Zhao, Xinyi; E.Derrick, Gemma; Sugimoto, Cassidy R.; Larivière, Vincent
Funded by Max-Planck-Institut für Bildungsforschung
The intersection of doctoral training and parenthood poses unique challenges for early-career researchers, with lasting consequences for gender equality in academic careers. Drawing on a global survey of 8,097 academic parents, we reconstruct life-course trajectories of academic parents to investigate gender differences in the timing and sequencing of PhD completion and parenthood, and their implications for long-term career development. We identify five distinct trajectories. Women were more likely to complete the PhD before age 30 and delay parenthood after 35, whereas men tended to become parents during doctoral studies and often had three or more children by age 40. Early parenthood was associated with the largest gender disparities in scientific citations, favoring men, while these disparities diminished among those who became parents after age 35. Across all trajectories, men were consistently more likely to secure and remain in academic positions. These findings underscore the structural challenges faced by early-career mothers and highlight the importance of institutional policies, such as parental leave, childcare provision, and flexible doctoral and tenure timelines, to better support the reconciliation of parenting and academic careers.
Salles Filho, Sérgio; Pacheco, Carlos Américo; De Negri, Fernanda; Vonortas, Nicholas S.; Dias, Rafael De Brito
This paper situates Brazilian science, technology and innovation (STI) policy within the broader international literature and provides a historical overview of key policy phases in Brazil. Therefore, we present an initial section that provides an overview of concepts and approaches proposed over time to analyze the role of STI in national development, with an emphasis on less developed countries. Whenever possible, connections are made to the historical phases presented in the subsequent sections of the article. The period described and analyzed spans from the initial institutionalization of STI policy in the 1940s to the early 2020s. The main policies and their rationales are presented across four major periods, two of which are subdivided into two sub-periods. This work demonstrates how STI policies reflected different moments of the country’s politics and its broader development policies, especially economic ones. The country has developed a complex STI system, well-established on several fronts, particularly in capacity building, scientific research and the creation of a robust institutional framework. It has struggled tirelessly to develop other areas, primarily those connected to the systematic application of knowledge generated by scientific and technological research to produce goods and services, thereby benefiting society. The text concludes by highlighting the challenges the country has faced and those it still confronts to make its STI system more responsive to the country's needs.
Academic discussions on Twitter have increased over the past decade. This study analyzes ca. 1.3 million scholarly conversations on Twitter, examining their temporal evolution, topical distribution, and associated publications. The results show a steady growth in the number of scholarly conversations, accompanied by rising proportions of longer and multi‐topic conversations. The visibility of different disciplines and topics varies significantly, with popular themes often closely related to societal events. By comparing topic co‐occurrence networks in Twitter conversations with co‐citation networks in scholarly literature, the study reveals both commonalities and differences in topic structures across academic and non‐academic communication contexts. Moreover, publications that appear in multiple conversations are associated with higher citation counts, suggesting a potential link between conversational engagement and scholarly impact. These findings highlight that the feature of conversations on social media has value not only for refining indicators of scholarly attention and influence beyond simple mention counts, but also to capture more broadly how research is disseminated online.
Vanz, Samile Andréa de Souza; Grácio, Maria Cláudia Cabrini; Docampo, Domingo; Chinchilla-Rodríguez, Zaida; dos Santos, Silvio Telles; OLIVEIRA, SANDRA C.
Funded by CNPq, CAPES, FAPERGS, Xunta de Galicia
This study investigates the perceptions of Brazilian researchers in agronomy regarding the order of authorship and the role of the corresponding author in scientific publications utilizing a survey of 380 responses. Key findings reveal that most researchers see the first author as the primary executor of the research, and the last author as the leader. The study also highlights a significant association between authorship order, research credibility, and citation impact, with differing views based on the type of institutional affiliation. In addition, the survey shows a preference for the corresponding author to be either the first or the last author, emphasizing their role in communication with journals. The results suggest that while the authorship order is crucial for recognizing contributions, the corresponding author’s role is primarily seen as a formality. The study calls for more precise guidelines on authorship practices and further research into authorship dynamics in different scientific fields.
