| 2026 | EACL | Emotionally Charged, Logically Blurred: AI-driven Emotional Framing Impairs Human Fallacy Detection. | Yanran Chen, Lynn Greschner, Roman Klinger, Michael Klenk, Steffen Eger |
| 2026 | LREC | Categorical Emotions or Appraisals - Which Emotion Model Explains Argument Convincingness Better? | Lynn Greschner, Meike Bauer, Sabine Weber, Roman Klinger |
| 2026 | LREC | Trust Me, I Can Convince You: The Contextualized Argument Appraisal Framework and the ContArgA Corpus. | Lynn Greschner, Sabine Weber, Roman Klinger |
| 2026 | LREC | PARL: Prompt-based Agents for Reinforcement Learning. | Yarik Menchaca Resendiz, Roman Klinger |
| 2026 | LREC | Entity-Level Sentiment Analysis with Sentence Relevance Detection. | Egil Rnningstad, Roman Klinger, Lilja vrelid, Erik Velldal |
| 2026 | LREC | Disambiguation of Emotion Annotations by Contextualizing Events in Plausible Narratives. | Johannes Schfer, Roman Klinger |
| 2026 | LREC | Less Is More? The Role of Demographic Author Information in Emotion Classification of Ambiguous Text. | Sabine Weber, Lynn Greschner, Roman Klinger |
| 2025 | ACL | Donate or Create? Comparing Data Collection Strategies for Emotion-labeled Multimodal Social Media Posts. | Christopher Bagdon, Aidan Combs, Carina Silberer, Roman Klinger |
| 2025 | ACL | iPrOp: Interactive Prompt Optimization for Large Language Models with a Human in the Loop. | Jiahui Li, Roman Klinger |
| 2025 | ACL | Which Demographics do LLMs Default to During Annotation? | Johannes Schfer, Aidan Combs, Christopher Bagdon, Jiahui Li, Nadine Probol, Lynn Greschner, Sean Papay, Yarik Menchaca Resendiz, Aswathy Velutharambath, Amelie Whrl, Sabine Weber, Roman Klinger |
| 2025 | COLING | MOPO: Multi-Objective Prompt Optimization for Affective Text Generation. | Yarik Menchaca Resendiz, Roman Klinger |
| 2025 | IJCNLP | Are Humans as Brittle as Large Language Models? | Jiahui Li, Sean Papay, Roman Klinger |
| 2024 | ACL | Understanding Fine-grained Distortions in Reports of Scientific Findings. | Amelie Whrl, Dustin Wright, Roman Klinger, Isabelle Augenstein |
| 2024 | COLING | Can Factual Statements Be Deceptive? The DeFaBel Corpus of Belief-based Deception. | Aswathy Velutharambath, Roman Klinger, Amelie Whrl |
| 2024 | COLING | EmoProgress: Cumulated Emotion Progression Analysis in Dreams and Customer Service Dialogues. | Eileen Wemmer, Sofie Labat, Roman Klinger |
| 2024 | EACL | What Makes Medical Claims (Un)Verifiable? Analyzing Entity and Relation Properties for Fact Verification. | Amelie Whrl, Yarik Menchaca Resendiz, Lara Grimminger, Roman Klinger |
| 2024 | EMNLP | Dealing with Controversy: An Emotion and Coping Strategy Corpus Based on Role Playing. | Enrica Troiano, Sofie Labat, Marco Stranisci, Rossana Damiano, Viviana Patti, Roman Klinger |
| 2024 | EMNLP | How Entangled is Factuality and Deception in German? | Aswathy Velutharambath, Amelie Whrl, Roman Klinger |
| 2024 | NAACL | "You are an expert annotator": Automatic Best-Worst-Scaling Annotations for Emotion Intensity Modeling. | Christopher Bagdon, Prathamesh Karmalkar, Harsha Gurulingappa, Roman Klinger |
| 2024 | WWW | English Prompts are Better for NLI-based Zero-Shot Emotion Classification than Target-Language Prompts. | Patrick Barei, Roman Klinger, Jeremy Barnes |
