Publications

@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{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 = {}
}

@article{10.1145/3582900.3582919,
author = {Zangerle, Eva and Bauer, Christine and Said, Alan},
title = {Report on the 2nd Workshop on the Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES 2022) at RecSys 2022},
year = {2023},
issue_date = {December 2022},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {56},
number = {2},
issn = {0163-5840},
url = {https://doi.org/10.1145/3582900.3582919},
doi = {10.1145/3582900.3582919},
journal = {SIGIR Forum},
month = {jan},
articleno = {15},
numpages = {4}
}

@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{10.1007/978-3-031-28241-6_60,
author="Bevendorff, Janek
and Chinea-Rios, Mara
and Franco-Salvador, Marc
and Heini, Annina
and K{\"o}rner, Erik
and Kredens, Krzysztof
and Mayerl, Maximilian
and Pkezik, Piotr
and Potthast, Martin
and Rangel, Francisco
and Rosso, Paolo
and Stamatatos, Efstathios
and Stein, Benno
and Wiegmann, Matti
and Wolska, Magdalena
and Zangerle, Eva",
title="Overview of PAN 2023: Authorship Verification, Multi-author Writing Style Analysis, Profiling Cryptocurrency Influencers, and Trigger Detection",
booktitle="Advances in Information Retrieval (ECIR 2023)",
year="2023",
publisher="Springer Nature Switzerland",
address="Cham",
pages="518--526",
isbn="978-3-031-28241-6"
}

@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{zangerle:habil:2022,
 author = {Eva Zangerle},
 school = {University of Innsbruck},
 title = {Recommender Systems for Music Retrieval Tasks},
 type = {Habilitation},
 year = {2022}
}

@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}
 }

@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{10.1145/3511808.3557656,
author = {Moscati, Marta and Parada-Cabaleiro, Emilia and Deldjoo, Yashar and Zangerle, Eva and Schedl, Markus},
title = {Music4All-Onion -- A Large-Scale Multi-Faceted Content-Centric Music Recommendation Dataset},
year = {2022},
isbn = {9781450392365},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3511808.3557656},
doi = {10.1145/3511808.3557656},
abstract = {When we appreciate a piece of music, it is most naturally because of its content, including rhythmic, tonal, and timbral elements as well as its lyrics and semantics. This suggests that the human affinity for music is inherently content-driven. This kind of information is, however, still frequently neglected by mainstream recommendation models based on collaborative filtering that rely solely on user-item interactions to recommend items to users. A major reason for this neglect is the lack of standardized datasets that provide both collaborative and content information. The work at hand addresses this shortcoming by introducing Music4All-Onion, a large-scale, multi-modal music dataset. The dataset expands the Music4All dataset by including 26 additional audio, video, and metadata characteristics for 109,269 music pieces. In addition, it provides a set of 252,984,396 listening records of 119,140 users, extracted from the online music platform Last.fm, which allows leveraging user-item interactions as well. We organize distinct item content features in an onion model according to their semantics, and perform a comprehensive examination of the impact of different layers of this model (e.g., audio features, user-generated content, and derivative content) on content-driven music recommendation, demonstrating how various content features influence accuracy, novelty, and fairness of music recommendation systems. In summary, with Music4All-Onion, we seek to bridge the gap between collaborative filtering music recommender systems and content-centric music recommendation requirements.},
booktitle = {Proceedings of the 31st ACM International Conference on Information & Knowledge Management},
pages = {4339–4343},
numpages = {5},
keywords = {music information retrieval, image, video, audio features, lyrics, music recommender systems, audio signal, multimedia content analysis, onion model, natural language processing},
location = {Atlanta, GA, USA},
series = {CIKM '22}
}

@proceedings{DBLP:conf/recsys/2022perspectives,
  editor    = {Eva Zangerle and
               Christine Bauer and
               Alan Said},
  title     = {Proceedings of the Perspectives on the Evaluation of Recommender Systems
               Workshop 2022 co-located with the 16th {ACM} Conference on Recommender
               Systems (RecSys 2022)},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {3228},
  publisher = {CEUR-WS.org},
  year      = {2022},
  url       = {http://ceur-ws.org/Vol-3228},
}

