Filters








605 Hits in 2.0 sec

Editorial

Andreas Thor, Stefanie Scherzinger, Günther Specht
2014 Datenbank-Spektrum  
doi:10.1007/s13222-014-0162-1 fatcat:yilobebezbgpdbrvtycnkm4myi

RelaX

Günther Specht, Johannes Kessler, Maximilian Mayerl, Michael Tschuggnall
2021 Datenbank-Spektrum  
Während für SQL zahlreiche Datenbanksysteme und Werkzeuge zur Verfügung stehen, mit denen Studierende ihre Anfragen interaktiv ausführen können, und die im Feh-Günther Specht guenther.specht@uibk.ac.at  ... 
doi:10.1007/s13222-021-00367-x fatcat:he5jhen52zaetod7pw7slsguqy

On the Influence of Machine Translation on Language Origin Obfuscation [article]

Benjamin Murauer, Michael Tschuggnall, Günther Specht
2021 arXiv   pre-print
In the last decade, machine translation has become a popular means to deal with multilingual digital content. By providing higher quality translations, obfuscating the source language of a text becomes more attractive. In this paper, we analyze the ability to detect the source language from the translated output of two widely used commercial machine translation systems by utilizing machine-learning algorithms with basic textual features like n-grams. Evaluations show that the source language
more » ... be reconstructed with high accuracy for documents that contain a sufficient amount of translated text. In addition, we analyze how the document size influences the performance of the prediction, as well as how limiting the set of possible source languages improves the classification accuracy.
arXiv:2106.12830v1 fatcat:u35vhble5rhoznzrj4oksmsuv4

Co-rating Attacks on Recommendation Algorithms

Manfred Moosleitner, Günther Specht, Eva Zangerle
2021 Workshop Grundlagen von Datenbanken  
Online shops, streaming services, and booking systems use algorithms to recommend items from their stock to users. These recommendations are often calculated based on the interactions of other users with the items, e.g., buying a product or watching a movie. This creates an attack point where the outcome of recommendation algorithms can be purposefully manipulated by manually or automatically created user interactions, aimed to raise or lower the relevance of specific items. We study the
more » ... bility of recommender algorithms by simulating a series of attacks on six recommendation algorithms, using three attack strategies, and two opposing attack objectives. We run these experiments with varying numbers of co-ratings per attack and evaluate the overall item ranking and an average change in average rank. Our results show that the effort required of and the efficiency reached by the attacks greatly depends on the strategy, objective, and recommendation algorithm. Additionally, the calculated average change in average rank provides an indicator about the attackability of recommendation algorithms. We find that neighborhood-and cluster-based algorithms show a higher vulnerability against attacks compared to algorithms based on matrix factorization.
dblp:conf/gvd/MoosleitnerSZ21 fatcat:smesdgxi3jcotlbtijm72inefe

Autoencoders for Next-Track-Recommendation

Michael Vötter, Eva Zangerle, Maximilian Mayerl, Günther Specht
2019 Workshop Grundlagen von Datenbanken  
In music recommender systems, playlist continuation is the task of continuing a user's playlist with a fitting next track, often also referred to as next-track or sequential recommendation. This work investigates the suitability and applicability of autoencoders for the task of playlist continuation. We utilize autoencoders and hence, representation learning to continue playlists. Our approach is inspired by the usage of autoencoders to denoise images and we consider the playlist without the
more » ... sing next-track as a noisy input. Particularly, we design different autoencoders for this specific task and investigate the effects of different designs on the overall suitability of recommendations produced by the resulting recommender systems. To evaluate the suitability of recommendations produced by the proposed approach, we utilize the AotM-2011 and LFM-1b datasets. Based on those datasets, we show that n-grams are a well performing alternative baseline to kNN. Fruther, we show that it is possible to outperform a kNN as well as an n-gram baseline with our autoencoder approach.
dblp:conf/gvd/VotterZMS19 fatcat:7zik2kdbbbgt7fhezzf2ofu2au

