Sergio Consoli

Sergio Consoli, Peter Markov, Nikolaos I. Stilianakis et al.

This paper presents a novel approach to epidemic surveillance, leveraging the power of Artificial Intelligence and Large Language Models (LLMs) for effective interpretation of unstructured big data sources, like the popular ProMED and WHO Disease Outbreak News. We explore several LLMs, evaluating their capabilities in extracting valuable epidemic information. We further enhance the capabilities of the LLMs using in-context learning, and test the performance of an ensemble model incorporating multiple open-source LLMs. The findings indicate that LLMs can significantly enhance the accuracy and timeliness of epidemic modelling and forecasting, offering a promising tool for managing future pandemic events.

Sergio Consoli, Luca Tiozzo Pezzoli, Elisa Tosetti

In this paper we employ economic news within a neural network framework to forecast the Italian 10-year interest rate spread. We use a big, open-source, database known as Global Database of Events, Language and Tone to extract topical and emotional news content linked to bond markets dynamics. We deploy such information within a probabilistic forecasting framework with autoregressive recurrent networks (DeepAR). Our findings suggest that a deep learning network based on Long-Short Term Memory cells outperforms classical machine learning techniques and provides a forecasting performance that is over and above that obtained by using conventional determinants of interest rates alone.

Luca Barbaglia, Sergio Consoli, Sebastiano Manzan

The goal of this paper is to evaluate the informational content of sentiment extracted from news articles about the state of the economy. We propose a fine-grained aspect-based sentiment analysis that has two main characteristics: 1) we consider only the text in the article that is semantically dependent on a term of interest (aspect-based) and, 2) assign a sentiment score to each word based on a dictionary that we develop for applications in economics and finance (fine-grained). Our data set includes six large US newspapers, for a total of over 6.6 million articles and 4.2 billion words. Our findings suggest that several measures of economic sentiment track closely business cycle fluctuations and that they are relevant predictors for four major macroeconomic variables. We find that there are significant improvements in forecasting when sentiment is considered along with macroeconomic factors. In addition, we also find that sentiment matters to explains the tails of the probability distribution across several macroeconomic variables.

Vanni Zavarella, Sergio Consoli, Diego Reforgiato Recupero et al.

Numerous methods and pipelines have recently emerged for the automatic extraction of knowledge graphs from documents such as scientific publications and patents. However, adapting these methods to incorporate alternative text sources like micro-blogging posts and news has proven challenging as they struggle to model open-domain entities and relations, typically found in these sources. In this paper, we propose an enhanced information extraction pipeline tailored to the extraction of a knowledge graph comprising open-domain entities from micro-blogging posts on social media platforms. Our pipeline leverages dependency parsing and classifies entity relations in an unsupervised manner through hierarchical clustering over word embeddings. We provide a use case on extracting semantic triples from a corpus of 100 thousand tweets about digital transformation and publicly release the generated knowledge graph. On the same dataset, we conduct two experimental evaluations, showing that the system produces triples with precision over 95% and outperforms similar pipelines of around 5% in terms of precision, while generating a comparatively higher number of triples.

Oscar Araque, Lorenzo Gatti, Sergio Consoli et al.

The moral value of liberty is a central concept in our inference system when it comes to taking a stance towards controversial social issues such as vaccine hesitancy, climate change, or the right to abortion. Here, we propose a novel Liberty lexicon evaluated on more than 3,000 manually annotated data both in in- and out-of-domain scenarios. As a result of this evaluation, we produce a combined lexicon that constitutes the main outcome of this work. This final lexicon incorporates information from an ensemble of lexicons that have been generated using word embedding similarity (WE) and compositional semantics (CS). Our key contributions include enriching the liberty annotations, developing a robust liberty lexicon for broader application, and revealing the complexity of expressions related to liberty across different platforms. Through the evaluation, we show that the difficulty of the task calls for designing approaches that combine knowledge, in an effort of improving the representations of learning systems.

Vanni Zavarella, Juan Carlos Gamero-Salinas, Sergio Consoli

Knowledge graphs (KGs) have been successfully applied to the analysis of complex scientific and technological domains, with automatic KG generation methods typically building upon relation extraction models capturing fine-grained relations between domain entities in text. While these relations are fully applicable across scientific areas, existing models are trained on few domain-specific datasets such as SciERC and do not perform well on new target domains. In this paper, we experiment with leveraging in-context learning capabilities of Large Language Models to perform schema-constrained data annotation, collecting in-domain training instances for a Transformer-based relation extraction model deployed on titles and abstracts of research papers in the Architecture, Construction, Engineering and Operations (AECO) domain. By assessing the performance gain with respect to a baseline Deep Learning architecture trained on off-domain data, we show that by using a few-shot learning strategy with structured prompts and only minimal expert annotation the presented approach can potentially support domain adaptation of a science KG generation model.

Sergio Consoli, Luca Tiozzo Pezzoli, Elisa Tosetti

We show how emotions extracted from macroeconomic news can be used to explain and forecast future behaviour of sovereign bond yield spreads in Italy and Spain. We use a big, open-source, database known as Global Database of Events, Language and Tone to construct emotion indicators of bond market affective states. We find that negative emotions extracted from news improve the forecasting power of government yield spread models during distressed periods even after controlling for the number of negative words present in the text. In addition, stronger negative emotions, such as panic, reveal useful information for predicting changes in spread at the short-term horizon, while milder emotions, such as distress, are useful at longer time horizons. Emotions generated by the Italian political turmoil propagate to the Spanish news affecting this neighbourhood market.

