Sérgio Nunes
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Sérgio Nunes has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
- Cristina Ribeiro
University of Porto
14 shared publications - Alípio Mário Jorge
Universidade do Porto
7 shared publications - José Devezas
INESC TEC and Faculty of Engineering, University of Porto, Porto, Portugal
7 shared publications - Ricardo Campos
University of Beira Interior, Covilhã, Portugal and INESC TEC, Porto, Portugal
7 shared publications - Gabriel David
Universidade do Porto
5 shared publications - Melinda Oroszlányová
College of Engineering and Technology, American University of the Middle East, Egaila 54200, Kuwait
5 shared publications
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5140-5145
Labadain Chat: A Conversational Agent for the Tetun Language
Large language model (LLM)-based conversational assistants are designed for general-purpose conversation tasks and are primarily optimized for high-resource languages. Although these systems support some low-resource languages (LRLs), their responses often fall short of user expectations. Consequently, speakers of LRLs remain marginalized and unable to fully benefit from advances in LLMs. These challenges underscore the need for targeted, language-specific solutions that can effectively serve underrepresented language communities. This study presents Labadain Chat, a conversational agent for Tetun, a low-resource language spoken by over 932,000 people in Timor-Leste. We adapt existing LLMs to Tetun using language-specific prompting strategies and report on the system's architecture, features, applications, and utility for the Tetun-speaking community. Results from the user study show a high task success rate for Labadain Chat (91%, with substantial inter-annotator agreement, Cohen's κ=0.67) and high user satisfaction (4.30 out of 5, with Cohen's weighted κ=0.75), demonstrating the effectiveness of language-specific LLM customization for Tetun. Overall, this study provides a practical pathway toward promoting equitable access to AI-powered information services for the Tetun-speaking community and suggests an adaptable methodology that can be applied to other under-resourced languages in similar contexts. The system is publicly available at https://www.labadain.com, with mobile applications for both iOS and Android.
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 5140-5145
Open AccessLabadain Chat: A Conversational Agent for the Tetun Language
Large language model (LLM)-based conversational assistants are designed for general-purpose conversation tasks and are primarily optimized for high-resource languages. Although these systems support some low-resource languages (LRLs), their responses often fall short of user expectations. Consequently, speakers of LRLs remain marginalized and unable to fully benefit from advances in LLMs. These challenges underscore the need for targeted, language-specific solutions that can effectively serve underrepresented language communities. This study presents Labadain Chat, a conversational agent for Tetun, a low-resource language spoken by over 932,000 people in Timor-Leste. We adapt existing LLMs to Tetun using language-specific prompting strategies and report on the system's architecture, features, applications, and utility for the Tetun-speaking community. Results from the user study show a high task success rate for Labadain Chat (91%, with substantial inter-annotator agreement, Cohen's κ=0.67) and high user satisfaction (4.30 out of 5, with Cohen's weighted κ=0.75), demonstrating the effectiveness of language-specific LLM customization for Tetun. Overall, this study provides a practical pathway toward promoting equitable access to AI-powered information services for the Tetun-speaking community and suggests an adaptable methodology that can be applied to other under-resourced languages in similar contexts. The system is publicly available at https://www.labadain.com, with mobile applications for both iOS and Android.
- Open Access
- 14 April 2026
- Published by Springer Nature in AI and Ethics
- Vol. 6 (2) , 252
Ethical dimensions of AI-supported fact-checking in elderly health care: a qualitative exploratory study
This article examines the ethical dimensions of AI-supported fact-checking tools in the context of elderly health care, focusing on how caregivers interpret trust, credibility, and cultural relevance when engaging with AI-mediated information. The study adopts a qualitative, exploratory methodology grounded in Value Sensitive Design and Human–Machine Communication. Empirical data were collected through a co-design workshop, focus group discussions, empathy map exercises, and descriptive questionnaires with elderly caregivers in a rural Portuguese context. Rather than aiming for statistical generalization, the research prioritizes contextual understanding and value articulation. The findings reveal that caregivers evaluate AI-supported fact-checking solutions not only in terms of informational accuracy, but also through ethical considerations such as protection, inclusion, trustworthiness, and perceived legitimacy. Differences between traditional journalistic approaches, automated AI solutions, and visual or animated formats were less salient than participants’ interpretations of how these tools aligned with their lived experiences and communicative norms. By foregrounding the perspectives of caregivers in a socioeconomically constrained setting, this study contributes empirically grounded insights to debates in AI ethics and responsible AI design. It highlights the importance of culturally sensitive, user-centered approaches when deploying AI technologies in health communication and misinformation management, particularly for vulnerable populations.
