Entradas recentes

• Item type: Item , Access status: Acesso restrito ,

  Decoding societal acceptance of innovative air mobility (IAM) via virtual reality simulations.

  (2026) Samoili, S.; Eleftherakis, P.-E.; Lopes, M.; Almeida, H.; Mcleod, J.; Anagnostopoulos, G.; Iliakis, K.; Xydis, S.; Kalakou, S.; Harris, Don; Li, Wen-Chin; Streitz, Norbert A.; Konomi, Shin'ichi

  Expandir

  The study investigates societal acceptance of Innovative Air Mobility (IAM) operations, from a perspective of visual and audiovisual pollution in urban and rural environments. Participants’ perception of drone and eVTOL operations was examined through Virtual Reality (VR) simulations across diverse scenarios, including various drone types, flight paths, and the presence or not of audio input, to measure the impact on visual/audiovisual pollution. Two methodologies are developed to quantify drone acceptance: NLP-based and HCI-based Acceptance Analyses. The NLP approach employed sentence-level sentiment analysis on verbal input of the participants during simulations, to uncover underlying factors affecting drone operation acceptance and implied acceptance beyond self-stated numerical ratings. The HCI method analysed participants’ interactions by quantifying non-tolerated audiovisual/visual pollution periods through “clicks” during the VR simulations. Results showed drone type and environment influence public acceptance. Sensing drones received the highest acceptance, while lower societal acceptance was indicated for passenger drones through lower sentiment scores. English speakers demonstrated higher readiness to approve drone operations, potentially due to more frequent drone exposure or linguistic differences, with the reasons requiring further investigation. The strong performance of the XGBoost model in predicting non-tolerated audiovisual/visual pollution validates the indirect predictive approach using HCI-collected biometric data. These findings provide a comprehensive understanding of human perception and acceptance levels in human-UAV interactions, surpassing self-reported ratings. The methods provide substantial guidance to UAV stakeholders, urban planners, and policymakers to design IAM systems accounting for public comfort and societal expectations.

  Expandir

  A carregar...
• Item type: Item , Access status: Acesso aberto ,

  INESC-ID @ eRisk 2025: Exploring fine-tuned, similarity-based, and prompt-based approaches to depression symptom identification

  (2025) Nunes, D. A. P.; Ribeiro, E.; Faggioli, Guglielmo; Ferro, Nicola; Rosso, Paolo; Spina, Damiano

  Expandir

  In this work, we describe our team’s approach to eRisk’s 2025 Task 1: Search for Symptoms of Depression. Given a set of sentences and the Beck’s Depression Inventory - II (BDI) questionnaire, participants were tasked with submitting up to 1, 000 sentences per depression symptom in the BDI, sorted by relevance. Participant submissions were evaluated according to standard Information Retrieval (IR) metrics, including Average Precision (AP) and R-Precision (R-PREC). The provided training data, however, consisted of sentences labeled as to whether a given sentence was relevant or not w.r.t. one of BDI’s symptoms. Due to this labeling limitation, we framed our development as a binary classification task for each BDI symptom, and evaluated accordingly. To that end, we split the available labeled data into training and validation sets, and explored foundation model fine-tuning, sentence similarity, Large Language Model (LLM) prompting, and ensemble techniques. The validation results revealed that fine-tuning foundation models yielded the best performance, particularly when enhanced with synthetic data to mitigate class imbalance. We also observed that the optimal approach varied by symptom. Based on these insights, we devised five independent test runs, two of which used ensemble methods. These runs achieved the highest scores in the official IR evaluation, outperforming submissions from 16 other teams.

  Expandir

  A carregar...
• Item type: Item , Access status: Acesso aberto ,

  Escolas, relações internacionais e psicopatologia – supremacia branca, barbárie e autodesenvolvimento: Uma perspectiva fenomenológica

  (2025) Lacerda-Nobre, Â.; Gameiro, A.; Duarte, R.; Cunha-Lima, M.; Delgado, Catarina; Pinto, Mariana Oliveira; Justino, Marta; Piteira, Martinha; Rocha, Natália; Anunciação, Pedro; Lourenço,Rodrigo; Lima, Sónia

  Expandir

  As práticas pedagógicas transmitem uma ampla gama de reflexões e trabalhos teóricos sobre os desempenhos reais das pessoas envolvidas no binómio ensino-aprendizagem. Seja qual for o domínio científico ou área de especialização, e independentemente da faixa etária e posição na educação e formação profissional, o mesmo princípio se aplica, ou seja, ao se referir o termo “pedagogias práticas” há uma sinalização da importância de reconhecer efetivamente o contexto aplicado e da vida real. Dito isto, há certas áreas que tendem a capturar perspetivas privilegiadas, que permitem compreender a mentalidade da sociedade ou época em geral, o zeitgeist ou espírito do tempo. Essas duas áreas são Relações Internacionais e Psicopatologia. Ambas as áreas científicas transmitem influências e contra-influências multidisciplinares. Além disso, ao usar a lente analítica e crítica da pedagogia prática, é possível abordar realidades sensíveis, delicadas e complexas relacionadas com preocupações sociais, culturais, económicas, ecológicas e políticas.

  Expandir

  A carregar...