Neubert, Patrícia da Silva; do Canto, Fábio Lorensi; Appel, André Luiz; Segundo, Washington
Introdução: Objetivou analisar o pagamento de taxas de processamento dos artigos em Acesso Aberto publicados por autores vinculados a instituições brasileiras. Método: Tomou como referência dados de artigos extraídos da base OpenAlex, publicados no período de 2018 a 2023, por meio de um script desenvolvido em linguagem Python. As estimativas de custo de APC foram baseadas em campo específico da base, com valores expressos em dólares estadunidenses (apc paid_usd). Resultados: Verificou-se um aumento de 70% no período e aumento médio anual de 11% nos valores investidos em pagamento de taxas. Os preços médios das taxas passaram de 1.085 dólares estadunidenses em 2018 para 1.264 dólares em 2023. Os resultados apontam ainda para a concentração dos pagamentos de taxas a editoras como MDPI, Elsevier, Springer Nature, Frontiers Media e Wiley, e para títulos de periódicos dessas mesmas editoras. Conclusão: Os resultados possibilitaram observar crescimento tanto no quantitativo de artigos publicados via pagamento de APC, com a consequente elevação dos valores investidos para o custeio da publicação desses artigos. Refletem a concentração dos recursos pagos, tanto em termos de títulos quanto em termos de grupos editoriais, dados que reforçam descobertas de estudos prévios com foco no Brasil ou em outros contextos. Reforçam, ainda, a prevalência de pagamentos de APC para periódicos híbridos, em contraposição à expectativa de crescimento da modalidade dourada, apregoada pela implementação dos chamados acordos transformativos.
Vicentin, Damaris Chieregato; de Moraes, Gustavo Hermínio Salati Marcondes; Fischer, Bruno Brandão; Meissner, Dirk; Yuan, Joseph Zhou; Miao, Zhongzhen
Funded by CNPq, FAPESP
Purpose This study aims to predict respondent-reported continuity of international scientific collaboration within the BRICS through a supervised binary classification approach. It examines whether respondents reported that collaborations continued in the form of joint projects and co-authored publications, using survey-based variables related to collaboration climate, partner attributes, perceived benefits, barriers and impacts. Design/methodology/approach The analysis is based on survey data comprising 313 valid responses for collaborative projects and 304 valid responses for publications involving researchers engaged in cross-border cooperation within the BRICS. The machine-learning input variables were derived from the survey responses; publicly accessible bibliometric and institutional sources were used only to identify eligible respondents. Seventeen variables were considered, including 15 predictors and two binary outcomes (Projects and Publications). Eight supervised machine learning classifiers were applied: Logistic Regression, support vector machine, k-nearest neighbors, decision tree, random forest, gradient boosting, histogram-based gradient boosting and naïve Bayes. Model performance was evaluated using stratified cross-validation and ShuffleSplit resampling, considering accuracy, F1-score, balanced accuracy and AUC metrics. Findings The results indicate that trust culture is the most consistent predictor of respondent-reported continuity across both outcomes, while resource availability and agenda alignment are particularly important in predicting respondent-reported project continuity. Originality/value This study offers an interpretable, respondent-level classification of reported collaboration continuity in BRICS-internal scientific partnerships. Its originality lies in treating the reported continuity of collaboration as a knowledge management -relevant outcome, distinguishing project-based from publication-based continuity and showing which established collaboration conditions remain informative across these two forms of sustained knowledge relationships.
Rodrigues, Wellington Barbosa; dos Santos, Thamyres Vieira; Mugnaini, Rogério
Funded by CNPq, CAPES
Objetivo. Este estudo buscou analisar a recuperação da produção científica brasileira em ambientes informacionais internacionais e de acesso aberto, a partir da produção científica registrada nos Currículos Lattes de bolsistas de Produtividade em Pesquisa (PQ) do CNPq. Por meio dos identificadores persistentes DOI e ORCID, efetivou-se a busca nas fontes OpenAlex e ORCID. Método. Estudo exploratório da produção científica de 16.203 currículos de bolsistas PQ com ORCID registrado, e cerca de 1,1 milhão de registros de produção com DOI atribuído, do período de 2015-2024. Comparou o percentual de DOIs nas sobreposições entre as fontes Lattes, OpenAlex e ORCID, e também o grau de complementaridade entre as fontes. Considerou as seguintes variáveis secundárias: grande área, área específica da bolsa PQ e localização