klinger.bib
@proceedings{wassa-2023-approaches,
title = {Proceedings of the 13th Workshop on Computational
Approaches to Subjectivity, Sentiment, {\&} Social
Media Analysis},
editor = {Barnes, Jeremy and De Clercq, Orph{\'e}e and
Klinger, Roman},
month = jul,
year = {2023},
address = {Toronto, Canada},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2023.wassa-1.0},
internaltype = {edited}
}
@inproceedings{Klinger2023a,
author = {Roman Klinger},
title = {Where are We in Event-centric Emotion Analysis?
Bridging Emotion Role Labeling and Appraisal-based
Approaches},
booktitle = {Proceedings of the Big Picture Workshop: Crafting a
Research Narrative},
year = {2023},
month = {December},
address = {Singapore},
organization = {EMNLP},
publisher = {Association for Computational Linguistics},
url = {https://www.romanklinger.de/publications/klinger2023.pdf},
archiveprefix = {arXiv},
eprint = {2309.02092},
primaryclass = {cs.CL},
internaltype = {workshop}
}
@article{Velutharambath2023a,
author = {Aswathy Velutharambath and Kai Sassenberg and Roman Klinger},
title = {Prevention or Promotion? {Predicting} Author's Regulatory Focus},
journal = {Northern European Journal of Language Technology},
year = {2023},
volume = {9},
number = {1},
month = {September},
internaltype = {journal},
url = {https://www.romanklinger.de/publications/VelutharambathSassenbergKlinger_NEJLT2023.pdf},
doi = {10.3384/nejlt.2000-1533.2023.4561}
}
@article{Troiano2023a,
author = {Enrica Troiano and Roman Klinger and Sebastian Padó},
title = {On the Relationship between Frames and Emotionality in Text},
journal = {Northern European Journal of Language Technology},
year = {2023},
volume = {9},
number = {1},
month = {September},
internaltype = {journal},
doi = {10.3384/nejlt.2000-1533.2023.4361},
url = {https://www.romanklinger.de/publications/TroianoKlingerPado_nejlt23.pdf}
}
@inproceedings{MenchacaResendiz2023,
title = {Affective Natural Language Generation of Event
Descriptions through Fine-grained Appraisal
Conditions},
author = {Menchaca Resendiz, Yarik and Klinger, Roman},
booktitle = {Proceedings of the 16th International Conference on
Natural Language Generation},
month = sep,
year = {2023},
address = {Prague, Czech Republic},
publisher = {Association for Computational Linguistics},
internaltype = {conferenceproc},
archiveprefix = {arXiv},
eprint = {2307.14004},
url = {https://aclanthology.org/2023.inlg-1.26},
pdf = {https://www.romanklinger.de/publications/MenchacaResendiz_Klinger_INLG2023.pdf}
}
@inproceedings{MenchacaResendiz2023b,
title = {Emotion-Conditioned Text Generation through
Automatic Prompt Optimization},
author = {Menchaca Resendiz, Yarik and Klinger, Roman},
booktitle = {Proceedings of the 1st Workshop on Taming Large
Language Models: Controllability in the era of
Interactive Assistants!},
month = sep,
year = 2023,
address = {Prague, Czech Republic},
publisher = {Association for Computational Linguistics},
internaltype = {workshop},
archiveprefix = {arXiv},
eprint = {2308.04857},
pdf = {https://www.romanklinger.de/publications/MenchacaResendiz_Klinger_TLLM2023.pdf}
}
@inproceedings{Wegge2023,
author = {Maximilian Wegge and Roman Klinger},
title = {Automatic Emotion Experiencer Recognition},
booktitle = {3rd Workshop on Computational Linguistics for the
Political and Social Sciences (CPSS)},
year = 2023,
month = may,
pdf = {https://www.romanklinger.de/publications/WeggeKlinger2023.pdf},
internaltype = {workshop},
archiveprefix = {arXiv},
eprint = {2305.16731}
}
@inproceedings{Velutharambath2023,
title = {{UNIDECOR}: A Unified Deception Corpus for
Cross-Corpus Deception Detection},
author = {Velutharambath, Aswathy and Klinger, Roman},
booktitle = {Proceedings of the 13th Workshop on Computational
Approaches to Subjectivity, Sentiment, {\&} Social
Media Analysis},
month = jul,
year = {2023},
address = {Toronto, Canada},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2023.wassa-1.5},
pages = {39--51},
abstract = {Verbal deception has been studied in psychology,
forensics, and computational linguistics for a
variety of reasons, like understanding behaviour
