Angelo Antonio Salatino

Automatic Classification of Springer Nature Proceedings with Smart Topic Miner

The process of classifying scholarly outputs is crucial to ensure timely access to knowledge. However, this process is typically carried out manually by expert editors, leading to high costs and slow throughput. In this paper we present Smart Topic Miner (STM), a novel solution which uses semantic web technologies to classify scholarly publications on the basis of a very large automatically generated ontology of research areas. STM was developed to support the Springer Nature Computer Science editorial team in classifying proceedings in the LNCS family. It analyses in real time a set of publications provided by an editor and produces a structured set of topics and a number of Springer Nature Classification tags, which best characterise the given input. In this paper we present the architecture of the system and report on an evaluation study conducted with a team of Springer Nature editors. The results of the evaluation, which showed that STM classifies publications with a high degree of accuracy, are very encouraging and as a result we are currently discussing the required next steps to ensure large-scale deployment within the company.

How are topics born? Understanding the research dynamics preceding the emergence of new areas

The ability to promptly recognise new research trends is strategic for many stake- holders, including universities, institutional funding bodies, academic publishers and companies. While the literature describes several approaches which aim to identify the emergence of new research topics early in their lifecycle, these rely on the assumption that the topic in question is already associated with a number of publications and consistently referred to by a community of researchers. Hence, 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 paper, 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 ‘parents’ of the new topic. These initial findings (i) confirm our hypothesis that it is possible in principle to detect the emergence of a new topic at the embryonic stage, (ii) provide new empirical evidence supporting relevant theories in Philosophy of Science, and also (iii) suggest that new topics tend to emerge in an environment in which weakly interconnected research areas begin to cross-fertilise.

Ontology Forecasting in Scientific Literature: Semantic Concepts Prediction Based on Innovation-Adoption Priors

The ontology engineering research community has focused for many years on supporting the creation, development and evolution of ontologies. Ontology forecasting, which aims at predicting semantic changes in an ontology, represents instead a new challenge. In this paper, we want to give a contribution to this novel endeavour by focusing on the task of forecasting semantic concepts in the research domain. Indeed, ontologies representing scientific disciplines contain only research topics that are already popular enough to be selected by human experts or automatic algorithms. They are thus unfit to support tasks which require the ability of describing and exploring the forefront of research, such as trend detection and horizon scanning. We address this issue by introducing the Semantic Innovation Forecast (SIF) model, which predicts new concepts of an ontology at time t + 1, using only data available at time t. Our approach relies on lexical innovation and adoption information extracted from historical data. We evaluated the SIF model on a very large dataset consisting of over one million scientific papers belonging to the Computer Science domain: the outcomes show that the proposed approach offers a competitive boost in mean average precision-at-ten compared to the baselines when forecasting over 5 years.

The Computer Science Ontology: A Large-Scale Taxonomy of Research Areas

Ontologies of research areas are important tools for characterising, exploring, and analysing the research landscape. Some fields of research are comprehensively described by large-scale taxonomies, e.g., MeSH in Biology and PhySH in Physics. Conversely, current Computer Science taxonomies are coarse-grained and tend to evolve slowly. For instance, the ACM classification scheme contains only about 2K research topics and the last version dates back to 2012. In this paper, we introduce the Computer Science Ontology (CSO), a large-scale, automatically generated ontology of research areas, which includes about 26K topics and 226K semantic relationships. It was created by applying the Klink-2 algorithm on a very large dataset of 16M scientific articles. CSO presents two main advantages over the alternatives: (i) it includes a very large number of topics that do not appear in other classifications, and (ii) it can be updated automatically by running Klink-2 on recent corpora of publications. CSO powers several tools adopted by the editorial team at Springer Nature and has been used to enable a variety of solutions, such as classifying research publications, detecting research communities, and predicting research trends. To facilitate the uptake of CSO we have developed the CSO Portal, a web application that enables users to download, explore, and provide granular feedback on CSO at different levels. Users can use the portal to rate topics and relationships, suggest missing relationships, and visualise sections of the ontology. The portal will support the publication of and access to regular new releases of CSO, with the aim of providing a comprehensive resource to the various communities engaged with scholarly data.

AUGUR: Forecasting the Emergence of New Research Topics

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. We address this issue by introducing Augur, a novel approach to the early detection of 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 interval and outperformed four alternative approaches in terms of both precision and recall.

Detection of Embryonic Research Topics by Analysing Semantic Topic Networks

Being aware of new research topics is an important asset for anybody involved in the research environment, including researchers, academic publishers and institutional funding bodies. In recent years, the amount of scholarly data available on the web has increased steadily, allowing the development of several approaches for detecting emerging research topics and assessing their trends. However, current methods focus on the detection of topics which are already associated with a label or a substantial number of documents. In this paper, we address instead the issue of detecting embryonic topics, which do not possess these characteristics yet. We suggest that it is possible to forecast the emergence of novel research topics even at such early stage and demonstrate that the emergence of a new topic can be anticipated by analysing the dynamics of pre-existing topics. We present an approach to evaluate such dynamics and an experiment on a sample of 3 million research papers, which confirms our hypothesis. In particular, we found that the pace of collaboration in sub-graphs of topics that will give rise to novel topics is significantly higher than the one in the control group.

Advanced classification of Alzheimer's disease and healthy subjects based on EEG markers

In this study, we compared several classifiers for the supervised distinction between normal elderly and Alzheimers disease individuals, based on resting state electroencephalographic markers, age, gender and education. Three main preliminary procedures served to perform features dimensionality reduction were used and discussed: a Support Vector Machines Recursive Features Elimination, a Principal Component Analysis and a novel method based on the correlation. In particular, five different classifiers were compared: two different configurations of SVM and three different optimal topologies of Error Back Propagation Multi Layer Perceptron Artificial Neural Networks (EBP MLP ANNs). Best result, in terms of classification (accuracy 86% and sensitivity 92%), was obtained by a Neural Network with 3 hidden layers that used as input: age, gender, education and 20 EEG features selected by the novel method based on the correlation.

Evaluation of Resonance in Staff Selection through Multimedia Contents

In this paper we present the results of an experimental Italian research project finalized to support the classification process of the two behavioural status (resonance and dissonance) of a candidate applying for a job position. The proposed framework is based on an innovative system designed and implemented to extract and process the non-verbal expressions like facial, gestural and prosodic of the subject, acquired during the whole job interview session. In principle, we created our own database, containing multimedia data extracted, by different software modules, from video, audio and 3D sensor streams and then used SVM classifiers that perform in terms of accuracy 72%, 79% and 63% respectively for facial, vocal and gestural features. ANN classifiers have also been used, obtaining comparable results. Finally, we combined all the three domains and then reported the results of this last classification test proving that the experimental proposed work seems to perform in a very encouraging way.