Search

Explaining how two machine learning classification models differ in their behaviour is gaining significance in eXplainable AI, given the increasing diffusion of learning-based decision support systems. Human decision-makers deal with more than one machine learning model in several practical situations. Consequently, the importance of understanding how two machine learning models work beyond their prediction performances is key to understanding their behaviour, differences, and likeness. Some attempts have been made to address these problems, for instance, by explaining text classifiers in a time-contrastive fashion. In this paper, we present MERLIN, a novel eXplainable AI approach that provides contrastive explanations of two machine learning models, introducing the concept of model-contrastive explanations. We propose an encoding that allows MERLIN to work with both text and tabular data and with mixed continuous and discrete features. To show the effectiveness of our approach, we evaluate it on an extensive set of benchmark datasets. MERLIN is also implemented as a python-pip package.

The rise of Big Data era calls for more efficient and effective Data Exploration and analysis tools. In this respect, the need to support advanced analytics on Big Data is driving data scientist’ interest toward massively parallel distributed systems and software platforms, such as Map-Reduce and Spark, that make possible their scalable utilization. However, when complex data mining algorithms are required, their fully scalable deployment on such platforms faces a number of technical challenges that grow with the complexity of the algorithms involved. Thus algorithms, that were originally designed for a sequential nature, must often be redesigned in order to effectively use the distributed computational resources. In this paper, we explore these problems, and then propose a solution which has proven to be very effective on the complex hierarchical clustering algorithm CLUBS+. By using four stages of successive refinements, CLUBS+ delivers high-quality clusters of data grouped around their centroids, working in a totally unsupervised fashion. Experimental results confirm the accuracy and scalability of CLUBS+ on platforms tailored for Big Data management.

This paper develops a set of innovative tools for labor market intelligence by applying machine learning techniques to web vacancies on the Italian labor market. Our approach allows to calculate, for each occupation, the different types of skills required by the market alongside a set of relevant variables such as region, sector, education and level of experience. We construct a taxonomy for skills and map it into the recently developed ESCO classification system. We subsequently develop measures of the relevance of soft and hard skills and we analyze their detailed composition. We apply the dataset constructed to the debate on computerization of work. We show that soft and digital skills are related to the probability of automation of a given occupation and we shed some light on the complementarity/substitutability of hard and soft skills.

Lexical taxonomies are widely used to foster information retrieval and exchange in several domains and applications. When there are multiple taxonomies, heterogeneity among them is a severe problem for efficient collaboration processes. In this paper, we propose WETA, a domain-independent, knowledge-poor method for automatic taxonomy alignment via word embeddings. WETA associates all the leaf terms of the origin taxonomy to one or many concepts in the destination taxonomy, employing a scoring function, which merges the score of a hierarchical method based on cosine similarity and the score of a classification task. WETA is developed in the context of an EU Grant aiming at bridging the national taxonomies of EU countries towards the European Skills, Competences, Qualifications and Occupations taxonomy (ESCO) using AI Algorithms. The results, validated within the EU project activities for bridging the Italian occupation taxonomy CP and ESCO, confirm the usefulness of WETA in supporting the automatic alignment of national labor taxonomies. WETA reaches a 0.8 accuracy on recommending top-5 occupations and a wMRR of 0.72. WETA reduces the human effort needed for building a mapping from scratch: it would allow domain experts to concentrate on the validation task and decrease the incoherence due to multiple judgments. It would also make the approach reproducible and transparent to policymakers.

The rapid growth of Web usage for advertising job positions provides a great opportunity for real-time labour market monitoring. This is the aim of Labour Market Intelligence (LMI), a field that is becoming increasingly relevant to EU Labour Market policies design and evaluation. The analysis of Web job vacancies, indeed, represents a competitive advantage to labour market stakeholders with respect to classical survey-based analyses, as it allows for reducing the time-to-market of the analysis by moving towards a fact-based decision making model. In this paper, we present our approach for automatically classifying million Web job vacancies on a standard taxonomy of occupations. We show how this problem has been expressed in terms of text classification via machine learning. We also show how our approach has been applied to certain real-life projects and we discuss the benefits provided to end users.

