NIMS: MagIC - Documentos de conferências nacionais
URI permanente para esta coleção:
Navegar
Entradas recentes
- Delimitando a Interface Urbano-Rural em PortugalPublication . Barbosa, Bruno; Oliveira, Sandra; Caetano, Mário; Rocha, Jorge; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)O ano de 2023 apresentou uma das temporadas de incêndios mais severas das últimas duas décadas no continente europeu. Eventos extremos como ocorridos em 2017 em Portugal, superam a capacidade de controle e aumentam a exposição e o risco da população. Áreas de transição entre os territórios urbanos e os espaços rurais/florestais, denominadas como Interface Urbano-Uural (IUR), são caracterizadas pela coexistência entre edificações e vegetação. A disposição das habitações e sua localização influencia na vulnerabilidade da edificação frente ao incêndio, sendo as perdas materiais mais prováveis em áreas com densidade estrutural de baixa a intermediária e em regiões com histórico frequente de incêndios. Nosso objetivo é mapear a IUR em Portugal continental para avaliar a exposição aos incêndios entre 2000-2023 utilizando diferentes bases de dados (BD) de edificações — (i) Base Geográfica de Edifícios de Portugal (IURB), (ii) GlobalMLBuildingFootprints (IUR-M) e (iii) World Settlement Footprint (IUR-W) — para avaliar as diferenças geradas nos mapeamentos. Considerou-se área candidata (AC) à IUR aquela que apresente densidade de edificações superior a 6,17 edifícios/km² em uma janela móvel circular com raio de 100-m. Se a AC apresentar mais de 50% de material combustível (MC) é classificada como intermix; as AC que não atinjam este critério, mas estejam localizadas a até 600 metros de fragmentos de MC com área superior a 5 km2 , são classificadas como interface. A exposição aos incêndios foi quantificada utilizando os perímetros das áreas ardidas (AA) entre os anos de 2000-2023. A área total de IUR variou de 7.620 km² (IUR-B) a 13.175 km² (IUR-M). A nível nacional, somente 29% das áreas de Intermix foram identificadas consistentemente pelas três BD, 35 enquanto 47% foram mapeadas por apenas uma BD – predominantemente pela IUR-M (39,5%). As áreas de Interface apresentaram maior concordância, aproximadamente 60%. A proporção de AA na IUR variou significativamente conforme o tipo de interface e a BD utilizada. Nas zonas de Intermix, a IUR-M apresentou a maior proporção média de AA (7,1%), superando a IUR-W (2,9%) e a IUR-B (2,2%). Nas áreas de Interface a proporção média de AA foi inferior, não superando os 3,5% (IUR-M). Embora existam diferenças nos mapas de IUR gerados foram encontradas áreas de sobreposição. Essas áreas mapeadas de forma recorrente representam pontos críticos de exposição aos incêndios e devem receber atenção prioritária.
- Who Reaches the Hubs?Publication . Filonchik, Khristina; NOVA Information Management School (NOVA IMS)Every day, thousands of people travel from suburban neighbourhoods to Lisbon, each depending on a transit hub to start their journey. Yet, which hubs they turn to and how easily they can reach them remain open questions. RQ1 – How does network structure relate to accessibility? To what extent do Node2Vec embeddings and graph centrality metrics explain suburban passengers' ability to reach transit hubs within 15 minutes? RQ2 – Where do structural importance and accessibility diverge? Which hubs are highly central in the metropolitan bus network yet offer poor short-travel-time access, indicating potential first-mile bottlenecks? RQ3 – Can graph-based representations reveal functional hub types? Do embeddings and clustering uncover distinct categories of hubs with characteristic accessibility and network roles?
- WAVePublication . Perezhohin, Yuriy; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)Automatic Speech Recognition (ASR) for low-resource languages often relies on synthetic speech generated by pairing Large Language Model (LLM) transcripts with Text-to-Speech (TTS) generated audio. However, blindly incorporating synthetic data can introduce mispronunciations, word omissions, and prosodic anomalies that degrade ASR performance and increase training time. Previous filtering methods assessed audio-text similarity at the sentence level, which masks localized word-level errors, a synthetic utterance may appear semantically aligned while still containing critical defects.
- Do you have AI friends?Publication . Yang, Yanrong; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)Artificial intelligence (AI)–based chatbots have emerged as potential tools to assist individuals in reducing anxiety and supporting well-being. RQ 1: What factors influence users engaged with AI-based well-being chatbots? RQ 2: How could AI-based well-being chatbot service be improved using the results of this study to improve users’ engagement and experience?
- Comparative analysis of pre and post COVID exam results in Portugal [poster]Publication . Santos, Samuel; NOVA Information Management School (NOVA IMS)The socioeconomic status (SES) tends to be “inherited at birth”. Education is key in breaking the cycle: +74% premium on salary of higher education Is there an After COVID/Before COVID (AC/BC) in education? All students were penalized, but the poorest suffered a harder impact. International assessments show Portugal has inverted a trend of improvement. Q: Did exam scores change after COVID?
