ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus
URI permanente para esta coleção:
Navegar
Percorrer ESTiG - Publicações em Proceedings Indexadas à WoS/Scopus por Domínios Científicos e Tecnológicos (FOS) "Ciências Sociais"
A mostrar 1 - 9 de 9
Resultados por página
Opções de ordenação
- Automating digital accessibility AI and machine learning for inclusive learning environmentsPublication . Costa, José Paulo; Coelho, Ana Sofia; Martins, Oliva M.D.Digital accessibility is essential for ensuring that students with disabilities have equal access to educational materials in higher education. Despite standards like the Web Content Accessibility Guidelines (WCAG) and PDF Universal Access (PDF/UA), many institutions still face challenges in providing accessible digital content. Existing tools can identify accessibility issues but often fail to automate the remediation process or offer personalised adjustments for individual learners. This paper presents an AI-driven framework designed to automate digital content detection, remediation, and personalisation to meet accessibility requirements. The proposed framework integrates AI and machine learning to enhance the accessibility of PDFs, HTML content, and multimedia resources, ensuring compliance with WCAG 2.1 and PDF/UA standards. The study demonstrates that the AI system detects accessibility issues with 92% accuracy and remediates 85% of identified problems. Additionally, the framework offers real-time personalised adjustments, improving user satisfaction for 94% of students with disabilities. The AI system also reduces the time and cost of ensuring accessibility, making it an efficient tool for educational institutions. The paper concludes with recommendations for further research to expand the framework’s capabilities and offers insights for developing inclusive education policies that leverage AI technology.
- Comparative analysis of machine learning models for customer segmentation in E-commerce: a data-driven approachPublication . Costa, José Paulo; Coelho, Ana Sofia; Martins, Oliva M.D.E-commerce growth has led to vast amounts of customer data, making effective customer segmentation crucial for personalized marketing and customer relationship management. This paper presents a comparative study of unsupervised clustering algorithms for segmenting e-commerce customers based on RFM (Recency, Frequency, Monetary) attributes and additional behavioural factors such as customer satisfaction and tenure. We evaluate multiple clustering techniques – including K-Means, hierarchical clustering, and DBSCAN – to identify which algorithm yields the most coherent and well-separated customer groups. Cluster validity is assessed using internal metrics, notably the silhouette coefficient and the Davies-Bouldin index, to determine the optimal number of clusters and the quality of results for each method. Experimental results on real e-commerce data show that the choice of clustering algorithm significantly impacts segment formation. K-Means clustering achieved the highest silhouette score and lowest Davies-Bouldin index, indicating the best overall performance in capturing distinct customer segments. A detailed profile analysis of the resulting clusters reveals interpretable segments (e.g., high-value loyal customers, at-risk customers, new customers) with apparent differences in purchasing behaviour, satisfaction levels, and customer tenure. These findings provide insights into the strengths of different clustering approaches for customer segmentation and offer practical guidance for e-commerce firms to enhance customer targeting and retention strategies.
- From likes to comments: tracking interaction trends on social networks to promote cultural eventsPublication . Ferreira, Jessica; Scalabrini, Elaine C.B.; Lopes, Isabel Maria; Pereira, João Paulo; Cardim, SofiaTourism drives the economy through job creation and infrastructure development, while the cultural component, such as gastronomy and historical heritage, enriches the visitor experience and reduces regional disparities. Municipalities use channels like Instagram to promote cultural events and strengthen local identity, reaching a diverse audience and encouraging community and visitor engagement. This study explores interaction trends in event posts on Bragança, Portuguese City Municipality’s Instagram from 2020 to 2023. The aim is to analyse the evolution of metrics such as likes, comments and views over the last four years. Using a quantitative approach, data was collected from Instagram posts using the APIFY platform, followed by an analysis using Python for statistical evaluation to identify correlations and patterns. The main results reveal significant variations in user engagement with different types of events and changes in follower behaviour over time. These findings offer valuable information for social media management and municipal event planning, emphasising the importance of adaptive strategies on digital platforms.
- Instagram’s role in driving outdoor tourismPublication . Ferreira, Jessica; Cardim, Sofia; Scalabrini, Elaine C.B.; Vaz, Roberto; Fernandes, Paula OdeteThe complexity of social media engagement, with multiple factors influencing this phenomenon, is increasingly present in corporate digital marketing. Some social networks allow the dynamic sharing of promotional content from businesses and tourist destinations through posting photographs, videos, and locations. Although visual quality and the use of hashtags are important strategies, contextual and emotional elements tend to have a more direct impact on user engagement. From this perspective, this study explores the suitability of activity counts extracted from a social media platform (Instagram) to know the visitor counts at selected outdoor attractions in the North Region of Portugal. Through a quantitative methodology, the analysis utilised data from posts with specific hashtags collected in 2024, totalling 5020 posts, 7433 comments, and 126,314 likes. Three hypotheses were tested: the influence of the visual content (images and videos), the themes of the posts (identified by hashtags), and the polarity of the comments on user engagement. The results showed that the visual content did not have a significant impact on the number of likes and comments. The analysis revealed no significant differences in engagement between different themes of the posts. Sentiment analysis showed significant differences in likes among positive, neutral, and negative comments, but not in the number of comments. Practical implications include the need for integrated, context-sensitive digital marketing strategies to maximise social media engagement. Future studies should explore seasonal variations, employ objective measures of content, and integrate both qualitative and quantitative methods for a deeper understanding.