We propose a recommender system that, starting from a set of users’ skills, identifies the most suitable jobs as they emerge from a large dataset of Online Job Vacancies (OJVs). To this aim, we process 2.5M+ OJVs posted in three different countries (United Kingdom, France, and Germany), training several embeddings and performing an intrinsic evaluation of their quality. Besides, we compute a measure of skill importance for each occupation in each country, the Revealed Comparative Advantage (rca). The best vector model, one for each country, together with the rca, is used to feed a graph database, which will serve as the keystone for the recommender system. Results are evaluated through a user study of 10 labor market experts, using P@3 and nDCG as scores. Results show a high precision for the recommendations provided by skills2job , and the high values of nDCG (0.985 and 0.984 in a [0,1] range) indicate a strong correlation between the experts’ scores and the rankings generated by skills2job .

Taxonomies are the mainstay of the semantic web as they aim at organising knowledge in concepts linked by IS-A relationships. However, keeping such hierarchies updated and able to represent the domain from which they have been drawn is still a time-consuming, costly and error prone activity. Here, word embeddings have proven to be effective in catching lexicon and semantic similarities to enrich taxonomies from text data. This, in turn, would require to evaluate the generated embeddings to estimate the extent to which they encode the semantic similarity derived from the hierarchy itself. In this paper, we propose and implement MEET-LM , a methodology that aims at generating and evaluating embeddings from a text corpus preserving the co-hyponymy relations synthesised from a domain-specific taxonomy. We apply MEET-LM to a real-life dataset of 2M+ vacancies related to ICT-jobs, framed within the research activities of an EU project that collects millions of Online Job Vacancies and classifies them within the European standard hierarchy ESCO. To show MEET-LM is useful in practice, we also trained a neural network to classify co-hyponym relations using the selected embeddings as features. Our experiments reach 99.4 % of accuracy and 86.5 % of f1-score.

We live in the Information Age, where most of the personal, business, and administrative data are collected and managed electronically. However, poor data quality may affect the effectiveness of knowledge discovery processes, thus making the development of the data improvement steps a significant concern. In this paper we propose the Multidimensional Robust Data Quality Analysis, a domain-independent technique aimed to improve data quality by evaluating the effectiveness of a black-box cleansing function. Here, the proposed approach has been realized through model checking techniques and then applied on a weakly structured dataset describing the working careers of millions of people. Our experimental outcomes show the effectiveness of our model-based approach for data quality as they provide a fine-grained analysis of both the source dataset and the cleansing procedures, enabling domain experts to identify the most relevant quality issues as well as the action points for improving the cleansing activities. Finally, an anonymized version of the dataset and the analysis results have been made publicly available to the community.

Over recent years, there has been a noticeable increase in the prescription of psychotropic drugs (PDs), particularly antidepressants (ADs). The aim of this retrospective study was to evaluate the consumption of PDs by all adult employees in Lombardy aged >18 years in the period 2007-2011 and the possible changes induced by the “economic crisis” in this highly productive area of Italy. The subjects were classified by gender, age class, nationality, education and province. During the five-year period, there were 3,554,860 employed adults in Lombardy, of whom 277,865 (7.8%) used PDs. The use of PDs (particularly ADs) was associated with being an Italian woman aged >55 years with a basic education and a blue collar job. The lower prevalence in immigrants may be due to the difficulty in gaining access to health services. The increase in PD use can be attributed more specifically to ADs and anti-epileptic drugs with anxiolytic properties. Although continuously increasing, the use of AD fluctuated and was greater during the fall and winter. The increase involved all of the provinces in Lombardy in a similar manner. In 39% of cases, the use of PDs (and particularly ADs) was limited to one trimester, although the AD guidelines suggest at least 6-12 months of treatment.