It's a busy week for DBIS - Eva and Benjamin are presenting their work at The Web Conference in Lyon, France.
Eva is presenting her paper "Recommendation-Assisted Data Curation for Wikidata" together with Claudia Müller-Birn of Freie Universität Berlin at the Wikipedia Workshop. Benjamin is presenting his paper "Detecting Music Genre Using Extreme Gradient Boosting" at the Challenges track, participating in the WWW 2018 Challenge: Learning to Recognize Musical Genre.
This week, Eva presents the paper ALF-200k: Towards Extensive Multimodal Analyses of Music Tracks and Playlists at the European Conference on Information Retrieval (ECIR) in Grenoble, France. In this paper, we (Michael Tschuggnall, Stefan Wurzinger, Günther Specht and Eva Zangerle) present the ALF-200k dataset, which comprises lyrics and audio features of 226,000 songs. The dataset and code can be found here.
DBIS is represented twice on the 19th CICLing conference in Hanoi, Vietnam. On March 19th, Benjamin presented his paper "On the Influence of Machine Translation on Language Origin Obfuscation", which explains how the original language of translated documents can be detected. Later that day, Michaels work "Algorithmic Segmentation of Job Ads Using Textual Analysis" was presented as part of the poster session, yielding interesting discussions from many different fields.
Two DBIS papers were accepted at the International Conference on Computational Linguistics and Intelligent Text Processing (CICLing) 2018, a well-known and established conference in the field of natural language processing. Benjamin evaluated the automatic detection of the origin of a machine translated text, and Michael proposed a new algorithm to automatically segment job ads. Both papers will be presented at the conference at the end of this month in Hanoi, Vietnam and will be published in a Springer LNCS volume.
Last week, Eva held an invited talk about "Evaluating the Users’ Experience: A Call for Utilizing Multi-Method Evaluations for Recommender Systems" at the Technical University (TU) Vienna, where she discussed how user-centric evaluations of recommender systems could be improved utilizing multiple perspectives. You can find the abstract of the talk on the news page of TU Vienna.
Our paper "HOT: A Height Optimized Trie Index for Main-Memory Database Systems" was accepted at the 2018 ACM SIGMOD/PODS International Conference on Management of Data. The paper was co-authored by Robert Binna, Eva Zangerle, Martin Pichl, Günther Specht (all DBIS) and Viktor Leis from the Technical University Munich. The SIGMOD conference is among the most reknown and important venues in the field of core database systems (core ranking A*) and naturally, we are very happy about this huge success :)
At this year's ISMIR conference (International Society for Music Information Retrieval), taking place in Paris in September, Eva will be co-chairing the WiMIR events (Women in Music Information Retrieval) together with Audrey Laplante from the University of Montreal.
The DBIS team wishes merry christmas, happy holidays and all the best to you in the year to come :)
At the moment, the 19 IEEE Symposium on Multimedia takes place in Taichung, Taiwan. Yesterday, Martin held a talk about the joint research between the University of Innsbruck and the Johannes Kepler University: He presented the paper "Mining Culture-Specific Music Listening Behavior from Social Media Data" by Martin Pichl, Eva Zangerle, Grünther Specht and Markus Schedl. The paper was also presented in the poster session in the evening, triggering an interesting discussion with other researchers.
This year, the 4th Digital Humanities Austria Conference will take place in Innsbruck. The DBIS team will be highly involved, taking part and presenting research on various topics:
Also, Günther Specht and Eva Zangerle have served in the Program Committee of the conference and will be chairing a session at the conference.
This week, Doris Silbernagl will present her work on "Recommending OSM Tags to Improve Metadata Quality" at the ACM SIGSPATIAL Workshop on Recommendations for Location-based Services and Social Networks (co-authored with Nikolaus Krismer, Nikolaus Augsten and Günther Specht).
Last week, Adelheid Heftberger presented our work on "Employing Wikidata for Fostering Scholarly Research" at WikidataCon, the largest conference on Wikidata, in Berlin. In this work, we propose a novel workflow that allows how an annotation tool may integrate articles of disciplines of the humanities to annotate these articles and to subsequently, automatically ingest the annotations into the Wikidata platform. A first prototype of such a workflow has already been developed in a cooperation of Eva Zangerle with Freie Universität Berlin, Brandenburgisches Zentrum für Medienwissenschaften and Berlin-Brandenburgische Akademie der Wissenschaften.
Please find further information on the publication on the according submission website and in the video recording of the presentation session (our talk begins at 16:15).
We are happy to announce a new publication success: Together with Markus Schedl from the Johannes Kepler University Linz we got the paper "Mining Culture-Specific Music Listening Behavior from Social Media Data" accepted at this year's IEEE International Symposium on Multimedia, which is going to take happen in Taichung in December.
A warm welcome to all new computer science students from the DBIS team. This week, the "Brückenkrus Informatik" starts. As part of this course, DBIS makes an introduction to Python, one of the data science programming languages.
This week, Michael Tschuggnall and Maximilian Mayerl presented their work at the Conference and Labs of the Evaluation Forum (CLEF).
Michael served as Task Chair of the Author Identification Task of the PAN workshop, Günther Specht also was member of the task committee there. The PAN workshop series deals with digital text forensics and includes challenges on e.g., author identification or obfuscation.
Also, MediaEval, a benchmarking initiative for multimedia retrieval, was co-located with CLEF. DBIS participated in the MediaEval challenge on Genre Classification (wrangling with hundreds of thousands of tracks and according features over weeks) and finished 2nd :) Maximilian presented our classification approach at the workshop.
