Benjamin Murauer, PhD.

@InProceedings{10.1007/978-3-031-23804-8_23,
author="Murauer, Benjamin
and Tschuggnall, Michael
and Specht, G{\"u}nther
and Brandl, Julia",
editor="Gelbukh, Alexander",
title="Algorithmic Segmentation of Job Ads Using Textual Analysis",
booktitle="Computational Linguistics and Intelligent Text Processing",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="287--300",
abstract="As job ads are getting more prevalent online, an automated analysis is becoming increasingly important, especially in the field of human resource management. In this paper, we propose an approach to automatically segment job ads by predefined categories like the description of a job or the offering company, which is needed to categorize and quantify different aspects of job ads. Using a manually annotated data set, textual features are extracted for each segment type in a first step and utilized to train state-of-the-art machine learning classification methods. Subsequently, these models are used by iterative algorithms to detect the individual segments. Using several optimization techniques like detecting typical segment start phrases, comprehensive evaluations show promising results.",
isbn="978-3-031-23804-8"
}

@InProceedings{10.1007/978-3-031-23793-5_26,
author="Murauer, Benjamin
and Tschuggnall, Michael
and Specht, G{\"u}nther",
editor="Gelbukh, Alexander",
title="On the Influence of Machine Translation on Language Origin Obfuscation",
booktitle="Computational Linguistics and Intelligent Text Processing",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="320--330",
abstract="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 can 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.",
isbn="978-3-031-23793-5"
}

@phdthesis{murauer2022dissertation,
  title={{Universal Grammar Features for Cross-Language Authorship Attribution}},
  school = {University of Innsbruck, Department of Computer Science},
  author={Benjamin Murauer},
  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{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},
}

@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{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",
}

@InProceedings{10.1007/978-3-030-28577-7_7,
author="Murauer, Benjamin
and Specht, G{\"u}nther",
editor="Crestani, Fabio
and Braschler, Martin
and Savoy, Jacques
and Rauber, Andreas
and M{\"u}ller, Henning
and Losada, David E.
and Heinatz B{\"u}rki, Gundula
and Cappellato, Linda
and Ferro, Nicola",
title="Generating Cross-Domain Text Classification Corpora from Social Media Comments",
booktitle="20th Conference and Labs of the Evaluation Forum (CLEF'2019)",
year="2019",
publisher="Springer International Publishing",
address="Cham",
pages="114--125",
isbn="978-3-030-28577-7"
}

@article{murauer2018dynamic,
  title={Dynamic Parameter Search for Cross-Domain Authorship Attribution},
  author={Murauer, Benjamin and Tschuggnall, Michael and Specht, G{\"u}nther},
  journal={Working Notes of CLEF},
  year={2018}
}

@inproceedings{Murauer:2018:DMG:3184558.3191822,
 author = {Murauer, Benjamin and Specht, G\"{u}nther},
 title = {Detecting Music Genre Using Extreme Gradient Boosting},
 booktitle = {Companion of the The Web Conference 2018 on The Web Conference 2018},
 series = {WWW '18},
 year = {2018},
 isbn = {978-1-4503-5640-4},
 location = {Lyon, France},
 pages = {1923--1927},
 numpages = {5},
 url = {https://doi.org/10.1145/3184558.3191822},
 doi = {10.1145/3184558.3191822},
 acmid = {3191822},
 publisher = {International World Wide Web Conferences Steering Committee},
 address = {Republic and Canton of Geneva, Switzerland},
 keywords = {gradient boosting, music classification, neural network},
} 

@inproceedings{Murauer2018Translation,
  title={{On the Influence of Machine Translation on Language Origin Obfuscation}},
  author={Murauer, Benjamin and Tschuggnall, Michael and Specht, G\"unther},
  year={2018},
  location={Hanoi, Vietnam},
  booktitle={Proceedings of the 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing'2018)},
  month=3,

}

@article{Murauer2017Genre,
  title={Hierarchical Multilabel Classification and Voting for Genre Classification},
  author={Murauer, Benjamin and Mayerl, Maximilian and Tschuggnall, Michael and Zangerle, Eva and Pichl, Martin and Specht, G{\"u}nther},
  booktitle={CEURS Working Notes Proceedings of the MediaEval 2017 Workshop},
  publisher={CEUR-WS.org},
  city={Dublin, Ireland},
  year={2017},
  url={http://ceur-ws.org/Vol-1984/Mediaeval_2017_paper_41.pdf},
}

@inProceedings{hicss17,
booktitle ={{50th Hawaii International Conference on System Sciences, {HICSS} 2017, Big Island, Hawaii, USA, January 4-7, 2017}},
title = {{A Peer-Based Approach on Analyzing Hacked Twitter Accounts}},
publisher = {IEEE},
year = {2017},
month = {January},
pages = {1841--1850},
author = {Murauer, Benjamin and Zangerle, Eva and and Specht, G\"unther},
}