geográfica (Estado e Região) da afiliação institucional do pesquisador. Resultados. A totalidade da produção mostrou que cerca de 79% dos DOIs recuperados das três fontes estão representados na Plataforma Lattes, enquanto a OpenAlex complementa com 18,8% e a ORCID com 5,5%. Por outro lado, o maior percentual de DOIs encontra-se na intersecção entre o Currículo Lattes e a OpenAlex (37,9%), com destaque para as Ciências Agrárias, Ciências Biológicas e Ciências Exatas e da Terra, e na intersecção entre as três fontes (29,3%). As Ciências Humanas, Ciências Sociais Aplicadas e Linguística, Letras e Artes destacam-se com os maiores percentuais advindos da OpenAlex, enquanto as Ciências de Saúde se destacam pelo percentual de DOIs exclusivos no Lattes (9,5%) e ORCID (2,8%). Entre as regiões, o Sudeste apresenta o maior percentual de DOIs provenientes da ORCID (2,1%) e na sobreposição Lattes e OpenAlex (40,1%). Por outro lado, o Centro-Oeste destaca-se com os maiores percentuais entre as fontes, sendo a região cujos DOIs presentes nos currículos foram mais complementados pela OpenAlex, o que pode significar que o identificador não tem sido registrado nos currículos. Ao comparar as áreas específicas e os estados, observou-se que, em ambos os casos, existe maior heterogeneidade no percentual de DOIs: na OpenAlex exclusivamente; na intersecção entre o Lattes e a OpenAlex; e na intersecção das três fontes. Dessa forma, observou-se que as áreas de Linguística, Letras e Artes, bem como de Ciências Agrárias, são as que apresentam maior homogeneidade entre as suas subáreas, ao passo que nas Ciências Sociais Aplicadas se observa maior heterogeneidade. Entre os Estados, a maior heterogeneidade foi observada na região Norte, enquanto a região Sul é a mais homogênea, seguida da região Sudeste. Considerações. As diferenças em relação à cobertura das fontes, sugerem que as particularidades da comunicação científica, considerando o ecossistema editorial/informacional, divergem mais entre áreas do que entre regiões, o que concerne às características de publicação dos resultados de pesquisa. A sobreposição das produções entre as fontes evidencia o potencial de univocidade dos PIDs, possibilitando que pesquisas como esta sejam realizadas de maneira objetiva, sem que as variações de metadados textuais interfiram na qualidade dos resultados.
dos Santos, Fernanda Bochi; Morandin, Janaina Laís Pacheco Lara; Boaretto, Rodrigo Marcelli; Mattos, Dirceu; Grácio, Maria Cláudia Cabrini
No contexto da Organização do Conhecimento, este estudo analisa de forma diacrônica os domínios temáticos na produção científica sobre Citricultura no estado de São Paulo (período 1996-2025), indexada na base Scopus. A busca resultou em 3.341 documentos utilizando-se os filtros para a área Agricultural and Biological Sciences, e, em seguida, as instituições e universidades do estado de São Paulo vinculadas às publicações. As redes mostram a associação entre as palavras-chave registradas pelos autores, sendo separadas em períodos de 10 anos e geradas no VOSviewer. Os resultados mostram que ao longo de três décadas, as redes de coocorrência de termos mostram a predominância dos domínios Fitopatológico e controle biológico. Observa-se também uma transição de domínios, pois na primeira década estão presentes domínios fitossanitários e de fertilidade do solo, enquanto o segundo período indica o domínio relativo ao manejo do solo e o terceiro período indica domínios voltados à nutrição e composição química.
St-Onge, Sylvain; Forgues, Éric; Volkanova, Victoria; Larivière, Vincent
L’anglicisation des activités de diffusion de la recherche est un fait attesté depuis plusieurs années, tant à l’échelle internationale que canadienne, et ce, dans des proportions variables, dans tous les domaines scientifiques. Cet article présente les résultats d’une étude qui a cherché à comprendre les effets qu’entraîne l’anglicisation de la recherche sur les revues qui publient en français au Canada en analysant leur transition vers le libre accès, leurs contraintes financières ainsi que les perceptions de leurs responsables. À partir d’une recension de 245 revues qui publient en français, ainsi que les résultats de 82 de ces revues ayant participé à notre sondage, notre analyse met en lumière une certaine contradiction : bien que les revues qui publient en français se déclarent moins optimistes quant à l’avenir de la publication en français, celles-ci démontrent une résilience importante dans un environnement scientifique largement dominé par l’anglais. Cette étude contribue à nuancer la compréhension des diverses conditions de production et de diffusion des savoirs scientifiques en français au Canada, et avance une réflexion sur les mesures à prendre pour soutenir de façon durable l’écosystème francophone de la recherche.
