Angelo A. Salatino

Angelo Salatino, Tanay Aggarwal, Andrea Mannocci et al.

Knowledge Organization Systems (KOSs), such as term lists, thesauri, taxonomies, and ontologies, play a fundamental role in categorising, managing, and retrieving information. In the academic domain, KOSs are often adopted for representing research areas and their relationships, primarily aiming to classify research articles, academic courses, patents, books, scientific venues, domain experts, grants, software, experiment materials, and several other relevant products and agents. These structured representations of research areas, widely embraced by many academic fields, have proven effective in empowering AI-based systems to i) enhance retrievability of relevant documents, ii) enable advanced analytic solutions to quantify the impact of academic research, and iii) analyse and forecast research dynamics. This paper aims to present a comprehensive survey of the current KOS for academic disciplines. We analysed and compared 45 KOSs according to five main dimensions: scope, structure, curation, usage, and links to other KOSs. Our results reveal a very heterogeneous scenario in terms of scope, scale, quality, and usage, highlighting the need for more integrated solutions for representing research knowledge across academic fields. We conclude by discussing the main challenges and the most promising future directions.

Alessandra Belfiore, Angelo Salatino, Francesco Osborne

Interest in Artificial Intelligence (AI) continues to grow rapidly, hence it is crucial to support researchers and organisations in understanding where AI research is heading. In this study, we conducted a bibliometric analysis on 257K articles in AI, retrieved from OpenAlex. We identified the main conceptual themes by performing clustering analysis on the co-occurrence network of topics. Finally, we observed how such themes evolved over time. The results highlight the growing academic interest in research themes like deep learning, machine learning, and internet of things.

Michael McCoubrey, Angelo Salatino, Francesco Osborne et al.

In recent years, there has been a growing use of generative AI, and large language models (LLMs) in particular, to support both the assessment and generation of scientific work. Although some studies have shown that LLMs can, to a certain extent, evaluate research according to perceived quality, our understanding of the internal mechanisms that enable this capability remains limited. This paper presents the first study that investigates how LLMs encode the concept of scientific quality through relevant monosemantic features extracted using sparse autoencoders. We derive such features under different experimental settings and assess their ability to serve as predictors across three tasks related to research quality: predicting citation count, journal SJR, and journal h-index. The results indicate that LLMs encode features associated with multiple dimensions of scientific quality. In particular, we identify four recurring types of features that capture key aspects of how research quality is represented: 1) features reflecting research methodologies; 2) features related to publication type, with literature reviews typically exhibiting higher impact; 3) features associated with high-impact research fields and technologies; and 4) features corresponding to specific scientific jargons. These findings represent an important step toward understanding how LLMs encapsulate concepts related to research quality.

Andrea Cadeddu, Alessandro Chessa, Vincenzo De Leo et al.

In 2012, the United Nations introduced 17 Sustainable Development Goals (SDGs) aimed at creating a more sustainable and improved future by 2030. However, tracking progress toward these goals is difficult because of the extensive scale and complexity of the data involved. Text classification models have become vital tools in this area, automating the analysis of vast amounts of text from a variety of sources. Additionally, large language models (LLMs) have recently proven indispensable for many natural language processing tasks, including text classification, thanks to their ability to recognize complex linguistic patterns and semantics. This study analyzes various proprietary and open-source LLMs for a single-label, multi-class text classification task focused on the SDGs. Then, it also evaluates the effectiveness of task adaptation techniques (i.e., in-context learning approaches), namely Zero-Shot and Few-Shot Learning, as well as Fine-Tuning within this domain. The results reveal that smaller models, when optimized through prompt engineering, can perform on par with larger models like OpenAI's GPT (Generative Pre-trained Transformer).

Francisco Bolanos, Angelo Salatino, Francesco Osborne et al.

This manuscript presents a comprehensive review of the use of Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is a rigorous and organised methodology that assesses and integrates previous research on a given topic. Numerous tools have been developed to assist and partially automate the SLR process. The increasing role of AI in this field shows great potential in providing more effective support for researchers, moving towards the semi-automatic creation of literature reviews. Our study focuses on how AI techniques are applied in the semi-automation of SLRs, specifically in the screening and extraction phases. We examine 21 leading SLR tools using a framework that combines 23 traditional features with 11 AI features. We also analyse 11 recent tools that leverage large language models for searching the literature and assisting academic writing. Finally, the paper discusses current trends in the field, outlines key research challenges, and suggests directions for future research.

