on the construction of a structureddescription of relevant aspects of an enterprise, the so-called enterprisemodel. Within this contribution we describe a wiki-based tool forenterprise modelling, called MoKi (Modelling wiKi). It specifically facilitatescollaboration between actors with different expertise to develop anenterprise model by using structural (formal) descriptions as well as moreinformal and semi-formal descriptions of knowledge. It also supports theintegrated development of interrelated models covering different aspectsof an enterprise.
Lindstaedt Stefanie , Rath Andreas S., Devaurs Didier
2009
‘Understanding context is vital’ [1] and ‘context is key’ [2]signal the key interest in the context detection field. Oneimportant challenge in this area is automatically detectingthe user’s task because once it is known it is possible tosupport her better. In this paper we propose an ontologybaseduser interaction context model (UICO) that enhancesthe performance of task detection on the user’s computerdesktop. Starting from low-level contextual attention metadatacaptured from the user’s desktop, we utilize rule-based,information extraction and machine learning approaches toautomatically populate this user interaction context model.Furthermore we automatically derive relations between themodel’s entities and automatically detect the user’s task.We present evaluation results of a large-scale user study wecarried out in a knowledge-intensive business environment,which support our approach.
Thurner-Scheuerer Claudia
2009
Schachner W., Koubek A.
2009
Lindstaedt Stefanie , Ghidini C., Kump Barbara, Mahbub N., Pammer-Schindler Viktoria, Rospocher M., Serafini L.
2009
Enterprise modelling focuses on the construction of a structureddescription, the so-called enterprise model, which represents aspectsrelevant to the activity of an enterprise. Although it has becomeclearer recently that enterprise modelling is a collaborative activity, involvinga large number of people, most of the enterprise modelling toolsstill only support very limited degrees of collaboration. Within thiscontribution we describe a tool for enterprise modelling, called MoKi(MOdelling wiKI), which supports agile collaboration between all differentactors involved in the enterprise modelling activities. MoKi is basedon a Semantic Wiki and enables actors with different expertise to developan enterprise model not only using structural (formal) descriptions butalso adopting more informal and semi-formal descriptions of knowledge.
Granitzer Michael, Lex Elisabeth, Juffinger A.
2009
People use weblogs to express thoughts, present ideas and share knowledge. However, weblogs can also be misused to influence and manipulate the readers. Therefore the credibility of a blog has to be validated before the available information is used for analysis. The credibility of a blogentry is derived from the content, the credibility of the author or blog itself, respectively, and the external references or trackbacks. In this work we introduce an additional dimension to assess the credibility, namely the quantity structure. For our blog analysis system we derive the credibility therefore from two dimensions. Firstly, the quantity structure of a set of blogs and a reference corpus is compared and secondly, we analyse each separate blog content and examine the similarity with a verified news corpus. From the content similarity values we derive a ranking function. Our evaluation showed that one can sort out incredible blogs by quantity structure without deeper analysis. Besides, the content based ranking function sorts the blogs by credibility with high accuracy. Our blog analysis system is therefore capable of providing credibility levels per blog.
Lindstaedt Stefanie , Hambach S., Müsebeck P., de Hoog R., Kooken J., Musielak M.
2009
Computational support for work-integrated learning will gain more and moreattention. We understand informal self-directed work-integrated learning of knowledgeworkers as a by-product of their knowledge work activities and propose a conceptual as wellas a technical approach for supporting learning from documents and learning in interactionwith fellow knowledge workers. The paper focuses on contextualization and scripting as twomeans to specifically address the latter interaction type.
Lex Elisabeth, Juffinger A.
2009
People use weblogs to express thoughts, present ideas and share knowledge, therefore weblogs are extraordinarily valuable resources, amongs others, for trend analysis. Trends are derived from the chronological sequence of blog post count per topic. The comparison with a reference corpus allows qualitative statements over identified trends. We propose a crosslanguage blog mining and trend visualisation system to analyse blogs across languages and topics. The trend visualisation facilitates the identification of trends and the comparison with the reference news article corpus. To prove the correctness of our system we computed the correlation between trends in blogs and news articles for a subset of blogs and topics. The evaluation corroborated our hypothesis of a high correlation coefficient for these subsets and therefore the correctness of our system for different languages and topics is proven.
Neidhart T., Granitzer Michael, Kern Roman, Weichselbraun A., Wohlgenannt G., Scharl A., Juffinger A.
2009
Lindstaedt Stefanie , Moerzinger R., Sorschag R. , Pammer-Schindler Viktoria, Thallinger G.
2009
Automatic image annotation is an important and challenging task, andbecomes increasingly necessary when managing large image collections. This paperdescribes techniques for automatic image annotation that take advantage of collaborativelyannotated image databases, so called visual folksonomies. Our approachapplies two techniques based on image analysis: First, classification annotates imageswith a controlled vocabulary and second tag propagation along visually similar images.The latter propagates user generated, folksonomic annotations and is thereforecapable of dealing with an unlimited vocabulary. Experiments with a pool of Flickrimages demonstrate the high accuracy and efficiency of the proposed methods in thetask of automatic image annotation. Both techniques were applied in the prototypicaltag recommender “tagr”.