Prof. Dr. Günther Specht

@article{mohammadi2025quantitative,
  title={Quantitative Assessment of GNN Counterfactual Explanation Robustness and Reproducibility under Adversarial Influence},
  author={Mohammadi, Amir Reza and M{\"u}ller, Michael M and Peintner, Andreas and Gstrein, Beatriz Barroso and Zangerle, Eva and Specht, G{\"u}nther},
  year={2025}
}

@InProceedings{murauer2022dtgrams,
  author       = {Amir Reza Mohammadi and
                  Amir{-}Hossein Karimi and
                  Mahdi Bohlouli and
                  Eva Zangerle and
                  G{\"{u}}nther Specht},
  booktitle = {Proceedings of the 34nd GI-Workshop Grundlagen von Datenbanksysteme (GvDB'23) },
  title     = {HPT4Rec: AutoML-based Hyperparameter Self-Tuning Framework for Session-based
                  Recommender Systems},
  year      = {2024},
}

@InProceedings{murauer2022dtgrams,
  author       = {Michael M. M{\"{u}}ller and
                  G{\"{u}}nther Specht and
                  Lukas Kleinheinz and
                  Janette F. Walde},
  booktitle = {Proceedings of the 35nd GI-Workshop Grundlagen von Datenbanksysteme (GvDB'24) },
  title        = {Bias Correction and Machine Learning in {AR(1)} Estimation: Bridging
                  Traditional and Modern Techniques},
  year      = {2024},
}

@inproceedings{voetter@songpopordinal,
        author =       {V\"{o}tter, Michael and Mayerl, Maximilian and Zangerle, Eva and Specht, G\"{u}nther},
	title        = {Song Popularity Prediction using Ordinal Classification},
	year         = 2023,
	booktitle    = {Proceedings of the 20th Sound and Music Computing Conference. June 15-17, 2023. Stockholm, Sweden},
	publisher    = {Royal College of Music and KTH Royal Institute of Technology},
	editor       = {Roberto Bresin and Kjetil Falkenberg},
	organization = {Royal College of Music and KTH Royal Institute of Technology}
}

@inproceedings{mci/Mayerl2023,
author = {Mayerl, Maximilian AND Vötter, Michael AND Specht, Günther AND Zangerle, Eva},
title = {Pairwise Learning to Rank for Hit Song Prediction},
booktitle = {BTW 2023},
year = {2023},
editor = {König-Ries, Birgitta AND Scherzinger, Stefanie AND Lehner, Wolfgang AND Vossen, Gottfried} ,
doi = { 10.18420/BTW2023-26 },
publisher = {Gesellschaft für Informatik e.V.},
address = {}
}

@inproceedings{mci/Moosleitner2023,
author = {Moosleitner, Manfred and Specht, Günther and Zangerle, Eva},
title = {Detection of Generated Text Reviews by Leveraging Methods from Authorship Attribution: Predictive Performance vs. Resourcefulness},
booktitle = {BTW 2023},
year = {2023},
editor = {König-Ries, Birgitta AND Scherzinger, Stefanie AND Lehner, Wolfgang AND Vossen, Gottfried} ,
doi = { 10.18420/BTW2023-11 },
publisher = {Gesellschaft für Informatik e.V.},
address = {}
}

@inproceedings{mayerl:ismir:2022,
   title        = {Verse versus Chorus: Structure-aware Feature Extraction for Lyrics-based Genre Recognition},
   author       = {Mayerl, Maximilian and Brandl, Stefan and Specht, G{\"u}nther and Schedl, Markus and Zangerle, Eva},
   year         = 2022,
   booktitle    = {Proceedings of the 23rd International Society for Music Information Retrieval Conference 2022},
   publisher    = {ISMIR},
   series       = {ISMIR '22},
   pages        = {884--890},
   doi          = {10.5281/zenodo.7316806}
 }

@article{10.1145/3506692,
author = {Binna, Robert and Zangerle, Eva and Pichl, Martin and Specht, G\"{u}nther and Leis, Viktor},
title = {Height Optimized Tries},
year = {2022},
issue_date = {March 2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {47},
number = {1},
issn = {0362-5915},
url = {https://doi.org/10.1145/3506692},
doi = {10.1145/3506692},
abstract = {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 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.},
journal = {ACM Trans. Database Syst.},
month = {apr},
articleno = {3},
numpages = {46},
keywords = {main memory, SIMD, Height optimized trie, index structure}
}

@InProceedings{moosleitner2022corattingattacks,
  author    = {Moosleitner, Manfred and Specht, G\"{u}nther and Zangerle, Eva},
  booktitle = {Proceedings of the 32nd GI-Workshop Grundlagen von Datenbanksysteme (GvDB'21) },
  title     = {{Co-rating Attacks on Recommendation Algorithms}},
  year      = {2022},
}

@InProceedings{murauer2022dtgrams,
  author    = {Murauer, Benjamin and Specht, G\"{u}nther},
  booktitle = {Proceedings of the 32nd GI-Workshop Grundlagen von Datenbanksysteme (GvDB'21) },
  title     = {{DT-grams: Structured Dependency Grammar Stylometry for Cross-Language Authorship Attribution}},
  year      = {2022},
}

@inproceedings{mayerlRecognizingSongMood2021,
	title = {Recognizing Song Mood and Theme: Clustering-based Ensembles},
	booktitle = {Working Notes Proceedings of the MediaEval 2021 Workshop},
	publisher = {ceur-ws.org},
	author = {Mayerl, Maximilian and Vötter, Michael and Peintner, Andreas and Specht, Günther and Zangerle, Eva},
	month = {12},
	year = {2021},
}