patterns, identifying false testimonies, and
detecting deception in online communication. Varying
motivations across research fields lead to
differences in the domain choices to study and in
the conceptualization of deception, making it hard
to compare models and build robust deception
detection systems for a given language. With this
paper, we improve this situation by surveying
available English deception datasets which include
domains like social media reviews, court
testimonials, opinion statements on specific topics,
and deceptive dialogues from online strategy
games. We consolidate these datasets into a single
unified corpus. Based on this resource, we conduct a
correlation analysis of linguistic cues of deception
across datasets to understand the differences and
perform cross-corpus modeling experiments which show
that a cross-domain generalization is challenging to
achieve. The unified deception corpus (UNIDECOR) can
be obtained from
https://www.ims.uni-stuttgart.de/data/unidecor.},
internaltype = {workshop},
pdf = {https://www.romanklinger.de/publications/VelutharambathKlinger_UNIDECOR_WASSA2023.pdf},
archiveprefix = {arXiv},
eprint = {2306.02827}
}
@incollection{Klinger2023,
address = {Berlin, Heidelberg},
title = {Emotionsklassifikation in {Texten} unter
{Berücksichtigung} des {Komponentenprozessmodells}},
isbn = {978-3-662-65963-2 978-3-662-65964-9},
url = {https://link.springer.com/10.1007/978-3-662-65964-9_7},
abstract = {Zusammenfassung Ein wichtiger Bestandteil unserer
alltäglichen Kommunikation, neben der Mitteilung und
Beschreibung von Ereignissen und Fakten, ist der
Ausdruck von Emotionen, welcher auch Bestandteil von
Hassrede ist: Es wird zum Beispiel Wut zum Ausdruck
gebracht, was wiederum bei den Betroffenen Angst,
Traurigkeit oder vielleicht auch Überraschung
auslösen kann. In der maschinellen Verarbeitung von
Sprache haben sich in der letzten Zeit einige
konkrete Aufgaben, welche Teil der Emotionsanalyse
in Text sind, herauskristallisiert. Diese sind zum
einen Klassifikationsaufgaben (welche Emotion drückt
ein Text aus?) und zum anderen relationale
Strukturlernaufgaben (welche Wörter bezeichnen die
Person, die eine Emotion fühlt und welche Wörter
lassen auf die Ursache der Emotion schließen?). Wir
verschaffen uns in diesem Kapitel einen kurzen
Überblick über das Feld und diskutieren im Anschluss
etwas genauer, wie sich die Beschreibungen von
Emotionen in verschiedenen Domänen unterscheiden und
wie Ereignisbeschreibungen mit Hilfe psychologischer
Theorien mit Emotionen zusammengebracht werden
können. Insbesondere analysieren wir auf Basis des
Emotions-Komponenten-Prozessmodells, auf welche
Komponenten von Emotionen (subjektives Gefühl,
kognitive Evaluation, Körperreaktion, Ausdruck,
Motivation) Autor:innen zugreifen, und stellen fest,
dass diese Verteilung zwischen sozialen Medien und
Literatur unterschiedlich ist. In beiden Domänen
spielt aber die kognitive Komponente zur
Interpretation von Emotionen eine wichtige
Rolle. Dies zeigt auf, dass insbesondere der
Ereignisinterpretation Aufmerksamkeit geschenkt
werden muss, um implizit kommunizierte Emotionen
aufzudecken. Dies motiviert uns, Emotionen mit Hilfe
der Appraisaltheorien zu analysieren, welche den
Zusammenhang zwischen kognitiven Prozessen und
Emotionen erklären. Zu beiden Konzepten – dem
Komponentenmodell und den Appraisaltheorien –
präsentieren wir Textkorpora und
Klassifikationsmodelle.},
language = {de},
booktitle = {Digitale {Hate} {Speech}},
publisher = {Springer Berlin Heidelberg},
author = {Klinger, Roman},
editor = {Jaki, Sylvia and Steiger, Stefan},
year = {2023},
doi = {10.1007/978-3-662-65964-9_7},
pages = {131--154},
internaltype = {conferenceproc}
}
@inproceedings{StajnerKlinger2023,
title = {Emotion Analysis from Texts},
author = {\v{S}tajner, Sanja and Klinger, Roman},
booktitle = {Proceedings of the 17th Conference of the European
Chapter of the Association for Computational
Linguistics: Tutorial Abstracts},
month = may,
year = {2023},
address = {Dubrovnik, Croatia},
publisher = {Association for Computational Linguistics},