Tanay Aggarwal, Angelo Salatino, Francesco Osborne et al.

Ontologies of research topics are crucial for structuring scientific knowledge, enabling scientists to navigate vast amounts of research, and forming the backbone of intelligent systems such as search engines and recommendation systems. However, manual creation of these ontologies is expensive, slow, and often results in outdated and overly general representations. As a solution, researchers have been investigating ways to automate or semi-automate the process of generating these ontologies. This paper offers a comprehensive analysis of the ability of large language models (LLMs) to identify semantic relationships between different research topics, which is a critical step in the development of such ontologies. To this end, we developed a gold standard based on the IEEE Thesaurus to evaluate the task of identifying four types of relationships between pairs of topics: broader, narrower, same-as, and other. Our study evaluates the performance of seventeen LLMs, which differ in scale, accessibility (open vs. proprietary), and model type (full vs. quantised), while also assessing four zero-shot reasoning strategies. Several models have achieved outstanding results, including Mixtral-8x7B, Dolphin-Mistral-7B, and Claude 3 Sonnet, with F1-scores of 0.847, 0.920, and 0.967, respectively. Furthermore, our findings demonstrate that smaller, quantised models, when optimised through prompt engineering, can deliver performance comparable to much larger proprietary models, while requiring significantly fewer computational resources.

Andrea Cadeddu, Alessandro Chessa, Vincenzo De Leo et al.

The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised framework for addressing critical societal, environmental, and economic challenges. Recent developments in natural language processing (NLP) and large language models (LLMs) have facilitated the automatic classification of textual data according to their relevance to specific SDGs. Nevertheless, in many applications, it is equally important to determine the directionality of this relevance; that is, to assess whether the described impact is positive, neutral, or negative. To tackle this challenge, we propose the novel task of SDG polarity detection, which assesses whether a text segment indicates progress toward a specific SDG or conveys an intention to achieve such progress. To support research in this area, we introduce SDG-POD, a benchmark dataset designed specifically for this task, combining original and synthetically generated data. We perform a comprehensive evaluation using six state-of-the-art large LLMs, considering both zero-shot and fine-tuned configurations. Our results suggest that the task remains challenging for the current generation of LLMs. Nevertheless, some fine-tuned models, particularly QWQ-32B, achieve good performance, especially on specific Sustainable Development Goals such as SDG-9 (Industry, Innovation and Infrastructure), SDG-12 (Responsible Consumption and Production), and SDG-15 (Life on Land). Furthermore, we demonstrate that augmenting the fine-tuning dataset with synthetically generated examples yields improved model performance on this task. This result highlights the effectiveness of data enrichment techniques in addressing the challenges of this resource-constrained domain. This work advances the methodological toolkit for sustainability monitoring and provides actionable insights into the development of efficient, high-performing polarity detection systems.

Tanay Aggarwal, Angelo Salatino, Francesco Osborne et al.

Ontologies and taxonomies of research fields are critical for managing and organising scientific knowledge, as they facilitate efficient classification, dissemination and retrieval of information. However, the creation and maintenance of such ontologies are expensive and time-consuming tasks, usually requiring the coordinated effort of multiple domain experts. Consequently, ontologies in this space often exhibit uneven coverage across different disciplines, limited inter-domain connectivity, and infrequent updating cycles. In this study, we investigate the capability of several large language models to identify semantic relationships among research topics within three academic domains: biomedicine, physics, and engineering. The models were evaluated under three distinct conditions: zero-shot prompting, chain-of-thought prompting, and fine-tuning on existing ontologies. Additionally, we assessed the cross-domain transferability of fine-tuned models by measuring their performance when trained in one domain and subsequently applied to a different one. To support this analysis, we introduce PEM-Rel-8K, a novel dataset consisting of over 8,000 relationships extracted from the most widely adopted taxonomies in the three disciplines considered in this study: MeSH, PhySH, and IEEE. Our experiments demonstrate that fine-tuning LLMs on PEM-Rel-8K yields excellent performance across all disciplines.