- Integrating sustainability, balanced scorecard and accounting information systems: a case in the automotive components industryPublication . Leite, Joaquim; Carmo, Cecília M. R.; Anes, HelenaThe aim of this study was to understand how to use the Balanced Scorecard (BSC) to propose cause-effect relationships in a car component manufacturing company. The literature review brings together BSC and accounting information systems, particularizing details of sustainability. The case study in a company that produces components for the automotive industry proved to be an appropriate research method. Data was collected by analyzing documents and interviewing the company manager. Content analysis was used to process the data collected. The information was organized according to the financial and non-financial perspectives of the BSC. The results obtained, through a proposal for a specific strategy map for a company manufacturing components for the automotive industry in the four classic perspectives of the BSC, without a sustainability perspective treated separately, clarified cause-effect relationships arising from management decisions involving concerns about improving environmental sustainability.
- Non-governmental organizations and innovation in the fish productive chain: combining the lenses of the sustainability balanced scorecard and information systemsPublication . Leite, Joaquim; Carmo, Cecília M. R.; Almeida, DanilsaThe objective of this research is to understand how to use the theoretical lens of the Sustainability Balanced Scorecard (SBSC) and information systems to explain innovation in the fish productive chain. The research method was the case study of a single Non-Governmental Organization (NGO) in São Tomé and Príncipe. Evidence was collected from content analysis and a long interview with the president of the NGO’s board of directors. The results showed that each new international funding for the NGO depends on the satisfaction of the partners involved (volunteer donors and beneficiaries/users) in previous projects, which in turn depends on the investment in facilities and equipment. Sustainability and innovation, as NGO’s strategic objectives, can be explained in the four traditional perspectives of the BSC because it is important to interpret the financial and non-financial effects.
- Population dynamics and economic strategies for enhancing industrial heritage: a bibliometric overviewPublication . Scalabrini, Elaine C.B.; Alves, Francisco; Neto, Reginaldo; Garcia, Joaquín; Teixeira, Felipe; Vaz, Roberto; Teixeira, João Paulo; Fernandes, Paula OdeteThis paper presents a bibliometric analysis examining the relationship between population dynamics and economic strategies for valorising industrial heritage based on 260 articles published between 1990 and 2025. The study reveals an exponential increase in publications from 2019 onward, reflecting a growing interest in this subject. The journal Sustainability emerges as the predominant source of publication, underscoring the significance of sustainability within this field. China is identified as the leader in scientific output, followed by Italy and the United States. Key terms identified include “sustainability,” “cultural heritage,” and “heritage preservation,” emphasising the central themes in this area of research. While the bibliometric analysis offers thoughts about research trends, it does have limitations, including its focus solely on articles published in English and the need for more content analysis. Future research should address these gaps to enhance understanding of the intricate relationship between population dynamics, economic development, and the preservation of industrial heritage.
- Towards accessible, inclusive, and intergenerational tourism in outdoor recreation: a bibliometric analysisPublication . Cardim, Sofia; Scalabrini, Elaine C.B.; Ferreira, Jessica; Fernandes, Paula Odete; Vaz, RobertoThe increasing number of tourists interested in outdoor activities registered a growth during the past few years, creating pressure in the sector to offer them adjusted products and services to enhance the overall experience of families travelling together. In this scope, ensuring that all individuals can equally enjoy shared time and togetherness despite their age or impairments is urgent. This research aims to be a pioneer and provide a comprehensive overview of the scientific field concerning the intersection of outdoor tourism with intergenerational, accessible, and inclusive tourism. This paper analyses the literature from multiple perspectives by conducting a bibliometric analysis combined with data visualisation tools, organising the knowledge to investigate the scientific production evolution, the main topics that have been addressed, and trends and emerging themes that can contribute to extending this scientific area. The results show this is yet an embryonic field in tourism, with low expression of publications in conferences, being guided mainly by themes connected to outdoor activities and recreation in landscape and parks as tourism destinations, sports and physical activities, historic building and conservation, and climate change. The current challenges are also discussed, providing emerging issues that must be addressed in future research, mainly linked to information and communication technologies.
- Using websites to disclose information on human capital: an exploratory study in the portuguese banking sectorPublication . Carmo, Cecília M. R.; Leite, Joaquim; Lima, BeatrizThis study examines the use of websites by Portuguese banks to disclose information about their human capital. For this purpose, a manual content analysis was carried out, based on an analysis grid that allows to identify the elements that are disclosed. The results show that banks already use websites to disclose information on human capital, but at a low level. There are also topics related to human capital information that no bank discloses on its website.