Timing: 01.10.2020 – 31.12.2024
Funding: Förderung des Bundesministeriums für Bildung und Forschung von KI-Nachwuchswissenschaftlerinnen

About the Project: The DynSoDA project will model the discourse aspects of language together with the deep representations of user characteristics and latent social network profiles derived from online dialogues. In contrast to current approaches, user representations will be treated as dynamically contextual. The project further envisions the use of transfer learning techniques at multiple levels of abstraction to work robustly across a range of NLP tasks related to social discourse (such as opinion detection, hate speech identification, or argument persuasiveness prediction).

Principal Investigators:  Prof. Dr. Lucie Flek

Publications:
- Unifying the Extremes: Developing a Unified Model for Detecting and Predicting Extremist Traits and Radicalization, A Lahnala, V Varadarajan, L Flek, HA Schwartz, RL Boyd, arXiv preprint arXiv:2501.04820 (2025)
- The Muddy Waters of Modeling Empathy in Language: The Practical Impacts of Theoretical Constructs, A Lahnala, C Welch, D Jurgens, L Flek, arXiv preprint arXiv:2501.14981 (2025)  
- Perspective Taking through Generating Responses to Conflict Situations, J Plepi, C Welch, L Flek, Findings of the Association for Computational Linguistics ACL 2024, 6482-6497
- Proceedings of the 1st Human-Centered Large Language Modeling Workshop, N Soni, L Flek, A Sharma, D Yang, S Hooker, HA Schwartz, Proceedings of the 1st Human-Centered Large Language Modeling Workshop
- Do Multilingual Large Language Models Mitigate Stereotype Bias? S Nie, M Fromm, C Welch, R Görge, A Karimi, J Plepi, NA Mowmita, ..., arXiv preprint arXiv:2407.05740
- EmPO: Emotion Grounding for Empathetic Response Generation through Preference Optimization, O Sotolar, V Formanek, A Debnath, A Lahnala, C Welch, L FLek, arXiv preprint arXiv:2406.19071
- Explaining GPT-4's Schema of Depression Using Machine Behavior Analysis, AV Ganesan, V Varadarajan, YK Lal, VC Eijsbroek, K Kjell, ONE Kjell, ..., arXiv preprint arXiv:2411.13800 (2024)
- Harnessing Personalization Methods to Identify and Predict Unreliable Information Spreader Behavior, Ashraf, Shaina and Gruschka, Fabio and Flek, Lucie and Welch, Charles, WOAH 2024
- A Perspectivist Corpus of Numbers in Social Judgements, M May, L Flek, C Welch, Proceedings of the 3rd Workshop on Perspectivist Approaches to NLP …
- Archetypes and Entropy: Theory-Driven Extraction of Evidence for Suicide Risk, V Varadarajan, A Lahnala, AV Ganesan, G Dey, S Mangalik, AM Bucur, ..., Proceedings of the 9th Workshop on Computational Linguistics and Clinical …
- Corpus Considerations for Annotator Modeling and Scaling, OO Sarumi, B Neuendorf, J Plepi, L Flek, J Schlötterer, C Welch, arXiv preprint arXiv:2404.02340
- LeadEmpathy: An Expert Annotated German Dataset of Empathy in Written Leadership Communication, Sedefoglu, Didem and Lahnala, Allison and Wagner, Jasmin and Flek, Lucie and Ohly, Sandra, LREC 2024
- Appraisal Framework for Clinical Empathy: A Novel Application to Breaking Bad News Conversations, Lahnala, Allison and Neuendorf, Béla and Thomin, Alexander and Welch, Charles and Stibane, Tina and Flek, Lucie, LREC 2024