Mojtaba Nayyeri, Gokce Muge Cil, Sahar Vahdati et al.

The incompleteness of Knowledge Graphs (KGs) is a crucial issue affecting the quality of AI-based services. In the scholarly domain, KGs describing research publications typically lack important information, hindering our ability to analyse and predict research dynamics. In recent years, link prediction approaches based on Knowledge Graph Embedding models became the first aid for this issue. In this work, we present Trans4E, a novel embedding model that is particularly fit for KGs which include N to M relations with N$\gg$M. This is typical for KGs that categorize a large number of entities (e.g., research articles, patents, persons) according to a relatively small set of categories. Trans4E was applied on two large-scale knowledge graphs, the Academia/Industry DynAmics (AIDA) and Microsoft Academic Graph (MAG), for completing the information about Fields of Study (e.g., 'neural networks', 'machine learning', 'artificial intelligence'), and affiliation types (e.g., 'education', 'company', 'government'), improving the scope and accuracy of the resulting data. We evaluated our approach against alternative solutions on AIDA, MAG, and four other benchmarks (FB15k, FB15k-237, WN18, and WN18RR). Trans4E outperforms the other models when using low embedding dimensions and obtains competitive results in high dimensions.

Angelo Salatino, Andrea Mannocci, Francesco Osborne

Analysing research trends and predicting their impact on academia and industry is crucial to gain a deeper understanding of the advances in a research field and to inform critical decisions about research funding and technology adoption. In the last years, we saw the emergence of several publicly-available and large-scale Scientific Knowledge Graphs fostering the development of many data-driven approaches for performing quantitative analyses of research trends. This chapter presents an innovative framework for detecting, analysing, and forecasting research topics based on a large-scale knowledge graph characterising research articles according to the research topics from the Computer Science Ontology. We discuss the advantages of a solution based on a formal representation of topics and describe how it was applied to produce bibliometric studies and innovative tools for analysing and predicting research dynamics.

Angelo A. Salatino, Francesco Osborne, Thiviyan Thanapalasingam et al.

Classifying research papers according to their research topics is an important task to improve their retrievability, assist the creation of smart analytics, and support a variety of approaches for analysing and making sense of the research environment. In this paper, we present the CSO Classifier, a new unsupervised approach for automatically classifying research papers according to the Computer Science Ontology (CSO), a comprehensive ontology of re-search areas in the field of Computer Science. The CSO Classifier takes as input the metadata associated with a research paper (title, abstract, keywords) and returns a selection of research concepts drawn from the ontology. The approach was evaluated on a gold standard of manually annotated articles yielding a significant improvement over alternative methods.

Angelo A. Salatino, Francesco Osborne, Enrico Motta

Ontologies of research areas have been proven to be useful in many application for analysing and making sense of scholarly data. In this chapter, we present the Computer Science Ontology (CSO), which is the largest ontology of research areas in the field of Computer Science, and discuss a number of applications that build on CSO, to support high-level tasks, such as topic classification, metadata extraction, and recommendation of books.

Angelo Antonio Salatino

Being able to rapidly recognise new research trends is strategic for many stakeholders, including universities, institutional funding bodies, academic publishers and companies. The literature presents several approaches to identifying the emergence of new research topics, which rely on the assumption that the topic is already exhibiting a certain degree of popularity and consistently referred to by a community of researchers. However, detecting the emergence of a new research area at an embryonic stage, i.e., before the topic has been consistently labelled by a community of researchers and associated with a number of publications, is still an open challenge. In this dissertation, we begin to address this challenge by performing a study of the dynamics preceding the creation of new topics. This study indicates that the emergence of a new topic is anticipated by a significant increase in the pace of collaboration between relevant research areas, which can be seen as the 'ancestors' of the new topic. Based on this understanding, we developed Augur, a novel approach to effectively detecting the emergence of new research topics. Augur analyses the diachronic relationships between research areas and is able to detect clusters of topics that exhibit dynamics correlated with the emergence of new research topics. Here we also present the Advanced Clique Percolation Method (ACPM), a new community detection algorithm developed specifically for supporting this task. Augur was evaluated on a gold standard of 1,408 debutant topics in the 2000-2011 timeframe and outperformed four alternative approaches in terms of both precision and recall.