@inproceedings{DBLP:conf/clef/BevendorffCFHKK22,
  author    = {Janek Bevendorff and
               Berta Chulvi and
               Elisabetta Fersini and
               Annina Heini and
               Mike Kestemont and
               Krzysztof Kredens and
               Maximilian Mayerl and
               Reynier Ortega{-}Bueno and
               Piotr Pezik and
               Martin Potthast and
               Francisco Rangel and
               Paolo Rosso and
               Efstathios Stamatatos and
               Benno Stein and
               Matti Wiegmann and
               Magdalena Wolska and
               Eva Zangerle},
  title     = {Overview of {PAN} 2022: Authorship Verification, Profiling Irony and
               Stereotype Spreaders, and Style Change Detection},
  booktitle = {Experimental {IR} Meets Multilinguality, Multimodality, and Interaction
               - 13th International Conference of the {CLEF} Association, {CLEF}
               2022, Bologna, Italy, September 5-8, 2022, Proceedings},
  series    = {Lecture Notes in Computer Science},
  volume    = {13390},
  pages     = {382--394},
  publisher = {Springer},
  year      = {2022},
  url       = {https://doi.org/10.1007/978-3-031-13643-6\_24},
  doi       = {10.1007/978-3-031-13643-6\_24},
}

@inproceedings{zangerle-recsys-2022,
author = {Zangerle, Eva and Bauer, Christine and Said, Alan},
title = {Second Workshop: Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES 2022)},
year = {2022},
isbn = {9781450392785},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3523227.3547408},
doi = {10.1145/3523227.3547408},
booktitle = {Proceedings of the 16th ACM Conference on Recommender Systems},
pages = {652–653},
numpages = {2},
keywords = {evaluation, recommender systems, personalized systems, methods, information retrieval},
location = {Seattle, WA, USA},
series = {RecSys '22}
}

@inproceedings{peintner:cars:2022,
 author = {Peintner, Andreas and Moscati, Marta and Parada-Cabaleiro, Emilia and Schedl, Markus and Zangerle, Eva},
 booktitle = {CARS: Workshop on Context-Aware Recommender Systems (RecSys ’22)},
 title = {Unsupervised Graph Embeddings for Session-based Recommendation with Item Features},
 year = {2022}
}

@inproceedings{DBLP:conf/clef/ZangerleMP022,
  author    = {Eva Zangerle and
               Maximilian Mayerl and
               Martin Potthast and
               Benno Stein},
  editor    = {Guglielmo Faggioli and
               Nicola Ferro and
               Allan Hanbury and
               Martin Potthast},
  title     = {Overview of the Style Change Detection Task at {PAN} 2022},
  booktitle = {Working Notes of {CLEF} 2022 - Conference and Labs
               of the Evaluation Forum},
  series    = {{CEUR} Workshop Proceedings},
  volume    = {3180},
  pages     = {2344--2356},
  publisher = {CEUR-WS.org},
  year      = {2022},
  url       = {http://ceur-ws.org/Vol-3180/paper-186.pdf},
  timestamp = {Wed, 10 Aug 2022 16:26:45 +0200},
  biburl    = {https://dblp.org/rec/conf/clef/ZangerleMP022.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

@article{voetter_ijsc_2022,
	title = {{HSP} {Datasets}: {Insights} on {Song} {Popularity} {Prediction}},
	issn = {1793-351X},
	url = {https://www.worldscientific.com/doi/abs/10.1142/S1793351X22400104},
	doi = {10.1142/S1793351X22400104},
	journal = {International Journal of Semantic Computing},
	author = {Vötter, Michael and Mayerl, Maximilian and Specht, Günther and Zangerle, Eva},
	month = may,
	year = {2022},
	note = {Publisher: World Scientific Publishing Co.},
	pages = {1--23},
}