A transformação institucional para a promoção da equidade de gênero na carreira acadêmica é um tema de grande repercussão internacional, porém ainda pouco estudado no Brasil. Esta pesquisa analisou as estruturas e estratégias institucionais adotadas em busca de equidade em quatro universidades públicas brasileiras, por meio da realização de entrevistas com gestores e ativistas, além de análise de documentos e informações dessas universidades. Os resultados destacam a importância de fortalecer a cultura institucional para estruturar iniciativas nas universidades e estabelecer um consenso entre os acadêmicos. A participação democrática e atuação conjunta com órgãos reguladores, financiadores e outras instituições são vistas como elementos importantes para gerar essa transformação. Temas como maternidade, parentalidade, cuidado, assédio e violência de gênero, e desigualdades na trajetória profissional se mostram centrais para promover o desenvolvimento. Além disso, o estudo evidencia os desafios enfrentados pelos entrevistados, como visões conservadoras e meritocráticas, que sustentam discursos de resistência encoberta no meio acadêmico.
Ferreira, Márcia R.; Costas, Rodrigo; Servedio, Vito D. P.; Thurner, Stefan
Research institutions are crucial in driving intellectual, social, and technological progress. Their ability to innovate depends mainly on their ability to attract, retain, and nurture scientific talent, ultimately making it available to other organizations, industries, or the economy. As researchers change institutions during their careers, their research topics also shift. The extent and mechanisms by which research institutions manage their internal portfolio of scientific topics through the attraction and deployment of researchers are far from well understood. We examine 25 million publication histories of 9.2 million scientists extracted from a large-scale bibliographic database covering thousands of research institutions worldwide to understand how the topics of mobile scientists align with those present in-house. We find a correlation between top-ranked institutions and greater topic alignment, i.e., the degree to which topics of incoming academics match those of their colleagues at the institution. We uncover a similarly high level of alignment among scientists leaving top-ranked institutions. The alignment of research topics in research institutions is more pronounced in engineering, life, health, earth, and physical sciences than in mathematics, computer science, social sciences, and the humanities. We show that institutions have generally become more closely aligned in their overall topic profile over the past two decades. We interpret these results in terms of the levels of proactive management of the composition of the scientific workforce and internal collaboration strategies at the institutional level.
Bascur, Juan Pablo; Costas, Rodrigo; Verberne, Suzan
Purpose Traditional science maps cluster documents into topics but are inherently biased toward clustering certain topics over others. This study investigates the extent to which topic bias can be influenced through the selection of data sources used to construct document networks. Design/methodology/approach We evaluate the clustering effectiveness of several topic categories using document networks constructed from two traditional science mapping sources (citations and text similarity) and six non-traditional data sources (policy documents, patent families, document authors, Facebook users, Twitter users, and Twitter conversations). Each source is evaluated both independently and in combination with a text similarity network. Findings Different data sources favor different kinds of topics. Facebook users favor health issues, patent families favor biotechnology topics, policy documents favor government and social issues, Twitter conversations favor food topics, Twitter users favor nursing topics, and document authors favor geographical entities. These findings demonstrate that topic bias can be systematically influenced through data source selection. Research limitations The study focuses on biomedical publications and is limited to the topic categories and data sources examined. Additional domains, data sources, and source combination methods may exhibit different patterns of topic bias. Practical implications The ability to influence topic bias through data source selection opens up the possibility of creating science maps tailored to different information needs. The reported source-specific biases can support the design of science maps optimized for particular users, tasks, or domains. Originality/value This study provides one of the first large-scale investigations of how alternative data sources affect topic emergence in science maps. It introduces an expanded methodology for evaluating topic-level clustering effectiveness and systematically characterizes the topical biases associated with different data sources, providing a foundation for future science map customization.
Pradier, Carolina; Céspedes, Lucía; van Bellen, Simon; Alperín, Juan Pablo; Larivière, Vincent
The dominance of English-language journals marginalizes national and local scholarly publications. Focusing on Canada’s bilingual (English and French), community‑oriented and Open Access‑rich journal ecosystem, this study uses comprehensive data to ask who relies on Canadian journals, how language and research focus affect reach, and what that reveals about balancing local relevance with global visibility. Drawing on two major bibliometric databases (OpenAlex and Dimensions), we show that Canadian journals play a key role as venues for the dissemination of locally relevant research while also contributing to the global infrastructure for scholarly communication. Most articles published in Canadian journals are authored by researchers affiliated with foreign institutions, and most research authored by Canadians is published in journals based outside Canada. We find that Canadian authors are most likely to publish their work in national journals when they are in decision-making roles, when the language of publication is French, or when the topics are locally relevant. Our findings also challenge the notion that only the Social Sciences and Humanities are locally bound: for the Canadian case, Life and earth sciences and Biomedical and health sciences were also found to be linguistically and geographically grounded. Finally, while researchers affiliated with government institutions are the most likely to publish in Canadian journals and to engage in research that has a Canadian object of study, researchers affiliated with French-speaking Québec-based universities stand out as the largest contributors to the Canadian journal ecosystem and account for the highest volume of French-language publications.