Luca Barbaglia, Sergio Consoli, Sebastiano Manzan

We evaluate the informational content of news-based sentiment indicators for forecasting Gross Domestic Product (GDP) and other macroeconomic variables of the five major European economies. Our data set includes over 27 million articles for 26 major newspapers in 5 different languages. The evidence indicates that these sentiment indicators are significant predictors to forecast macroeconomic variables and their predictive content is robust to controlling for other indicators available to forecasters in real-time.

Luca Barbaglia, Sergio Consoli, Sebastiano Manzan et al.

We propose an Economic Lexicon (EL) specifically designed for textual applications in economics. We construct the dictionary with two important characteristics: 1) to have a wide coverage of terms used in documents discussing economic concepts, and 2) to provide a human-annotated sentiment score in the range [-1,1]. We illustrate the use of the EL in the context of a simple sentiment measure and consider several applications in economics. The comparison to other lexicons shows that the EL is superior due to its wider coverage of domain relevant terms and its more accurate categorization of the word sentiment.

Sergio Consoli, Pietro Coletti, Peter V. Markov et al.

The rapid evolution of artificial intelligence (AI), together with the increased availability of social media and news for epidemiological surveillance, are marking a pivotal moment in epidemiology and public health research. Leveraging the power of generative AI, we use an ensemble approach which incorporates multiple Large Language Models (LLMs) to extract valuable actionable epidemiological information from the World Health Organization (WHO) Disease Outbreak News (DONs). DONs is a collection of regular reports on global outbreaks curated by the WHO and the adopted decision-making processes to respond to them. The extracted information is made available in a daily-updated dataset and a knowledge graph, referred to as eKG, derived to provide a nuanced representation of the public health domain knowledge. We provide an overview of this new dataset and describe the structure of eKG, along with the services and tools used to access and utilize the data that we are building on top. These innovative data resources open altogether new opportunities for epidemiological research, and the analysis and surveillance of disease outbreaks.

Michael van Hartskamp, Sergio Consoli, Wim Verhaegh et al.

The idea of Artificial Intelligence (AI) has a long history. It turned out, however, that reaching intelligence at human levels is more complicated than originally anticipated. Currently we are experiencing a renewed interest in AI, fueled by an enormous increase in computing power and an even larger increase in data, in combination with improved AI technologies like deep learning. Healthcare is considered the next domain to be revolutionized by Artificial Intelligence. While AI approaches are excellently suited to develop certain algorithms, for biomedical applications there are specific challenges. We propose recommendations to improve AI projects in the biomedical space and especially clinical healthcare.

Marijn van Knippenberg, Vlado Menkovski, Sergio Consoli

Neuro-Evolution is a field of study that has recently gained significantly increased traction in the deep learning community. It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural networks. Recent Neuro-Evolution approaches have shown promising results, rivaling hand-crafted neural networks in terms of accuracy. A two-step approach is introduced where a convolutional autoencoder is created that efficiently compresses the input data in the first step, and a convolutional neural network is created to classify the compressed data in the second step. The creation of networks in both steps is guided by by an evolutionary process, where new networks are constantly being generated by mutating members of a collection of existing networks. Additionally, a method is introduced that considers the trade-off between compression and information loss of different convolutional autoencoders. This is used to select the optimal convolutional autoencoder from among those evolved to compress the data for the second step. The complete framework is implemented, tested on the popular CIFAR-10 data set, and the results are discussed. Finally, a number of possible directions for future work with this particular framework in mind are considered, including opportunities to improve its efficiency and its application in particular areas.

Sergio Consoli, Jacek Kustra, Pieter Vos et al.

We provide preliminary details and formulation of an optimization strategy under current development that is able to automatically tune the parameters of a Support Vector Machine over new datasets. The optimization strategy is a heuristic based on Iterated Local Search, a modification of classic hill climbing which iterates calls to a local search routine.

Sergio Consoli, Josè Andrès Moreno Pèrez

In this paper we describe an extension of the Variable Neighbourhood Search (VNS) which integrates the basic VNS with other complementary approaches from machine learning, statistics and experimental algorithmic, in order to produce high-quality performance and to completely automate the resulting optimization strategy. The resulting intelligent VNS has been successfully applied to a couple of optimization problems where the solution space consists of the subsets of a finite reference set. These problems are the labelled spanning tree and forest problems that are formulated on an undirected labelled graph; a graph where each edge has a label in a finite set of labels L. The problems consist on selecting the subset of labels such that the subgraph generated by these labels has an optimal spanning tree or forest, respectively. These problems have several applications in the real-world, where one aims to ensure connectivity by means of homogeneous connections.

Sergio Consoli, Josè Andrès Moreno Pèrez, Nenad Mladenovic

In a currently ongoing project, we investigate a new possibility for solving the k-labelled spanning forest (kLSF) problem by an intelligent Variable Neighbourhood Search (Int-VNS) metaheuristic. In the kLSF problem we are given an undirected input graph G and an integer positive value k, and the aim is to find a spanning forest of G having the minimum number of connected components and the upper bound k on the number of labels to use. The problem is related to the minimum labelling spanning tree (MLST) problem, whose goal is to get the spanning tree of the input graph with the minimum number of labels, and has several applications in the real world, where one aims to ensure connectivity by means of homogeneous connections. The Int-VNS metaheuristic that we propose for the kLSF problem is derived from the promising intelligent VNS strategy recently proposed for the MLST problem, and integrates the basic VNS for the kLSF problem with other complementary approaches from machine learning, statistics and experimental algorithmics, in order to produce high-quality performance and to completely automate the resulting strategy.