| 2023 | INLG | Affective Natural Language Generation of Event Descriptions through Fine-grained Appraisal Conditions. | Yarik Menchaca Resendiz, Roman Klinger |
| 2022 | COLING | Natural Language Inference Prompts for Zero-shot Emotion Classification in Text across Corpora. | Flor Miriam Plaza del Arco, Mara Teresa Martn Valdivia, Roman Klinger |
| 2022 | ICLR | Constraining Linear-chain CRFs to Regular Languages. | Sean Papay, Roman Klinger, Sebastian Pad |
| 2022 | LREC | CoVERT: A Corpus of Fact-checked Biomedical COVID-19 Tweets. | Isabelle Mohr, Amelie Whrl, Roman Klinger |
| 2022 | LREC | x-enVENT: A Corpus of Event Descriptions with Experiencer-specific Emotion and Appraisal Annotations. | Enrica Troiano, Laura Oberlnder, Maximilian Wegge, Roman Klinger |
| 2022 | LREC | Recovering Patient Journeys: A Corpus of Biomedical Entities and Relations on Twitter (BEAR). | Amelie Whrl, Roman Klinger |
| 2022 | NAACL | Embarrassingly Simple Performance Prediction for Abductive Natural Language Inference. | Emils Kadikis, Vaibhav Srivastav, Roman Klinger |
| 2020 | COLING | Appraisal Theories for Emotion Classification in Text. | Jan Hofmann, Enrica Troiano, Kai Sassenberg, Roman Klinger |
| 2020 | COLING | Lost in Back-Translation: Emotion Preservation in Neural Machine Translation. | Enrica Troiano, Roman Klinger, Sebastian Pad |
| 2020 | EMNLP | Dissecting Span Identification Tasks with Performance Prediction. | Sean Papay, Roman Klinger, Sebastian Pad |
| 2020 | LREC | GoodNewsEveryone: A Corpus of News Headlines Annotated with Emotions, Semantic Roles, and Reader Perception. | Laura Ana Maria Bostan, Evgeny Kim, Roman Klinger |
| 2020 | LREC | PO-EMO: Conceptualization, Annotation, and Modeling of Aesthetic Emotions in German and English Poetry. | Thomas N. Haider, Steffen Eger, Evgeny Kim, Roman Klinger, Winfried Menninghaus |
| 2020 | LREC | Automatic Section Recognition in Obituaries. | Valentino Sabbatino, Laura Ana Maria Bostan, Roman Klinger |
| 2019 | ACL | Crowdsourcing and Validating Event-focused Emotion Corpora for German and English. | Enrica Troiano, Sebastian Pad, Roman Klinger |
| 2019 | NAACL | Frowning Frodo, Wincing Leia, and a Seriously Great Friendship: Learning to Classify Emotional Relationships of Fictional Characters. | Evgeny Kim, Roman Klinger |
| 2019 | NAACL | Adversarial Training for Satire Detection: Controlling for Confounding Variables. | Robert McHardy, Heike Adel, Roman Klinger |
| 2018 | ACL | Bilingual Sentiment Embeddings: Joint Projection of Sentiment Across Languages. | Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde |
| 2018 | ACL | SANTO: A Web-based Annotation Tool for Ontology-driven Slot Filling. | Matthias Hartung, Hendrik ter Horst, Frank Grimm, Tim Diekmann, Roman Klinger, Philipp Cimiano |
| 2018 | COLING | Projecting Embeddings for Domain Adaption: Joint Modeling of Sentiment Analysis in Diverse Domains. | Jeremy Barnes, Roman Klinger, Sabine Schulte im Walde |
| 2018 | COLING | An Analysis of Annotated Corpora for Emotion Classification in Text. | Laura Ana Maria Bostan, Roman Klinger |
| 2018 | COLING | Who Feels What and Why? Annotation of a Literature Corpus with Semantic Roles of Emotions. | Evgeny Kim, Roman Klinger |
