Browsing by Author "Antunes, Ana"
Now showing 1 - 3 of 3
Results Per Page
Sort Options
- EEG Mode: emotional episode generation for social sharing of emotionsPublication . Antunes, Ana; Campos, Joana; Dias, João; Santos, Pedro A.; Prada, RuiSocial sharing of emotions (SSE) occurs when one communicates their feelings and reactions to a certain event in the course of a social interaction. The phenomenon is part of our social fabric and plays an important role in creating empathetic responses and establishing rapport. Intelligent social agents capable of SSE will have a mechanism to create and build long-term interaction with humans. In this paper, we present the Emotional Episode Generation (EEG) model, a fine-tuned GPT-2 model capable of generating emotional social talk regarding multiple event tuples in a human-like manner. Human evaluation results show that the model successfully translates one or more event-tuples into emotional episodes, reaching quality levels close to human performance. Furthermore, the model clearly expresses one emotion in each episode as well as humans. To train this model we used a public dataset and built upon it using event extraction techniques(1).
- Prompting for socially intelligent agents with chatGPTPublication . Antunes, Ana; Campos, Joana; Guimarães, Manuel; Dias, João; Santos, Pedro A.Socially Intelligent Agents (SIAs) have become increasingly popular in various contexts, including education and entertainment. However, creating complex social scenarios tailored to a designer's specific goals remains a significant challenge. The authoring burden can be substantial, limiting the potential of SIAs to deliver rich, engaging experiences. In this work, we propose leveraging the extensive knowledge stored within Large Language Models and use theory-driven prompting to extract social practices and identify appropriate social affordances for a scenario description. Our prompting approach aims to guide the system into considering the essential components (beliefs and desires) necessary to produce intentions, actions, and emotions(1). Results show that our approach produces large amounts of accurate and new information that can add value to the scenario. However, the process can introduce inaccuracies without human supervision.
- Workforce skills in family support: a systematic reviewPublication . Zegarac, Nevenka; Isakov, Anita Burgund; Nunes, Cristina; Antunes, AnaPurpose: Skills used in the practice of family support workforce are implemented in different settings and frameworks. The conceptual assumptions and epistemological frameworks of diversity are a challenge. Various paradigms of intervention, different sectors, and disciplinary involvement indicate the need to systematize and clarify knowledge in the field. Method: Using preferred reporting items for systematic reviews and meta-analyses guidelines, a systematic review was conducted, including qualitative, quantitative, and mixed-method studies on skills in the practice of family support. Results: The literature was collected in an exhaustive search of several databases, where a set of 8,489 papers was selected. The workforce skills described were the qualities of the professionals, technical skills, and specific knowledge. Discussion: Most of the studies were literature reviews, did not define specific skills, had very small samples, and had issues with bias. We discuss implications for practice in social work as well as the gaps to be covered in further research of family support.