This study investigates ethical documentation for open-source AI models through a combination of a Multivocal Literature Review (MLR) with a large-scale empirical analysis of real-world Model Cards. We aim to address the gap in how ethical considerations are documented and implemented in both research and practice. Publications from major scholarly databases and arXiv (N = 36) were systematically retrieved, screened, and analysed. In parallel, metadata and documentation from the most-downloaded models on Hugging Face Hub were processed, yielding over 60,000 valid Model Cards after filtering. The literature review shows that Model Cards are the predominant artifact in open publication settings, but ethical coverage is uneven: transparency is most frequently addressed, while societal and environmental aspects are rarely discussed. Notably, bias is often referenced generically, with little methodological consideration. Finally, the Model Card analysis reveals three issues that indicate an implementation gap: (i) only 16.8% include explicit references to ethics (e.g., bias, limitations, risks), (ii) these sections are typically brief, and (iii) their relative prevalence declines over time despite absolute growth in model releases. These findings underscore the importance of standardized documentation, clearer guidelines, and machine-readable, verifiable ethical properties to support responsible model development and reuse.

This study proposes an open-environment, multi-label human risk classification framework, capable of identifying possible risks to which individuals appearing on input video data are exposed. The framework consists of an ensemble of models covering object detection, action recognition, context understanding and text classification tasks. Each model is evaluated separately in the context of home environments, with the overall framework performing well in each evaluation after fine tuning. The models were evaluated using a combination of several datasets, including Charades, ETRI-Activity3D, and custom video question answering and risk datasets. This study exploits the ability of large language models to interpret semantic visual features combined with textual input in order to understand the context in which the person is placed. The framework’s ability to output multiple risks and its cross-domain capabilities make it a powerful tool that can enhance current risk management systems in a variety of scenarios, such as homes, construction sites and industry.

Early detection of cognitive disorders such as Alzheimer’s disease is critical for enabling timely clinical intervention and improving patient outcomes. In this work, we introduce CogniAlign, a multimodal architecture for Alzheimer’s detection that integrates audio and textual modalities, two non-intrusive sources of information that offer complementary insights into cognitive health. Unlike prior approaches that fuse modalities at a coarse level, CogniAlign leverages a word-level temporal alignment strategy that synchronizes audio embeddings with corresponding textual tokens based on transcription timestamps. This alignment supports the development of token-level fusion techniques, enabling more precise cross-modal interactions. To fully exploit this alignment, we propose a Gated Cross-Attention Fusion mechanism, where audio features attend over textual representations, guided by the superior unimodal performance of the text modality. In addition, we incorporate prosodic cues, specifically interword pauses, by inserting pause tokens into the text and generating audio embeddings for silent intervals, further enriching both streams. We evaluate CogniAlign on the ADReSSo dataset, where it achieves an accuracy of 87.35% over a Leave-One-Subject-Out setup and of 90.36% over a 5 fold Cross-Validation, outperforming existing state-of-the-art methods. A detailed ablation study confirms the advantages of our alignment strategy, attention-based fusion, and prosodic modeling. Finally, we perform a corpus analysis to assess the impact of the proposed prosodic features and apply Integrated Gradients to identify the most influential input segments used by the model in predicting cognitive health outcomes.

Emotions play a crucial role in our daily lives, influencing how we face challenges throughout the day and shaping our behavior, even when we are not consciously aware of them. Detecting emotional states in others relies on comprehending the collective impact of a variety of actions that emotions can produce, such as facial expressions, posture, tone of voice, or speech. To address this challenge, we propose a multimodal transformer-based model designed to recognize the emotional moods of individuals using video data, including audio and text transcriptions. Consequently, our model extracts the most relevant information from each modality to make a final prediction. Throughout this work, different fusion architectures have been integrated with transformer-based models to determine the optimal combination. This study examines the performance of individual modalities and their combinations using the CMU-MOSEI dataset. This dataset encompasses preprocessed video, audio, and text data. Our best model achieves a weighted accuracy of 85.59% on this dataset, surpassing previous works for this task.

Abstract Scientists face challenges when finding datasets related to their research problems due to the limitations of current dataset search engines. Existing tools for searching research datasets rely on publication content or metadata, do not considering the data contained in the publication in the form of tables. Moreover, scientists require more elaborate inputs and functionalities to retrieve different parts of an article, such as data presented in tables, based on their search purposes. Therefore, this paper proposes a novel approach to retrieve relevant tabular datasets from publications. The input of our system is a research problem stated as an abstract from a scientific paper, and the output is a set of relevant tables from publications that are related to the research problem. This approach aims to provide a better solution for scientists to find useful datasets that support them in addressing their research problems. To validate this approach, experiments were conducted using word embedding from different language models to calculate the semantic similarity between abstracts and tables. The results showed that contextual models significantly outperformed non-contextual models, especially when pre-trained with scientific data. Furthermore, the importance of context was found to be crucial for improving the results.

This paper proposes a multimodal deep learning architecture combining text and audio information to predict dementia, a disease which affects around 55 million people all over the world and makes them in some cases dependent people. The system was evaluated on the DementiaBank Pitt Corpus dataset, which includes audio recordings as well as their transcriptions for healthy people and people with dementia. Different models have been used and tested, including Convolutional Neural Networks (CNN) for audio classification, Transformers for text classification, and a combination of both in a multimodal ensemble. These models have been evaluated on a test set, obtaining the best results by using the text modality, achieving 90.36% accuracy on the task of detecting dementia. Additionally, an analysis of the corpus has been conducted for the sake of explainability, aiming to obtain more information about how the models generate their predictions and identify patterns in the data.

