Sathya Bursic


2024

pdf
LLMs of Catan: Exploring Pragmatic Capabilities of Generative Chatbots Through Prediction and Classification of Dialogue Acts in Boardgames’ Multi-party Dialogues
Andrea Martinenghi | Gregor Donabauer | Simona Amenta | Sathya Bursic | Mathyas Giudici | Udo Kruschwitz | Franca Garzotto | Dimitri Ognibene
Proceedings of the 10th Workshop on Games and Natural Language Processing @ LREC-COLING 2024

Human language interactions involve complex processes beyond pure information exchange, for example, actions aimed at influencing beliefs and behaviors within a communicative context. In this paper, we propose to investigate the dialogue understanding capabilities of large language models (LLMs), particularly in multi-party settings, where challenges like speaker identification and turn-taking are common. Through experiments on the game-based STAC dataset, we explore zero and few-shot learning approaches for dialogue act classification in a multi-party game setting. Our intuition is that LLMs may excel in tasks framed through examples rather than formal descriptions, influenced by a range of pragmatic features like information presentation order in prompts and others. We also explore the models’ predictive abilities regarding future dialogue acts and study integrating information on dialogue act sequences to improve predictions. Our findings suggest that ChatGPT can keep up with baseline models trained from scratch for classification of certain dialogue act types but also reveal biases and limitations associated with the approach. These insights can be valuable for the development of multi-party chatbots and we try to point out directions for future research towards nuanced understanding and adaptation in diverse conversational contexts

pdf
Empowering Users and Mitigating Harm: Leveraging Nudging Principles to Enhance Social Media Safety
Gregor Donabauer | Emily Theophilou | Francesco Lomonaco | Sathya Bursic | Davide Taibi | Davinia Hernández-Leo | Udo Kruschwitz | Dimitri Ognibene
Proceedings of the Fourth Workshop on Threat, Aggression & Cyberbullying @ LREC-COLING-2024

Social media have become an integral part of our daily lives, yet they have also resulted in various negative effects on users, ranging from offensive or hateful content to the spread of misinformation. In recent years, numerous automated approaches have been proposed to identify and combat such harmful content. However, it is crucial to recognize the human aspect of users who engage with this content in designing efforts to mitigate these threats. We propose to incorporate principles of behavioral science, specifically the concept of nudging into social media platforms. Our approach involves augmenting social media feeds with informative diagrams, which provide insights into the content that users are presented. The goal of our work is to empower social media users to make well-informed decisions for themselves and for others within these platforms. Nudges serve as a means to gently draw users’ attention to content in an unintrusive manner, a crucial consideration in the context of social media. To evaluate the effectiveness of our approach, we conducted a user study involving 120 Italian-speaking participants who interacted with a social media interface augmented with these nudging diagrams. Participants who had used the augmented interface were able to outperform those using the plain interface in a successive harmful content detection test where nudging diagrams were not visible anymore. Our findings demonstrate that our approach significantly improves users’ awareness of potentially harmful content with effects lasting beyond the duration of the interaction. In this work, we provide a comprehensive overview of our experimental materials and setup, present our findings, and refer to the limitations identified during our study.