@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{10.1007/978-3-030-99739-7_42,
author="Bevendorff, Janek
and Chulvi, Berta
and Fersini, Elisabetta
and Heini, Annina
and Kestemont, Mike
and Kredens, Krzysztof
and Mayerl, Maximilian
and Ortega-Bueno, Reyner
and Pezik, Piotr
and Potthast, Martin
and Rangel, Francisco
and Rosso, Paolo
and Stamatatos, Efstathios
and Stein, Benno
and Wiegmann, Matti
and Wolska, Magdalena
and Zangerle, Eva",
editor="Hagen, Matthias
and Verberne, Suzan
and Macdonald, Craig
and Seifert, Christin
and Balog, Krisztian
and N{\o}rv{\aa}g, Kjetil
and Setty, Vinay",
title="Overview of PAN 2022: Authorship Verification, Profiling Irony and Stereotype Spreaders, Style Change Detection, and Trigger Detection",
booktitle="Advances in Information Retrieval. ECIR 2022",
year="2022",
publisher="Springer International Publishing",
address="Cham",
pages="331--338",
abstract="The paper gives a brief overview of the four shared tasks to be organized at the PAN 2022 lab on digital text forensics and stylometry hosted at the CLEF 2022 conference. The tasks include authorship verification across discourse types, multi-author writing style analysis, author profiling, and content profiling. Some of the tasks continue and advance past editions (authorship verification and multi-author analysis) and some are new (profiling irony and stereotypes spreaders and trigger detection). The general goal of the PAN shared tasks is to advance the state of the art in text forensics and stylometry while ensuring objective evaluation on newly developed benchmark datasets.",
isbn="978-3-030-99739-7", 
doi="10.1007/978-3-030-99739-7_42",
url="https://link.springer.com/chapter/10.1007/978-3-030-99739-7_42"
}

@article{zangerle:sigirforum:2021,
author = {Zangerle, Eva and Bauer, Christine and Said, Alan},
title = {Report on the 1st Workshop on the Perspectives on the Evaluation of Recommender Systems (PERSPECTIVES 2021) at RecSys 2021},
year = {2022},
issue_date = {December 2021},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {55},
number = {2},
issn = {0163-5840},
url = {https://doi.org/10.1145/3527546.3527565},
doi = {10.1145/3527546.3527565},
abstract = {Evaluation is a central step when it comes to developing, optimizing, and deploying recommender systems. The PERSPECTIVES 2021 workshop at the 15th ACM Conference on Recommender Systems brought together academia and industry to critically reflect on the evaluation of recommender systems. The primary goal of the workshop was to capture the current state of evaluation from different, and maybe even diverging or contradictory perspectives.Date: 25 and 30 September 2021.Website: https://perspectives-ws.github.io/2021/.},
journal = {SIGIR Forum},
month = {mar},
articleno = {16},
numpages = {5}
}

@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{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{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{DBLP:conf/clef/BevendorffCSKMM21,
  author    = {Janek Bevendorff and
               Berta Chulvi and
               Gretel Liz De la Pe{\~{n}}a Sarrac{\'{e}}n and
               Mike Kestemont and
               Enrique Manjavacas and
               Ilia Markov and
               Maximilian Mayerl and
               Martin Potthast and
               Francisco Rangel and
               Paolo Rosso and
               Efstathios Stamatatos and
               Benno Stein and
               Matti Wiegmann and
               Magdalena Wolska and
               Eva Zangerle},
  editor    = {K. Sel{\c{c}}uk Candan and
               Bogdan Ionescu and
               Lorraine Goeuriot and
               Birger Larsen and
               Henning M{\"{u}}ller and
               Alexis Joly and
               Maria Maistro and
               Florina Piroi and
               Guglielmo Faggioli and
               Nicola Ferro},
  title     = {Overview of {PAN} 2021: Authorship Verification, Profiling Hate Speech
               Spreaders on Twitter, and Style Change Detection},
  booktitle = {Experimental {IR} Meets Multilinguality, Multimodality, and Interaction
               - 12th International Conference of the {CLEF} Association, {CLEF}
               2021, Virtual Event, September 21-24, 2021, Proceedings},
  series    = {Lecture Notes in Computer Science},
  volume    = {12880},
  pages     = {419--431},
  publisher = {Springer},
  year      = {2021},
  url       = {https://doi.org/10.1007/978-3-030-85251-1\_26},
  doi       = {10.1007/978-3-030-85251-1\_26},
}