Abstract
The goal of the Semantic Web is to allow the software agents around us and AIs to extract information from the Internet as easily as humans do. This semantic web is a network of connected graphs, where relations between concepts and entities make up a layout that is very easy for machines to navigate. At the moment, there are only a few tools that enable humans to navigate this new layer of the Internet, and those that exist are for the most part very specialized tools that require from the user a lot of pre-existing knowledge about the technologies behind this structure. In this article we report on the development of DAOLOT, a search engine that allows users with no previous knowledge of the semantic web to take full advantage of its information network. This paper presents its design, the algorithm behind it and the results of the validation testing conducted with users. The results of our validation testing show that DAOLOT is useful and intuitive to users, even those without any previous knowledge of the field, and provides curated information from multiple sources instantly about any topic.

Abstract
Consuming Semantic Web data presents several challenges, from the number of datasets it is composed of, to the (very) large size of some of those datasets and the uncertain availability of querying endpoints. According to its core principles, accessing linked data can be done simply by dereferencing the IRIs of RDF resources. This is a light alternative both for clients and servers when compared to dataset dumps or SPARQL endpoints. The linked data interface does not support complex querying, but using it recursively may suffice to gather information about RDF resources, or to extract the relevant sub-graph which can then be processed and queried using other methods. We present Derzis¹, an open source semantic web crawler capable of traversing the linked data cloud starting from a set of seed resources. Derzis maintains information about the paths followed while crawling, which allows to define property path-based restrictions to the crawling frontier.

Abstract
Scientific publications are the main vehicle to disseminate information in the field of biotechnology for wastewater treatment. Indeed, the new research paradigms and the application of high-throughput technologies have increased the rate of publication considerably. The problem is that manual curation becomes harder, prone-to-errors and time-consuming, leading to a probable loss of information and inefficient knowledge acquisition. As a result, research outputs are hardly reaching engineers, hampering the calibration of mathematical models used to optimize the stability and performance of biotechnological systems. In this context, we have developed a data curation workflow, based on text mining techniques, to extract numerical parameters from scientific literature, and applied it to the biotechnology domain. A workflow was built to process wastewater-related articles with the main goal of identifying physico-chemical parameters mentioned in the text. This work describes the implementation of the workflow, identifies achievements and current limitations in the overall process, and presents the results obtained for a corpus of 50 full-text documents.

Abstract
Abstract This paper investigates the ability of large language models (LLMs) to evaluate semantic relations between word pairs by examining their alignment with human-generated semantic ratings. Semantic relations represent the degree of connection (e.g., relatedness or similarity) between linguistic elements and are traditionally validated against human-annotated datasets. Due to the challenges of building such datasets and recent progress in LLMs’ capacity to model human-like understanding, we explore whether LLMs can serve as reliable substitutes for traditional human ratings. We conducted experiments using multiple LLMs from OpenAI, Google, Mistral, and Anthropic, evaluating their performance across diverse English and Portuguese semantic relations datasets. We included in the analysis PAP900, a recently published dataset of semantic relations in Portuguese, to examine the influence of prior exposure to the dataset on LLM training. The results show that the LLM predictions correlate strongly with human ratings. The findings reveal the potential of LLMs to supplement or replace traditional semantic measure algorithms and crowd-sourced human annotations in semantic tasks.

Abstract
The PAP900 dataset centers on the semantic relationship between affective words in Portuguese. It contains 900 word pairs, each annotated by at least 30 human raters for both semantic similarity and semantic relatedness. In addition to the semantic ratings, the dataset includes the word categorization used to build the word pairs and detailed sociodemographic information about annotators, enabling the analysis of the influence of personal factors on the perception of semantic relationships. Furthermore, this article describes in detail the dataset construction process, from word selection to agreement metrics. Data was collected from Portuguese university psychology students, who completed two rounds of questionnaires. In the first round annotators were asked to rate word pairs on either semantic similarity or relatedness. The second round switched the relation type for most annotators, with a small percentage being asked to repeat the same relation. The instructions given emphasized the differences between semantic relatedness and semantic similarity, and provided examples of expected ratings of both. There are few semantic relations datasets in Portuguese, and none focusing on affective words. PAP900 is distributed in distinct formats to be easy to use for both researchers just looking for the final averaged values and for researchers looking to take advantage of the individual ratings, the word categorization and the annotator data. This dataset is a valuable resource for researchers in computational linguistics, natural language processing, psychology, and cognitive science. (c) 2025TheAuthors.

Abstract
Semantic measure (SM) algorithms allow software to mimic the human ability of assessing the strength of the semantic relations between elements such as concepts, entities, words, or sentences. SM algorithms are typically evaluated by comparison against gold standard datasets built by human annotators. These datasets are composed of pairs of elements and an averaged numeric rating. Building such datasets usually requires asking human annotators to assign a numeric value to their perception of the strength of the semantic relation between two elements. Large language models (LLMs) have recently been successfully used to perform tasks which previously required human intervention, such as text summarization, essay writing, image description, image synthesis, question answering, and so on. In this paper, we present ongoing research on LLMs capabilities for semantic relations assessment. We queried several LLMs to rate the relationship of pairs of elements from existing semantic measures evaluation datasets, and measured the correlation between the results from the LLMs and gold standard datasets. Furthermore, we performed additional experiments to evaluate which other factors can influence LLMs performance in this task. We present and discuss the results obtained so far.