url = {https://aclanthology.org/2023.eacl-tutorials.2},
pages = {7--12},
abstract = {Emotion analysis in text is an area of research that
encompasses a set of various natural language
processing (NLP) tasks, including classification and
regression settings, as well as structured
prediction tasks like role labelling or stimulus
detection. In this tutorial, we provide an overview
of research from emotion psychology which sets the
ground for choosing adequate NLP methodology, and
present existing resources and classification
methods used for emotion analysis in texts. We
further discuss appraisal theories and how events
can be interpreted regarding their presumably caused
emotion and briefly introduce emotion role
labelling. In addition to these technical topics, we
discuss the use cases of emotion analysis in text,
their societal impact, ethical considerations, as
well as the main challenges in the field.},
pdf = {https://eacl2023tutorial.github.io/EmotionAnalysis-EACL-Tutorial-Summary.pdf},
internaltype = {abstrconf}
}
@inproceedings{Wuehrl2023,
author = {Amelie W\"uhrl and Lara Grimminger and Roman
Klinger},
title = {An Entity-based Claim Extraction Pipeline for
Real-world Fact-checking},
month = {May},
year = {2023},
booktitle = {Proceedings of the Sixth Fact Extraction and
VERification Workshop (FEVER)},
address = {Dubrovnik, Croatia},
organization = {Association for Computational Linguistics},
pdf = {https://www.romanklinger.de/publications/WuehrlKlingerFEVER2023.pdf},
url = {https://aclanthology.org/2023.fever-1.3},
pages = {29–37},
internaltype = {workshop},
archiveprefix = {arXiv},
eprint = {2304.05268}
}
@article{Troiano2023,
author = {Enrica Troiano and Laura Oberl\"ander and Roman
Klinger},
title = {Dimensional Modeling of Emotions in Text with
Appraisal Theories: Corpus Creation, Annotation
Reliability, and Prediction},
journal = {Computational Linguistics},
number = 1,
volume = 49,
month = mar,
year = 2023,
address = {Cambridge, MA},
publisher = {MIT Press},
abstract = {The most prominent tasks in emotion analysis are to
assign emotions to texts and to understand how
emotions manifest in language. An observation for
NLP is that emotions can be communicated implicitly
by referring to events, appealing to an empathetic,
intersubjective understanding of events, even
without explicitly mentioning an emotion name. In
psychology, the class of emotion theories known as
appraisal theories aims at explaining the link
between events and emotions. Appraisals can be
formalized as variables that measure a cognitive
evaluation by people living through an event that
they consider relevant. They include the assessment
if an event is novel, if the person considers
themselves to be responsible, if it is in line with
the own goals, and many others. Such appraisals
explain which emotions are developed based on an
event, e.g., that a novel situation can induce
surprise or one with uncertain consequences could
evoke fear. We analyze the suitability of appraisal
theories for emotion analysis in text with the goal
of understanding if appraisal concepts can reliably
be reconstructed by annotators, if they can be
predicted by text classifiers, and if appraisal
concepts help to identify emotion categories. To
achieve that, we compile a corpus by asking people
to textually describe events that triggered
particular emotions and to disclose their
appraisals. Then, we ask readers to reconstruct
emotions and appraisals from the text. This setup
allows us to measure if emotions and appraisals can
be recovered purely from text and provides a human
baseline. Our comparison of text classification
methods to human annotators shows that both can
reliably detect emotions and appraisals with similar
performance. Therefore, appraisals constitute an
alternative computational emotion analysis paradigm
and further improve the categorization of emotions
in text with joint models.},
doi = {10.1162/coli_a_00461},
url = {https://doi.org/10.1162/coli_a_00461},
internaltype = {journal},
archiveprefix = {arXiv},
eprint = {2206.05238}
}