4.-8. März 2019

Johannes Kessler, Michael Tschuggnall, Günther Specht
2019 Datenbanksysteme für Business, Technologie und Web  
Specht  ...  for Relational Algebra eXecutor and is available at http://dbis-uibk.github.io/relax with the exception of correlated subqueries and recursive statements 506 Johannes Kessler, Michael Tschuggnall, Günther  ... 
doi:10.18420/btw2019-32 dblp:conf/btw/KesslerTS19 fatcat:grwwdy2q3nasbn5isimzilknm4

Incremental Calculation of Isochrones Regarding Duration

Nikolaus Krismer, Günther Specht, Johann Gamper
2014 Workshop Grundlagen von Datenbanken  
An isochrone in a spatial network is the minimal, possibly disconnected subgraph that covers all locations from where a query point is reachable within a given time span and by a given arrival time [5] . A novel approach for computing isochrones in multimodal spatial networks is presented in this paper. The basic idea of this incremental calculation is to reuse already computed isochrones when a new request with the same query point is sent, but with different duration. Some of the major
more » ... ges of the new calculation attempt are described and solutions to the most problematic ones are outlined on basis of the already established MINE and MINEX algorithms. The development of the incremental calculation is done by using six different cases of computation. Three of them apply to the MINEX algorithm, which uses a vertex expiration mechanism, and three cases to MINE without vertex expiration. Possible evaluations are also suggested to ensure the correctness of the incremental calculation. In the end some further tasks for future research are outlined.
dblp:conf/gvd/KrismerSG14 fatcat:eqqrwbtsera5bilnjtroezlypy

SentiStorm: Echtzeit-Stimmungserkennung von Tweets

Eva Zangerle, Martin Illecker, Günther Specht
2016 HMD Praxis der Wirtschaftsinformatik  
Specht  ... 
doi:10.1365/s40702-016-0237-6 fatcat:tr4ed3eyh5hf5i3lrn3jd7bjey

Die Forschungsgruppe Datenbanken und Informationssysteme an der Universität Innsbruck

Günther Specht
2018 Datenbank-Spektrum  
Literatur Die Forschungsgruppe (Lehrstuhl) Datenbanken und Informationssysteme (DBIS) an der Universität Innsbruck wurde 2006 von Günther Specht gegründet und wird seither von ihm geleitet.  ...  Specht guenther.specht@uibk.ac.at 1 hängt.  ... 
doi:10.1007/s13222-018-0278-9 fatcat:5z6pzea7mnbndc6s5xxl7vau2m

SnoopyTagging

Wolfgang Gassler, Eva Zangerle, Martin Bürgler, Günther Specht
2012 Proceedings of the 21st international conference companion on World Wide Web - WWW '12 Companion  
Current mass-collaboration platforms use tags to annotate and categorize resources enabling effective search capabilities. However, as tags are freely chosen keywords, the resulting tag vocabulary is very heterogeneous. Another shortcoming of simple tags is that they do not allow for a specification of context to create meaningful metadata. In this paper we present the SnoopyTagging approach which supports the user in the process of creating contextualized tags while at the same time decreasing
more » ... the heterogeneity of the tag vocabulary by facilitating intelligent self-learning recommendation algorithms.
doi:10.1145/2187980.2188102 dblp:conf/www/GasslerZBS12 fatcat:mb4byjkvpbervn3zi6zudgva54

Height Optimized Tries

Robert Binna, Eva Zangerle, Martin Pichl, Günther Specht, Viktor Leis
2022 ACM Transactions on Database Systems  
We present the Height Optimized Trie (HOT), a fast and space-efficient in-memory index structure. The core algorithmic idea of HOT is to dynamically vary the number of bits considered at each node, which enables a consistently high fanout and thereby good cache efficiency. For a fixed maximum node fanout, the overall tree height is minimal and its structure is deterministically defined. Multiple carefully engineered node implementations using SIMD instructions or lightweight compression schemes
more » ... provide compactness and fast search and optimize HOT structures for different usage scenarios. Our experiments, which use a wide variety of workloads and data sets, show that HOT outperforms other state-of-the-art index structures for string keys both in terms of search performance and memory footprint, while being competitive for integer keys.
doi:10.1145/3506692 fatcat:fxlo2iqanbbbvop7l2qpb5f6ra