- 14 April 2026
- Published by Springer Nature in AI and Ethics
- Vol. 6 (2) , 252
Open AccessEthical dimensions of AI-supported fact-checking in elderly health care: a qualitative exploratory study
This article examines the ethical dimensions of AI-supported fact-checking tools in the context of elderly health care, focusing on how caregivers interpret trust, credibility, and cultural relevance when engaging with AI-mediated information. The study adopts a qualitative, exploratory methodology grounded in Value Sensitive Design and Human–Machine Communication. Empirical data were collected through a co-design workshop, focus group discussions, empathy map exercises, and descriptive questionnaires with elderly caregivers in a rural Portuguese context. Rather than aiming for statistical generalization, the research prioritizes contextual understanding and value articulation. The findings reveal that caregivers evaluate AI-supported fact-checking solutions not only in terms of informational accuracy, but also through ethical considerations such as protection, inclusion, trustworthiness, and perceived legitimacy. Differences between traditional journalistic approaches, automated AI solutions, and visual or animated formats were less salient than participants’ interpretations of how these tools aligned with their lived experiences and communicative norms. By foregrounding the perspectives of caregivers in a socioeconomically constrained setting, this study contributes empirically grounded insights to debates in AI ethics and responsible AI design. It highlights the importance of culturally sensitive, user-centered approaches when deploying AI technologies in health communication and misinformation management, particularly for vulnerable populations.
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8705-8708
CitiLink-Summ: A Dataset of Discussion Subjects Summaries in European Portuguese Municipal Meeting Minutes
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 8705-8708
Open AccessCitiLink-Summ: A Dataset of Discussion Subjects Summaries in European Portuguese Municipal Meeting Minutes
- 24 March 2026
- Published by Springer Nature
- p. 511-527
CitiLink-Minutes: A Multilayer Annotated Dataset of Municipal Meeting Minutes
- 24 March 2026
- Published by Springer Nature
- p. 511-527
CitiLink-Minutes: A Multilayer Annotated Dataset of Municipal Meeting Minutes
- 24 March 2026
- Published by Springer Nature
- p. 193-199
CitiLink: Enhancing Municipal Transparency and Citizen Engagement Through Searchable Meeting Minutes
- 24 March 2026
- Published by Springer Nature
- p. 193-199
CitiLink: Enhancing Municipal Transparency and Citizen Engagement Through Searchable Meeting Minutes
- 24 March 2026
- Published by Springer Nature
- p. 544-560
ClaimPT: A Portuguese Dataset of Annotated Claims in News Articles
- 24 March 2026
- Published by Springer Nature
- p. 544-560
ClaimPT: A Portuguese Dataset of Annotated Claims in News Articles
- 16 September 2025
- Published by Springer Nature
- p. 262-275
Cross-Lingual Information Retrieval in Tetun for Ad-Hoc Search
- 16 September 2025
- Published by Springer Nature
- p. 262-275
Cross-Lingual Information Retrieval in Tetun for Ad-Hoc Search
- 16 September 2025
- Published by Springer Nature
- p. 276-288
User Behavior in Sports Search: Entity-Centric Query and Click Log Analysis
- 16 September 2025
- Published by Springer Nature
- p. 276-288
User Behavior in Sports Search: Entity-Centric Query and Click Log Analysis
- Open Access
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 297-306
Insights into LLM-Based Conversational Search: A Study of Tetun-Speaking Users' Search Behavior
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 297-306
Open AccessInsights into LLM-Based Conversational Search: A Study of Tetun-Speaking Users' Search Behavior
- Open Access
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 264-274
Zero-Shot and Hybrid Strategies for Tetun Ad-Hoc Text Retrieval
- 18 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 264-274
Open AccessZero-Shot and Hybrid Strategies for Tetun Ad-Hoc Text Retrieval