- From Human to MachinePublication . Maia, Rodrigo dos Reis; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)In capital markets, earnings calls are central to investment decisions, providing stakeholders with insights into firms’ performance and strategic direction. Held quarterly, earnings calls combine mandatory and voluntary disclosures, reducing information asymmetry, supporting stock price stability, and strengthening investor confidence. Despite their importance, current evaluation approaches often examine isolated elements such as tone or textual content, without capturing the multidimensional nature of these events. The increasing prevalence of videocasts offers new opportunities to analyse verbal and non-verbal cues, such as vocal tone and facial expressions, providing richer evidence of managerial sentiment. This study addresses a key gap by proposing a robust scale for evaluating earnings calls. Integrating dimensions of regulated disclosures, voluntary communication, management forecasts, and AI-driven analytical tools, the research identifies core components of corporate disclosure grounded in financial communication literature. Scale development followed a rigorous process: initial item generation, expert review, pilot testing with financial professionals, and survey data collection from investors and analysts. Exploratory factor analysis refined the structure and validated the instrument. The resulting scale aims to offer a reliable tool to assess earnings call effectiveness and advance research in corporate disclosure, investor relations, and managerial communication.
- Analyzing engagement in virtual teamsPublication . Barreiras, Pedro; Information Management Research Center (MagIC) - NOVA Information Management School; NOVA Information Management School (NOVA IMS)From Videoconferencing to Virtual Reality In 2019, only about 5% of employees worked remotely, despite the concept dating back to the 1970s. After the COVID-19 pandemic emerged, organizations relied on videoconferencing (VC) for remote meetings. Consequently, businesses unprepared for the transition to VC were significantly impacted. Therefore, to address such issues and be better prepared for the future, we must contribute to a greater understanding of the next technological shift. From Videoconferencing to Virtual Reality (VR): VR is emerging as a potential alternative to VC. Big tech companies, such as Meta and Microsoft, promote virtual reality as the future of remote meetings, highlighting benefits for engagement, interactions, and creativity. However, it remains crucial to verify whether users perceive the technological superiority of VR as leading to improved outcomes. Uncertainty Avoidance (UA) UA is one of the most important Hofstede dimensions influencing perceptions toward information and communication technologies, to which countries with low UA (vs. high UA) levels are more likely to be receptive. Research Question How do videoconferencing and virtual reality for collaborative meetings compare in terms of perceived engagement, and what elements influence this comparison?
- Where Users Go, Testing Should FollowPublication . Somova, Anna; NOVA Information Management School (NOVA IMS)Software Quality Assurance (SQA) teams often lack visibility into how real users interact with applications. As a result, testing efforts may focus on less important areas while critical or emerging issues remain unnoticed. This study analyzes real-world usage data (page views, engagement time, devices) from Google Analytics to understand which parts of the system matter most.
- AI Self-Efficacy, Trust, and Human Reliance on AI-Generated AdvicePublication . Carreiro, André; NOVA Information Management School (NOVA IMS)Artificial Intelligence (AI) systems increasingly influence human judgment and decision-making across professional and everyday contexts. Recommendation engines, decision-support systems, and especially large language models have intensified human–AI interaction, making it essential to understand how individuals perceive their own ability to work with AI and how this perception shapes downstream behaviors such as trust, advice-taking, and reliance. Research in technology acceptance and digital literacy suggests that self-efficacy influences technology use, confidence, and adaptation; however, its specific role in AI-supported decision-making remains conceptually fragmented. This review synthesizes evidence aiming to clarify how these constructs are connected, identifying emerging directions for future research on human–AI decision dynamics.
- Human or AIPublication . de Almeida Diogo, Diogo; NOVA Information Management School (NOVA IMS)Marketers have long created advertisements using persuasion, narrative techniques, artistic expression, and emotional resonance. But what happens when brands begin using Artificial Intelligence to develop these same messages? Generative AI is already used by 42% of marketing teams (Singla et al., 2025), with 80% of digital advertisers employing it to produce content (Beis, 2025). As adoption grows, so does the tension between human creativity and machine intelligence, fueling debate about how consumers interpret AI-generated advertising. While prior research has examined ads where AI authorship is explicitly disclosed (Wu et al., 2025), no studies have explored how consumers respond when AI is used to generate advertisement copy without disclosure and if there is any influence based on the experience the user already has with the technology. This raises important questions about how perceived authorship influences instrumental variables linked to purchase intention, such as relevance and credibility. Understanding these dynamics is crucial for advertisers seeking to integrate AI tools without compromising message effectiveness or consumer trust.