| 2018 | DSAA | An Empirical Analysis of the Role of Amplifiers, Downtoners, and Negations in Emotion Classification in Microblogs. | Florian Strohm, Roman Klinger |
| 2018 | EMNLP | DERE: A Task and Domain-Independent Slot Filling Framework for Declarative Relation Extraction. | Heike Adel, Laura Ana Maria Bostan, Sean Papay, Sebastian Pad, Roman Klinger |
| 2018 | NLDB | Assessing the Impact of Single and Pairwise Slot Constraints in a Factor Graph Model for Template-Based Information Extraction. | Hendrik ter Horst, Matthias Hartung, Roman Klinger, Nicole Brazda, Hans Werner Mller, Philipp Cimiano |
| 2018 | NLDB | On the Semantic Similarity of Disease Mentions in MEDLINE and Twitter. | Camilo Thorne, Roman Klinger |
| 2017 | NLDB | Identifying Right-Wing Extremism in German Twitter Profiles: A Classification Approach. | Matthias Hartung, Roman Klinger, Franziska Schmidtke, Lars Vogel |
| 2017 | NLDB | What You Use, Not What You Do: Automatic Classification of Recipes. | Hanna Kicherer, Marcel Dittrich, Lukas Grebe, Christian Scheible, Roman Klinger |
| 2017 | NLDB | Does Optical Character Recognition and Caption Generation Improve Emotion Detection in Microblog Posts? | Roman Klinger |
| 2017 | NLDB | Fine-Grained Opinion Mining from Mobile App Reviews with Word Embedding Features. | Mario Snger, Ulf Leser, Roman Klinger |
| 2017 | RANLP | Towards Confidence Estimation for Typed Protein-Protein Relation Extraction. | Camilo Thorne, Roman Klinger |
| 2016 | ACL | Model Architectures for Quotation Detection. | Christian Scheible, Roman Klinger, Sebastian Pad |
| 2016 | LREC | SCARE ― The Sentiment Corpus of App Reviews with Fine-grained Annotations in German. | Mario Snger, Ulf Leser, Steffen Kemmerer, Peter Adolphs, Roman Klinger |
| 2015 | CoNLL | Instance Selection Improves Cross-Lingual Model Training for Fine-Grained Sentiment Analysis. | Roman Klinger, Philipp Cimiano |
| 2014 | LREC | The USAGE review corpus for fine grained multi lingual opinion analysis. | Roman Klinger, Philipp Cimiano |
| 2013 | ACL | Bi-directional Inter-dependencies of Subjective Expressions and Targets and their Value for a Joint Model. | Roman Klinger, Philipp Cimiano |
| 2013 | EMNLP | Orthonormal Explicit Topic Analysis for Cross-Lingual Document Matching. | John Philip McCrae, Philipp Cimiano, Roman Klinger |
| 2013 | ICDM | Joint and Pipeline Probabilistic Models for Fine-Grained Sentiment Analysis: Extracting Aspects, Subjective Phrases and their Relations. | Roman Klinger, Philipp Cimiano |
| 2012 | WEBIST | E-Government and Policy Simulation in Intelligent Virtual Environments. | Fotis Aisopos, Magdalini Kardara, Philipp Senger, Roman Klinger, Athanasios Papaoikonomou, Konstantinos Tserpes, Michael Gardner, Theodora A. Varvarigou |
| 2011 | RANLP | Automatically Selected Skip Edges in Conditional Random Fields for Named Entity Recognition. | Roman Klinger |
| 2009 | RANLP | Feature Subset Selection in Conditional Random Fields for Named Entity Recognition. | Roman Klinger, Christoph M. Friedrich |
| 2009 | RANLP | User's Choice of Precision and Recall in Named Entity Recognition. | Roman Klinger, Christoph M. Friedrich |
| 2008 | ISMB | Detection of IUPAC and IUPAC-like chemical names. | Roman Klinger, Corinna Kolrik, Juliane Fluck, Martin Hofmann-Apitius, Christoph M. Friedrich |