Abstract This paper presents a machine learning-based classifier for detecting points of interest through the combined use of images and text from social networks. This model exploits the transfer learning capabilities of the neural network architecture CLIP (Contrastive Language-Image Pre-Training) in multimodal environments using image and text. Different methodologies based on multimodal information are explored for the geolocation of the places detected. To this end, pre-trained neural network models are used for the classification of images and their associated texts. The result is a system that allows creating new synergies between images and texts in order to detect and geolocate trending places that has not been previously tagged by any other means, providing potentially relevant information for tasks such as cataloging specific types of places in a city for the tourism industry. The experiments carried out reveal that, in general, textual information is more accurate and relevant than visual cues in this multimodal setting.

Abstract This paper presents a new approach to retrieve and further integrate tabular datasets (collections of rows and columns) using union and join operations. In this work, both processes were carried out using a similarity measure based on contextual word embeddings, which allows finding semantically similar tables and overcome the recall problem of lexical approaches based on string similarity. This work is the first attempt to use contextual word embeddings in the whole pipeline of table search and integration, including for the first time their use in the join operation. A comprehensive analysis of their performance was carried out on both retrieving and integrating tabular datasets, comparing them with context-free models. Column headings and cell values were used as contextual information and their impact on each task was evaluated. The results revealed that contextual models significantly outperform context-free models and a traditional weighting schema in ad hoc table retrieval. In the data integration task, contextual models also improved the results on union operation compared to context-free approaches.

Public Sector Information (PSI) scenarios require tools that support retrieval of tabular open data beyond keyword-based search on metadata. This paper presents a novel interface for searching tabular open data, as well as a search engine that retrieves tabular data by considering table contents apart from metadata. Our search engine uses word embeddings to calculate the semantic similarity between tabular open data, providing a ranking of candidate tabular datasets to be integrated with an input query table according to the different intentions of the open data reuser (e.g. column or row extension as well as data completion). An initial set of experiments have been conducted, showing promising results in this task.

Post-truth is a term that describes a distorting phenomenon that aims to manipulate public opinion and behavior. One of its key engines is the spread of Fake News. Nowadays most news is rapidly disseminated in written language via digital media and social networks. Therefore, to detect fake news it is becoming increasingly necessary to apply Artificial Intelligence (AI) and, more specifically Natural Language Processing (NLP). This paper presents a review of the application of AI to the complex task of automatically detecting fake news. The review begins with a definition and classification of fake news. Considering the complexity of the fake news detection task, a divide-and-conquer methodology was applied to identify a series of subtasks to tackle the problem from a computational perspective. As a result, the following subtasks were identified: deception detection; stance detection; controversy and polarization; automated fact checking; clickbait detection; and, credibility scores. From each subtask, a PRISMA compliant systematic review of the main studies was undertaken, searching Google Scholar. The various approaches and technologies are surveyed, as well as the resources and competitions that have been involved in resolving the different subtasks. The review concludes with a roadmap for addressing the future challenges that have emerged from the analysis of the state of the art, providing a rich source of potential work for the research community going forward.

This paper presents the first large‐scale investigation of the users and uses of WorldCat.org , the world's largest bibliographic database and global union catalog. Using a mixed‐methods approach involving focus group interviews with 120 participants, an online survey with 2,918 responses, and an analysis of transaction logs of approximately 15 million sessions from WorldCat.org , the study provides a new understanding of the context for global union catalog use. We find that WorldCat.org is accessed by a diverse population, with the three primary user groups being librarians, students, and academics. Use of the system is found to fall within three broad types of work‐task (professional, academic, and leisure), and we also present an emergent taxonomy of search tasks that encompass known‐item, unknown‐item, and institutional information searches. Our results support the notion that union catalogs are primarily used for known‐item searches, although the volume of traffic to WorldCat.org means that unknown‐item searches nonetheless represent an estimated 250,000 sessions per month. Search engine referrals account for almost half of all traffic, but although WorldCat.org effectively connects users referred from institutional library catalogs to other libraries holding a sought item, users arriving from a search engine are less likely to connect to a library.

Wikipedia has become one of the most important sources of information available all over the world. However, the categorization of Wikipedia articles is not standardized and the searches are mainly performed on keywords rather than concepts. In this paper we present an application that builds a hierarchical structure to organize all Wikipedia entries, so that medical articles can be reached from general to particular, using the well known Medical Subject Headings (MeSH) thesaurus. Moreover, the language links between articles will allow using the directory created in different languages. The final system can be packed and ported to mobile devices as a standalone offline application.

This paper presents an application for medicinal plants prescription based on text classification techniques. The system receives as an input a free text describing the symptoms of a user, and retrieves a ranked list of medicinal plants related to those symptoms. In addition, a set of links to Wikipedia are also provided, enriching the information about every medicinal plant presented to the user. In order to improve the accessibility to the application, the input can be written in six different languages, adapting the results accordingly. The application interface can be accessed from different devices and platforms.