Sott, Michele Kremer; Mikhaĭlov, A. A.; Ruffoni, Janaína; Tello‐Gamarra, Jorge; Fischer, Bruno Brandão
Numerous studies have examined innovative partnerships between universities and industrial companies; however, universities are typically treated as a monolithic unit of analysis. Shifting the focus to individual academic research groups (RGs) provides a better understanding of the complexity and heterogeneity of such interactions. This article aims to analyze the interactions between Brazilian industrial firms and university research groups to understand how specific characteristics of these micro-level units influence firms' innovative outcomes. The research utilizes data from the Brazilian national census of research groups (DGP-CNPq) combined with a survey of industrial firms that collaborated with these groups. The study develops five econometric models to measure the effects of firm and research group characteristics on the dimensions of innovation performance, such as technological and business capabilities, and product and process innovation. The results indicate that research group characteristics do not directly affect a firm’s innovation performance. Instead, the presence of a robust knowledge infrastructure and involvement in R&D departments are the primary determinants of enhanced technological and business capabilities in collaborative agreements. Furthermore, while applied science is a significant predictor for product innovation, process innovation is primarily driven by the firm's own technological intensity and the university’s knowledge infrastructure. This study is among the first to provide a granular, micro-level analysis of how research group characteristics — rather than university-wide traits — shape the tangible benefits firms derive from collaboration, specifically within the context of an emerging economy.
Since the establishment of the Science Citation Index in the 1960s, scientific evaluation systems have favored metrics like the impact factor (IF), creating a hierarchy that privileges “mainstream” journals while marginalizing local publications. This model has driven Latin American researchers to publish in international journals, often in English and with high article processing charges (APCs), to gain academic recognition and funding. However, this dynamic has undervalued regional journals, despite initiatives like SciELO, RedALyC, and Latindex demonstrating high standards of quality, open access, and increasing internationalization. In response, an interdisciplinary team proposed the creation of a local scientific journal at the Faculty of Biochemical and Pharmaceutical Sciences of the National University of Rosario (FBIOyF, by its Spanish acronym), aiming to engage globally without neglecting local values and criteria. To assess this initiative, we conducted a survey among faculty researchers. The results reveal significant interest in a publication that promotes the dissemination of locally generated knowledge, facilitates access for non-English-speaking communities, and fosters interdisciplinary collaborations, making science more equitable and more sensitive to social context.
In Brazil, health policy formulation, particularly through Clinical Protocols and Therapeutic Guidelines (PCDTs), is significantly influenced by scientific evidence. The National Commission for the Incorporation of Technologies into the Unified Health System (CONITEC) approves these PCDTs to standardize healthcare practices, thereby exemplifying the nexus of scientific research and policy. This study analyzes the scientific literature referenced in the PCDTs approved by CONITEC, exploring the flow of knowledge from global scientific research to Brazil’s health policy. Our approach involved a data pipeline for collecting, preprocessing, and analyzing information from scientific publications cited in all CONITEC’s PCDT reports published until 2023. The process encompasses web scraping, pattern recognition, and bibliometric analysis. The study identified references predominantly from the United States and the United Kingdom, with notable contributions from Brazilian sources. Cited research is almost entirely written in English and published in high-impact factor English-language journals. These findings document the global influence on Brazil’s health policies, with a substantial portion of the cited scientific evidence originating from international sources.
Derrick, Gemma; Hauseux, Marlene; Sheridan, Mary; Chen, Peiying; Larivière, Vincent; van Leeuwen, Thed N.; Sugimoto, Cassidy R.
