Abstract This paper presents a comprehensive review of the use Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is rigorous and organised methodology that assesses integrates prior research on given topic. Numerous tools have been developed to assist partially automate process. The increasing role AI this field shows great potential providing more effective support for researchers, moving towards semi-automatic creation literature reviews. Our study focuses how...

In the last few years, chatbots have become mainstream solutions adopted in a variety of domains for automatizing communication at scale. same period, knowledge graphs attracted significant attention from business and academia as robust scalable representations information. scientific academic research domain, they are increasingly used to illustrate relevant actors (e.g., researchers, institutions), documents articles, patents), entities concepts, innovations), other related Following...

In recent years, transformer-based models have emerged as powerful tools for natural language processing tasks, demonstrating remarkable performance in several domains. However, they still present significant limitations. These shortcomings become more noticeable when dealing with highly specific and complex concepts, particularly within the scientific domain. For example, transformer particular difficulties articles due to domain-specific terminologies sophisticated ideas often encountered...

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 identifying the emergence of topics, which rely on assumption that topic already exhibiting a certain degree popularity consistently referred by community researchers. However, detecting area at an embryonic stage, i.e., before has been labelled researchers associated with...

Ontologies of research areas are important tools for characterizing, exploring, and analyzing the landscape. Some fields comprehensively described by large-scale taxonomies, e.g., MeSH in Biology PhySH Physics. Conversely, current Computer Science taxonomies coarse-grained tend to evolve slowly. For instance, ACM classification scheme contains only about 2K topics last version dates back 2012. In this paper, we introduce Ontology (CSO), a large-scale, automatically generated ontology areas,...

The tourism and hospitality sectors have become increasingly important in the last few years companies operating this field are constantly challenged with providing new innovative services. At same time, (big-) data has "new oil" of century Knowledge Graphs emerging as most natural way to collect, refine, structure heterogeneous information. In paper, we present a methodology for semi-automatic generating Tourism Graph (TKG), which can be used supporting variety intelligent services space,...

This manuscript presents a comprehensive review of the use Artificial Intelligence (AI) in Systematic Literature Reviews (SLRs). A SLR is rigorous and organised methodology that assesses integrates previous research on given topic. Numerous tools have been developed to assist partially automate process. The increasing role AI this field shows great potential providing more effective support for researchers, moving towards semi-automatic creation literature reviews. Our study focuses how...

Abstract Knowledge Organization Systems (KOSs), such as term lists, thesauri, taxonomies, and ontologies, play a fundamental role in categorising, managing, retrieving information. In the academic domain, KOSs are often adopted for representing research areas their relationships, primarily aiming to classify articles, courses, patents, books, scientific venues, domain experts, grants, software, experiment materials, several other relevant products agents. These structured representations of...

The ability to promptly recognise new research trends is strategic for many stakeholders, including universities, institutional funding bodies, academic publishers and companies. While the literature describes several approaches which aim identify emergence of topics early in their lifecycle, these rely on assumption that topic question already associated with a number publications consistently referred by community researchers. Hence, detecting area at an embryonic stage , i.e., before has...

Abstract Academia and industry share a complex, multifaceted, symbiotic relationship. Analyzing the knowledge flow between them, understanding which directions have biggest potential, discovering best strategies to harmonize their efforts is critical task for several stakeholders. Research publications patents are an ideal medium analyze this space, but current data sets of scholarly cannot be used such purpose because they lack high-quality characterization relevant research topics...

Online platforms have become the primary means for travellers to search, compare, and book accommodations their trips. Consequently, online revenue managers must acquire a comprehensive comprehension of these dynamics formulate competitive appealing offerings. Recent advancements in natural language processing, specifically through development large models, demonstrated significant progress capturing intricate nuances human language. On other hand, knowledge graphs emerged as potent...

Abstract Classifying scientific articles, patents, and other documents according to the relevant research topics is an important task, which enables a variety of functionalities, such as categorising in digital libraries, monitoring predicting trends, recommending papers one or more topics. In this paper, we present latest version CSO Classifier (v3.0), unsupervised approach for automatically classifying Computer Science Ontology (CSO), comprehensive taxonomy areas field Science. The takes...

In this study, we compared several classifiers for the supervised distinction between normal elderly and Alzheimer's disease individuals, based on resting state electroencephalographic markers, age, gender education. Three main preliminary procedures served to perform features dimensionality reduction were used discussed: a Support Vector Machines Recursive Features Elimination, Principal Component Analysis novel method correlation. particular, five different compared: two configurations of...

Knowledge graphs (KGs) are widely used for modeling scholarly communication, performing scientometric analyses, and supporting a variety of intelligent services to explore the literature predict research dynamics. However, they often suffer from incompleteness (e.g., missing affiliations, references, topics), leading reduced scope quality resulting analyses. This issue is usually tackled by computing knowledge graph embeddings (KGEs) applying link prediction techniques. only few KGE models...

In recent decades, we have experienced a continuously increasing publication rate of scientific articles and related research objects (e.g., data sets, software packages). As this trend keeps growing, practitioners in the field scholarly knowledge are confronted with several challenges. special issue, focus on two major categories such challenges: (a) those to organization achieve flexible, context-sensitive, fine-grained, machine-actionable representation that at same time is structured,...