@inproceedings{voetter:ism:2021,
  author    = {
               Michael V\"{o}tter and Maximilian Mayerl and G\"{u}nther Specht and Eva Zangerle},
  title     = {Novel Datasets for Evaluating Song Popularity Prediction Tasks},
  booktitle = {{IEEE} International Symposium on Multimedia, {ISM} 2021, Virtual Event, November 29 -- December 1, 2021},
  pages     = {166--173},
  publisher = {{IEEE}},
  year      = {2021},
  doi       = {10.1109/ISM52913.2021.00034},
}

@InProceedings{murauer2021authbench,
  author    = {Murauer, Benjamin and Specht, G\"{u}nther},
  booktitle = {Proceedings of the Second Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP'21)},
  title     = {{Developing a Benchmark for Reducing Data Bias in Authorship Attribution}},
  publisher = {Association for Computational Linguistics},
  year      = {2021},
  pages     = {179--188}
}

@inproceedings{murauer-specht-2021-small,
    title = "Small-Scale Cross-Language Authorship Attribution on Social Media Comments",
    author = "Murauer, Benjamin  and Specht, G\"{u}nther",
    booktitle = "Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)",
    month = aug,
    year = "2021",
    url = "https://aclanthology.org/2021.mtsummit-LoResMT.2",
    pages = "11--19",
    year      = {2021},
    pages     = {11--19},
}

@Article{Specht2021ReLaX,
  author={Specht, G{\"u}nther and Kessler, Johannes and Mayerl, Maximilian and Tschuggnall, Michael},
  title={RelaX - Interaktive Relationale Algebra in der Lehre},
  journal={Datenbank-Spektrum},
  year={2021},
  month={Jan},
  day={24},
  abstract={Das relationale Modell und insbesondere die relationale Algebra bilden die Grundlage jedes relationalen Datenbanksystems. Daher ist es in der Lehre wichtig, den Studierenden eine fundierte Einf{\"u}hrung in die relationale Algebra zu geben. Nur so erhalten sie ein vertieftes Verst{\"a}ndnis f{\"u}r die interne Ausf{\"u}hrung einer Anfrage. W{\"a}hrend es viele M{\"o}glichkeiten gibt, SQL zu {\"u}ben, fehlen bisher gr{\"o}{\ss}tenteils solche M{\"o}glichkeiten f{\"u}r die relationale Algebra. Sie wird meist nur theoretisch unterrichtet. Darum hat die Forschungsgruppe DBIS an der Universit{\"a}t Innsbruck ein rein webbasiertes Tool entwickelt, das die Lehre der relationalen Algebra erleichtern und verbessern soll: RelaX. RelaX ist unter http://dbis-uibk.github.io/relax/frei verf{\"u}gbar.},
  issn={1610-1995},
  doi={10.1007/s13222-021-00367-x},
  url={https://doi.org/10.1007/s13222-021-00367-x}
}

@inproceedings{ecir20_pan,
 abstract = {The paper gives a brief overview of the four shared tasks that are to be organized at the PAN 2020 lab on digital text forensics and stylometry, hosted at CLEF conference. The tasks include author profiling, celebrity profiling, cross-domain author verification, and style change detection, seeking to advance the state of the art and to evaluate it on new benchmark datasets.},
 address = {Cham},
 author = {Bevendorff, Janek
and Ghanem, Bilal
and Giachanou, Anastasia
and Kestemont, Mike
and Manjavacas, Enrique
and Potthast, Martin
and Rangel, Francisco
and Rosso, Paolo
and Specht, Günther
and Stamatatos, Efstathios
and Stein, Benno
and Wiegmann, Matti
and Zangerle, Eva},
 booktitle = {Advances in Information Retrieval, ECIR 2020},
 editor = {Jose, Joemon M.
and Yilmaz, Emine
and Magalhães, João
and Castells, Pablo
and Ferro, Nicola
and Silva, Mário J.
and Martins, Flávio},
 isbn = {978-3-030-45442-5},
 pages = {508--516},
 publisher = {Springer International Publishing},
 title = {Shared Tasks on Authorship Analysis at PAN 2020},
 year = {2020}
}

@inproceedings{mediaeval2020,
 author = {Michael Vötter and Maximilian Mayerl and Günther Specht and Eva Zangerle},
 booktitle = {Working Notes Proceedings of the MediaEval 2020 Workshop},
 month = {12},
 publisher = {ceur-ws.org},
 title = {Recognizing Song Mood and Theme: Leveraging Ensembles of Tag Groups},
 year = {2020}
}

@inproceedings{mediaeval2020conspiracy,
 author = {Moosleitner, Manfred and Murauer, Benjamin and Specht, Günther},
 booktitle = {Working Notes Proceedings of the MediaEval 2020 Workshop},
 month = {12},
 publisher = {ceur-ws.org},
 title = {Detecting Conspiracy Tweets using Support Vector Machines},
 year = {2020}
}

@inproceedings{zangerle2020overview,
  title={Overview of the style change detection task at PAN 2020},
  author={Zangerle, Eva and Mayerl, Maximilian and Specht, G{\"u}nther and Potthast, Martin and Stein, Benno},
  year={2020},
  organization={CLEF}
}

@inproceedings{tschuggnall-etal-2019-reduce,
    title = "Reduce {\textbackslash}{\&} Attribute: Two-Step Authorship Attribution for Large-Scale Problems",
    author = {Tschuggnall, Michael  and
      Murauer, Benjamin  and
      Specht, G{\"u}nther},
    booktitle = "Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/K19-1089",
    doi = "10.18653/v1/K19-1089",
    pages = "951--960",
}