The event of having a child for an academic is associated with lower research productivity for women, even when the parenting burden is shared by both male and female parents. Universities and research organizations commonly employ “family‐friendly” policies to simultaneously ease work expectations and provide flexibility in work patterns, performance, and participation. Recent trends of fathers taking more responsibility for parenting engagement than past generations have challenged universities to adopt a greater diversity of family‐friendly policy approaches to ensure maximum workforce participation. However, such policies have done little to ameliorate that increased harm on academic careers, especially women's. Using a global survey of 10,445 academic parents, this study analyzes 5903 free‐text, qualitative responses to explore individualized rationales of how a parenting “unit” functions at the household level. By examining the gaps and silences in the testimonies of parents, this study concentrates on the gendered nature of parental rationales and the power imbalances and assumptions made around a partner's conceptualization of choice in parenting. The findings show that differing notions of parental workplace flexibility are used to reinforce gendered concepts of care at the household level. This undermines policy goals of helping parents in the workplace, especially if the policies are used to nudge mothers to disengage from work.
Maruyama, William Takahiro; Digiampietri, Luciano A.
The increasing use of digital data in electoral prediction has motivated a growing body of computational research, yet the field remains methodologically diverse and lacks consolidated comparative frameworks. This article presents a systematic review of computational approaches for electoral outcome prediction using digital data between 2020 and 2025. Following rigorous systematic methodology, searches were conducted across three scientific databases, resulting in 80 primary studies analyzed after applying explicit quality criteria. The review proposes a taxonomy classifying studies by data integration and predictive complexity, enabling systematic identification of methodological patterns. Results reveal geographic concentration in few countries, with Twitter as the dominant platform and sentiment analysis as the most frequent technique. Vote percentage prediction and winner identification represent the primary objectives, evaluated mainly through regression and classification metrics. The field demonstrates numerical expansion with modest geographic diversification, yet persistent challenges remain regarding sample representativeness, cross-context generalization, and absence of standardized validation protocols. Findings indicate the need for broader geographic coverage, reduced platform dependency, and establishment of uniform evaluation criteria to advance methodological maturity in computational electoral prediction.
Köhler, André Fontan; Segatto, Camila Alves; Digiampietri, Luciano A.
Trabalha-se com um estudo bibliométrico do tipo avaliativo. Seu corpus consiste em 24 periódicos brasileiros de turismo; o objeto de estudo são os artigos neles publicados, em 2020-2024, e suas citações. Há dois objetivos principais, a saber: i) avaliar a trajetória das citações; ii) avaliar e ordenar esses periódicos, segundo seu impacto (citações). Os materiais e métodos consistem na coleta, revisão e desambiguação manuais dos artigos e citações, estatística descritiva e cálculo dos índices H e G. Os resultados são comparados aos de 1990-2018, por meio de literatura. A Revista Brasileira de Pesquisa em Turismo ocupa a primeira posição para todas as métricas e rankings, via de regra com resultados muito acima do periódico seguinte. A Revista Rosa dos Ventos destaca-se nas métricas e rankings baseados no conjunto de artigos mais citados para cada periódico, aproximando-se, neles, dos resultados da Revista Brasileira de Pesquisa em Turismo. Complementam o primeiro quartil dos periódicos mais citados a Anais Brasileiros de Estudos Turísticos, PODIUM Sport, Leisure and Tourism Review, Turismo: Visão e Ação e Revista Acadêmica Observatório de Inovação do Turismo. Houve profundas mudanças nos rankings de impacto e nos índices H e G, em comparação com os resultados do período 1990-2018.
Veríscimo, Erico de Souza; Bernardes Júnior, João Luiz; Digiampietri, Luciano A.
User experience (UX) is fundamental for the acceptance and use of information systems. Although there are well-known and widely used UX evaluation techniques for traditional interfaces, a literature review revealed several gaps regarding UX evaluation in non-immersive 3D interaction. One significant gap is the predominant use of pragmatic criteria in assessments, while another is the lack of an approach that evaluates hedonic aspects using facial emotion recognition. This work proposes an approach for automatically evaluating user experience in non-immersive three-dimensional environments, focusing on its hedonic aspects based on facial emotion recognition. An experimental protocol was developed and approved by the Ethics Committee. The experiment was conducted with 52 participants. Throughout the testing period (before, during, and after the interaction), participants' faces were recorded using a low-cost camera. The experiment involved participants playing a game and answering questionnaires, including categorization and mood profile instruments, as well as the UEQ-S and the PLEX Framework. The Face-api.js library was used for facial emotion recognition. The hypothesis that automatic facial emotion recognition can support user experience evaluation was confirmed. This method enabled the estimation of UEQ-S and PLEX questionnaire responses with an average error of approximately ±1 point using only emotion extraction through an artificial intelligence model. Given that UX evaluation is crucial for the acceptance of new software or functionality, this work contributes to improving system quality and acceptance.