Enhancing ECA Rules for Distributed Active Database Systems [chapter]

Thomas Heimrich, Günther Specht
2003 Lecture Notes in Computer Science  
This action makes sure that P is fulfilled. 204 Thomas Heimrich, Günther Specht The use of the tuple <S,D,P,C,A> is illustrated by the following example.  ... 
doi:10.1007/3-540-36560-5_15 fatcat:m3vrlgvqejgjjjqnp6kisrgz7a

"Sorry, I was hacked"

Eva Zangerle, Günther Specht
2014 Proceedings of the 29th Annual ACM Symposium on Applied Computing - SAC '14  
Online social networks like Facebook or Twitter have become powerful information diffusion platforms as they have attracted hundreds of millions of users. The possibility of reaching millions of users within these networks not only attracted standard users, but also cyber-criminals who abuse the networks by spreading spam. This is accomplished by either creating fake accounts, bots, cyborgs or by hacking and compromising accounts. Compromised accounts are subsequently used to spread spam in the
more » ... name of their legitimate owner. This work sets out to investigate how Twitter users react to having their account hacked and how they deal with compromised accounts. We crawled a data set of tweets in which users state that their account was hacked and subsequently performed a supervised classification of these tweets based on the reaction and behavior of the respective user. We find that 27.30% of the analyzed Twitter users change to a new account once their account was hacked. 50.91% of all users either state that they were hacked or apologize for any unsolicited tweets or direct messages.
doi:10.1145/2554850.2554894 dblp:conf/sac/ZangerleS14 fatcat:xqpvz4gywrgbnoip7jfqu55paq

#Wikipedia on Twitter

Eva Zangerle, Georg Schmidhammer, Günther Specht
2015 Proceedings of the 11th International Symposium on Open Collaboration - OpenSym '15  
Wikipedia has long become a standard source of information on the web and as such is widely referenced on the web and in social media. This paper analyzes the usage of Wikipedia on Twitter by looking into languages used on both platforms, content features of posted articles and recent edits of those articles. The analysis is based on a set of four million tweets and links these tweets to Wikipedia articles and their features to identify interesting relations. We find that within English and
more » ... nese tweets containing a link to Wikipedia, 97% of the links lead to the English resp. Japanese Wikipedia, whereas for other languages 20% of the tweets contain a link to a Wikipedia of a different language. Our results also indicate that the number of tweets about a certain topic is not correlated to the number of recent edits on the particular page at the time of sending the tweet.
doi:10.1145/2788993.2789845 dblp:conf/wikis/ZangerleSS15 fatcat:aewpfx3w6zc2xp3pa35tks6wnq

#nowplaying Music Dataset

Eva Zangerle, Martin Pichl, Wolfgang Gassler, Günther Specht
2014 Proceedings of the First International Workshop on Internet-Scale Multimedia Management - WISMM '14  
The extraction of information from online social networks has become popular in both industry and academia as these data sources allow for innovative applications. However, in the area of music recommender systems and music information retrieval, respective data is hardly exploited. In this paper, we present the #nowplaying dataset, which leverages social media for the creation of a diverse and constantly updated dataset, which describes the music listening behavior of users. For the creation
more » ... the dataset, we rely on Twitter, which is frequently facilitated for posting which music the respective user is currently listening to. From such tweets, we extract track and artist information and further metadata. The dataset currently comprises 49 million listening events, 144,011 artists, 1,346,203 tracks and 4,150,615 users which makes it considerably larger than existing datasets.
doi:10.1145/2661714.2661719 dblp:conf/mm/ZangerlePGS14 fatcat:tsu2wzhfbfbupk5gjwb2w7fh5i
« Previous Showing results 1 — 15 out of 605 results