no code implementations • NAACL (Emoji) 2022 • Jens Reelfs, Timon Mohaupt, Sandipan Sikdar, Markus Strohmaier, Oliver Hohlfeld
We study the extent to which emoji can be used to add interpretability to embeddings of text and emoji.
1 code implementation • EMNLP (FEVER) 2021 • Justus Mattern, Yu Qiao, Elma Kerz, Daniel Wiechmann, Markus Strohmaier
As the world continues to fight the COVID-19 pandemic, it is simultaneously fighting an ‘infodemic’ – a flood of disinformation and spread of conspiracy theories leading to health threats and the division of society.
no code implementations • 5 Feb 2024 • Meng Cao, Hussain Hussain, Sandipan Sikdar, Denis Helic, Markus Strohmaier, Roman Kern
We further study how interventions on network properties influence fairness by examining counterfactual scenarios with alternative evolution outcomes and differing network properties.
1 code implementation • 10 May 2023 • Max Klabunde, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
Measuring similarity of neural networks to understand and improve their behavior has become an issue of great importance and research interest.
no code implementations • 26 Apr 2023 • Ivan Smirnov, Camelia Oprea, Markus Strohmaier
We find that toxic comments consistently reduce the activity of editors, leading to an estimated loss of 0. 5-2 active days per user in the short term.
1 code implementation • 11 Jan 2023 • Jan Engler, Sandipan Sikdar, Marlene Lutz, Markus Strohmaier
To address this limitation, we present SensePOLAR, an extension of the original POLAR framework that enables word-sense aware interpretability for pre-trained contextual word embeddings.
no code implementations • 29 Dec 2022 • Tobias Schumacher, Marlene Lutz, Sandipan Sikdar, Markus Strohmaier
By virtue of their diverse application contexts, we argue that such a comparative analysis is not straightforward.
1 code implementation • 13 Sep 2022 • Hussain Hussain, Meng Cao, Sandipan Sikdar, Denis Helic, Elisabeth Lex, Markus Strohmaier, Roman Kern
We hope our findings raise awareness about this issue in our community and lay a foundation for the future development of GNN models that are more robust to such attacks.
no code implementations • 14 Jun 2022 • Fariba Karimi, Marcos Oliveira, Markus Strohmaier
In this chapter, we provide an overview of recent advances in data-driven and theory-informed complex models of social networks and their potential in understanding societal inequalities and marginalization.
1 code implementation • 23 Jul 2021 • Hussain Hussain, Tomislav Duricic, Elisabeth Lex, Denis Helic, Markus Strohmaier, Roman Kern
In this work, we study adversarial attacks that are uninformed, where an attacker only has access to the graph structure, but no information about node attributes.
1 code implementation • 9 Jul 2021 • Felix I. Stamm, Martin Becker, Markus Strohmaier, Florian Lemmerich
This paper introduces Redescription Model Mining, a novel approach to identify interpretable patterns across two datasets that share only a subset of attributes and have no common instances.
1 code implementation • 4 Mar 2021 • Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
More generally, we find that the performance on multiclass quantification is inferior to the results obtained in the binary setting.
1 code implementation • 19 Feb 2021 • Thorsten Ruprechter, Manoel Horta Ribeiro, Tiago Santos, Florian Lemmerich, Markus Strohmaier, Robert West, Denis Helic
Wikipedia, the largest encyclopedia ever created, is a global initiative driven by volunteer contributions.
Computers and Society
1 code implementation • 8 Feb 2021 • Georg Ahnert, Ivan Smirnov, Florian Lemmerich, Claudia Wagner, Markus Strohmaier
The FairCeptron framework is an approach for studying perceptions of fairness in algorithmic decision making such as in ranking or classification.
1 code implementation • 13 Jun 2020 • Ivan Smirnov, Florian Lemmerich, Markus Strohmaier
The most common approach to this issue is debiasing, for example via the introduction of quotas that ensure proportional representation of groups with respect to a certain, often binary attribute.
1 code implementation • 3 Jun 2020 • Lukas Moldon, Markus Strohmaier, Johannes Wachs
We examine how the behavior of software developers changes in response to removing gamification elements from GitHub, an online platform for collaborative programming and software development.
Software Engineering Computers and Society Social and Information Networks
2 code implementations • 20 May 2020 • Tobias Schumacher, Hinrikus Wolf, Martin Ritzert, Florian Lemmerich, Jan Bachmann, Florian Frantzen, Max Klabunde, Martin Grohe, Markus Strohmaier
We systematically evaluate the (in-)stability of state-of-the-art node embedding algorithms due to randomness, i. e., the random variation of their outcomes given identical algorithms and graphs.
no code implementations • 19 May 2020 • Jens Helge Reelfs, Oliver Hohlfeld, Markus Strohmaier, Niklas Henckell
We train word-emoji embeddings on large scale messaging data obtained from the Jodel online social network.
1 code implementation • 9 Mar 2020 • Radomir Popović, Florian Lemmerich, Markus Strohmaier
Bias in Word Embeddings has been a subject of recent interest, along with efforts for its reduction.
1 code implementation • 27 Jan 2020 • Binny Mathew, Sandipan Sikdar, Florian Lemmerich, Markus Strohmaier
We introduce POLAR - a framework that adds interpretability to pre-trained word embeddings via the adoption of semantic differentials.
no code implementations • 23 Dec 2019 • Michael Ellers, Michael Cochez, Tobias Schumacher, Markus Strohmaier, Florian Lemmerich
In that setting, we analyze whether after the removal of the node from the network and the deletion of the vector representation of the respective node in the embedding significant information about the link structure of the removed node is still encoded in the embedding vectors of the remaining nodes.
no code implementations • LREC 2018 • Andreas Niekler, Arnim Bleier, Christian Kahmann, Lisa Posch, Gregor Wiedemann, Kenan Erdogan, Gerhard Heyer, Markus Strohmaier
The iLCM project pursues the development of an integrated research environment for the analysis of structured and unstructured data in a "Software as a Service" architecture (SaaS).
no code implementations • 28 Oct 2016 • Simon Walk, Lisette Espín-Noboa, Denis Helic, Markus Strohmaier, Mark Musen
In particular, we were able to identify seven distinct browsing-behavior types, which all make use of different functionality provided by BioPortal.
no code implementations • 21 Mar 2016 • Lisa Posch, Philipp Schaer, Arnim Bleier, Markus Strohmaier
This paper presents a system which creates and visualizes probabilistic semantic links between concepts in a thesaurus and classes in a classification system.
no code implementations • 20 Jan 2016 • Lisette Espín-Noboa, Florian Lemmerich, Philipp Singer, Markus Strohmaier
By applying this combination of approaches to taxi data in Manhattan, we can discover and explain different patterns in human mobility that cannot be identified in a collective analysis.
no code implementations • 24 Jul 2015 • Lisa Posch, Arnim Bleier, Philipp Schaer, Markus Strohmaier
In this paper, we present the Polylingual Labeled Topic Model, a model which combines the characteristics of the existing Polylingual Topic Model and Labeled LDA.
no code implementations • 8 Jul 2014 • Simon Walk, Philipp Singer, Markus Strohmaier, Tania Tudorache, Mark A. Musen, Natalya F. Noy
For example, the 11th revision of the ICD, which is currently under active development by the WHO contains nearly 50, 000 classes representing a vast variety of different diseases and causes of death.