Shahzad Syed K, Granitzer Michael, Helic Denis
2011
Ontology and Semantic Framework has becomepervasive in computer science. It has huge impact at database,business logic and user interface for a range of computerapplications. This framework is also being introduced, presentedor plugged at user interfaces for various software and websites.However, establishment of structured and standardizedontological model based user interface development environmentis still a challenge. This paper talks about the necessity of such anenvironment based on User Interface Ontology (UIO). To explorethis phenomenon, this research focuses at the User Interfaceentities, their semantics, uses and relationships among them. Thefirst part focuses on the development of User Interface Ontology.In the second step, this ontology is mapped to the domainontology to construct a User Interface Model. Finally, theresulting model is quantified and instantiated for a user interfacedevelopment to support our framework. This UIO is anextendable framework that allows defining new sub-conceptswith their ontological relationships and constraints.
Horn Christopher, Pimas Oliver, Granitzer Michael, Lex Elisabeth
2011
In this paper, we outline our experiments carried out at theTREC Microblog Track 2011. Our system is based on a plain text indexextracted from Tweets crawled from twitter.com. This index hasbeen used to retrieve candidate Tweets for the given topics. The resultingTweets were post-processed and then analyzed using three differentapproaches: (i) a burst detection approach, (ii) a hashtag analysis, and(iii) a Retweet analysis. Our experiments consisted of four runs: Firstly,a combination of the Lucene ranking with the burst detection, and secondly,a combination of the Lucene ranking, the burst detection, and thehashtag analysis. Thirdly, a combination of the Lucene ranking, the burstdetection, the hashtag analysis, and the Retweet analysis, and fourthly,again a combination of the Lucene ranking with the burst detection butin this case with more sophisticated query language and post-processing.We achieved the best MAP values overall in the fourth run.
Seifert Christin, Ulbrich Eva Pauline, Granitzer Michael
2011
In text classification the amount and quality of training datais crucial for the performance of the classifier. The generation of trainingdata is done by human labelers - a tedious and time-consuming work. Wepropose to use condensed representations of text documents instead ofthe full-text document to reduce the labeling time for single documents.These condensed representations are key sentences and key phrases andcan be generated in a fully unsupervised way. The key phrases are presentedin a layout similar to a tag cloud. In a user study with 37 participantswe evaluated whether document labeling with these condensedrepresentations can be done faster and equally accurate by the humanlabelers. Our evaluation shows that the users labeled word clouds twiceas fast but as accurately as full-text documents. While further investigationsfor different classification tasks are necessary, this insight couldpotentially reduce costs for the labeling process of text documents.
Granitzer Michael, Lindstaedt Stefanie
2011
Kern Roman, Zechner Mario, Granitzer Michael
2011
Author disambiguation is a prerequisite for utilizingbibliographic metadata in citation analysis. Automaticdisambiguation algorithms mostly rely on cluster-based disambiguationstrategies for identifying unique authors given theirnames and publications. However, most approaches rely onknowing the correct number of unique authors a-priori, whichis rarely the case in real world settings. In this publicationwe analyse cluster-based disambiguation strategies and developa model selection method to estimate the number of distinctauthors based on co-authorship networks. We show that, givenclean textual features, the developed model selection methodprovides accurate guesses of the number of unique authors.