- Vanishing Boundaries: A Unifying Account of Multidimensional Emotion Dynamics and Alterations in Depression, AM Bucur, TA Koosha, A Cosma, L Flek, SE Thanarajah, F Bernhard, ..., OSF
- Personalized Intended and Perceived Sarcasm Detection on Twitter, Plepi, J., Buski, M., Flek, L., NLPCSS 2023
- Domain Transfer for Empathy, Distress, and Personality Prediction, Gruschka, F., Lahnala, A., Welch, C., Flek, L., WASSA 2023
- Style Locality for Controllable Generation with kNN Language Models, Nawezi, G., Flek, L., Welch, C., GEM 2023
- OpinionConv: Conversational Product Search with Grounded Opinions, Sadiri Javadi, V., Potthast, M., Flek, L., SIGDIAL 2023
- Challenges of GPT-3-Based Conversational Agents for Healthcare, Lechner, F., Lahnala, A., Welch, C., Flek, L., RANLP 2023
- OK Boomer: Probing the Socio-Demographic Divide in Echo Chambers, Geiss, H. J., Sakketou, F., Flek, L., NLP for Social Media 2022
- CAISA at SocialDisNER: Robust Cross-Lingual Detection of Disease Mentions on Social Media, Karimi, A., Flek, L., SMM4H @ CoLing 2022
- The Impact of Differential Privacy on Group Disparity Mitigation, Hansen, V. P. B., Neerkaje, A. T., Sawhney, R., Flek, L., Sogaard, A., PrivacyNLP 2022
- Refining Diagnosis Paths for Medical Diagnosis Based on an Augmented Knowledge Graph, Heilig, N. et al., SeWeBMeDA @ ESWC 2022
- UserNLP’22: Workshop on User-centered NLP, Huang, X. et al., WWW Conference 2022
- Paraphrasing-Based Data Augmentation for Dialogue Systems, Vogel, L., Flek, L., TSD 2022
- Investigating User Radicalization: A Novel Dataset for Identifying Fine-Grained Temporal Shifts in Opinion, Sakketou, F., Lahnala, A., Vogel, L., Flek, L., LREC 2022
- A New Dataset for Identifying Misinformation Spreaders and Political Bias, Sakketou, F., Plepi, J., Cervero, R., Rosso, P., Flek, L., LREC 2022 
- Unifying Data Perspectivism and Personalization: An Application to Social Norms, Plepi, J., Neuendorf, B., Flek, L., Welch, C., EMNLP 2022
- Mitigating Toxic Degeneration with Empathetic Data, Lahnala, A., Welch, C., Neuendorf, B., Flek, L., NAACL-HLT 2022
- A Critical Reflection and Forward Perspective on Empathy and NLP, Lahnala, A., Welch, C., Jurgens, D., Flek, L., EMNLP 2022
- CAISA at WASSA 2022: Adapter-Tuning for Empathy Prediction, Lahnala, A., Welch, C., Flek, L., WASSA 2022
- Temporal Graph Analysis of Misinformation Spreaders, Sakketou, F., Plepi, J., Geiss, J.-H., Flek, L., TextGraphs @ CoLing 2022
- Understanding Interpersonal Conflict Types and Their Impact on Perception Classification, Welch, C., Plepi, J., Neuendorf, B., Flek, L., NLPCSS @ EMNLP
- Perceived and Intended Sarcasm Detection with Graph Attention Networks, Plepi, J., Flek, L., EMNLP 2021
- PHASE: Learning Emotional Phase-aware Representations for Suicide Ideation Detection on Social Media, Sawhney, R., Joshi, H., Shah, R. R., Flek, L., EACL 2021
- Suicide Ideation Detection via Social and Temporal User Representations using Hyperbolic Learning, Sawhney, R., Joshi, H., Shah, R. R., Flek, L., NAACL 2021
- Automated Template Paraphrasing for Conversational Assistants, Vogel, L., Flek, L., Widening NLP @ EMNLP 2021
­- HYPMIX: Hyperbolic Interpolative Data Augmentation, Sawhney, R., Thakkar, M., Agarwal, S., Jin, D., Yang, D., Flek, L., EMNLP 2021
- Towards User-Centric Text-to-Text Generation: A Survey, Yang, D., Flek, L., TSD 2021