To be truly innovative it is necessary to go beyond the boundary of consolidated practices and have an overview of the scenario; then identify new perspectives, define challenging goals, work creatively, commit to reaching new goals.

This is the mindset of innovation according to Piazza Copernico.

Whether it is an incremental or radical, improvement or replacement innovation, each innovation is a new and creative way of dealing with known and emerging problems.

Making innovation requires an "ambidextrous” approach (Charles O'Reilly and Michael Tushman, Harvard Business Review, 2004), that is, to overcome the impasse between established and functioning practices and knowing how to explore new paths and opportunities, while maintaining the ability to effectively carry out existing activities.

However, innovation is not alone doing things in a new way, but also lead the change both in the business processes, both in the leadership of people inspiring them towards innovation and improvement.

Piazza Copernico realizes this challenge with aoptics of Open Innovation and through a Innovation Plan and Research and Development (R&D) updated annually.

The Plan is dedicated to the study and development of new applications specifically dedicated to the Training and HR sector, but always plans to make these new transversal applications, where possible extending its use in other business sectors.


Piazza Copernico has experimented in the R&D area the approach of combining corporate professionalism with the world of research with a view to Open Innovation, consolidating in this sense important collaborations with organisms specialized with which it collaborates on:

  • own internal projects,
  • training of the Digital Transformation professions,
  • dissemination of artificial intelligence practices and methods.

For this reason, a specialized team has been created within our company which coordinates all the Innovation activities, which develops and monitors important collaborations with companies, organizations, National Research Organizations e University, for example:


The main areas of work are currently:

  • innovation and experimentation of new didactic models e e-learning solutions;
  • qualitative analysis of the texts, through semantic analysis techniques, Sentiment Analysis and Opinion Mining, Natural Language Processing;
  • paradigm generation of data visualization and creation of statistical indicators through Pattern Analysis, Clustering and aggregate indexing techniques.

Just from the activities of Research and development the numerous production innovations that PIAZZA COPERNICO continually makes available to its customers are born.


Semantic analysis models, through which contents and relationships are analyzed, elaborating a hierarchical map of contents


La Sentiment Analysis allows you to analyze the words carrying polarization and to check the trend of the opinions of individuals and of the topics to identify areas of satisfaction / dissatisfaction


For each type of numerical or structured data it is possible to organize Analytics dashboards aimed at data visualization


From research to field application

On the themes of the DIGITAL TRANSFORMATION companies are witnessing a very rapid acceleration both in the projects started and in the acquisition of talents and professionalism.

Often we find ourselves facing new problems and issues, with procedures and guidelines of action not yet consolidated.

The need for a continuous updating, inspired by a concrete approach and focused on real problems, in order to exploit the potential of new models that continually emerge in research.

Knowing how to adapt modeling choices to objectives, data and concrete problems is a fundamental skill for those who work with innovation.

The training offer of #InnovationLabs

The seminar formula (4 hours) has the function of providing operators with the study coordinates of a problem.

The workshop (from 8 to 12 hours) is a didactic experience led by subject matter experts that allows you to experiment with innovative techniques and tools in practical cases. It allows you to do an active experimentation, deepening and meta-evaluation of the most interesting and innovative methods.

Purpose of #InnovationLabs

To experiment under the supervision of experts different models of textual data analysis, through the use of the most advanced techniques of artificial intelligence.
The training course combines theoretical insights with a strong practical component, with real applications to business models.

#InnovationLabs recipients

Data scientists who work in the company in the field of data and text management

#InnovationLabs catalog

AREA: Innovation in HR
Basics in HR data science
Understanding HR data science and data driven decision making
Data understanding: fundamentals
Natural language processing: summarization, text classification and question answering with Transformers Models in python and R.
Understanding linguistics & meanings between sentiment and semantics in working environments
AREA: Machine Learning
Bayesian Machine Learning with R. Data import: Problems, strategies and solutions
Bayesian Machine Learning with R. Import of data: choice and evaluation of models
Bayesian Machine Learning with R. Data import: prediction between problems, significance and opportunity
Machine Learning: Bayesian Machine Learning laboratory with R. Graphing and data visualization
High performance computing
Bayesian Machine Learning with R and C ++


Data science new perspectives: Text classification with Transformers
2022, June, 8th


Application Deadline
2022, May, 25th



Software by Semantic analysis and Sentiment of large volumes of open texts.

The Semantic Analysis and Sentiment algorithms analyze the words of the original texts to find out which themes go through them, how they are connected to each other and how they change over time.
These algorithms allow to overcome the bias manual classification of data by a team of assessors, as well as significantly reducing the broad effort required.

The software facilitates and reduces the manual analysis work, providing an objective summary on which the evaluators can work directly on the interpretation of the results.

How to use SemantiCase:

  • per intercept the actually relevant arguments for people, even identifying new or latent topics from their first evidence;
  • per measure the graduality of opinions (positive or negative) stratified by categories of people, by individual, by topic / topic by adopting a measurement calibrated on internal communication;
  • per understand the "sensitive" and influential issues on opinion;
  • to identify the typical communicative characteristics of each category of people in order to harmonize communication with the specific language of the various groups;
  • per monitor over time the more or less influential themes on people's judgment.

Examples of application of SemantiCase:



LearnalyzeR is a system of learning analytics developed to communicate via API with company LMS platforms. The tool is responsible for processing the data stored daily in the corporate training platforms, acquiring the data of all training from online courses, videos, classrooms and webinars, social learning and ticketing and tutoring systems.

LearnalyzeR uses a  composite quantitative indicator formed by the aggregation of quantitative sub-indicators to measure the training experience of each user, and compare it with other participants or other courses (even of different methodology).

It is therefore a dashboard for analyzing the progress of courses, with the possibility of comparing different editions of a course or organization chart nodes, with the ability to analyze recurring patterns and classify behavior on courses.

It is an expert analysis system, whose values ​​can be easily customized on the specificities of the training context of the data and automatically parameterized to describe the learning experience.

In fact, the analysis model and the variables that characterize it can be "re-weighted", that is, adjusted to the values ​​and the Corporate KPIs, by administering a preliminary questionnaire to the operators of the company Digital Academy.

LearnalyzeR is a daily utility tool to support the Academies because it allows you to analyze the evolution of data and make data-driven decisions in an increasingly effective way to manage the provision of training courses of various kinds: online courses, classroom courses / webinars, blended courses, video courses.

The assumption of the tool is that the participant's training experience does not end in the launch and study of individual teaching materials, but is a more complex process in which the platform as a relationship environment with other participants and / or with a tutor supporting the study, or even with scheduled messaging, represents a system to be understood more deeply. In addition to these aspects, other "gray areas" are represented by the impact of personal variables, the characteristics of the course, the time available with respect to the effectiveness of online training.

The tool implements an analysis system that gives the opportunity to understand:

  •  the effective use of a course, to identify not only study styles and preferences, but also the critical areas of the course itself (didactic meta-evaluation);
  •  user behavior in relation to a specific course to evaluate the effectiveness of design and organizational choices;
  •  the most effective teaching solutions, attention to the different types of course, the use of teaching time, the impact of variables external to the courses.

This analysis on the data allows to correlate the different variables present in LMS, overcoming a logic of vertical consultation of the reports in favor of a three-dimensional exploration of the implicit phenomena, to fully understand the value of the teaching experience.

Project aimed at the construction of a system of ADynamic ssessment for the personalization of the evaluation tests.

The project is characterized as a system of adaptive testing oriented to administer complex evaluation tests of a dynamic type capable of adapting the route of administration of the questions based on the result achieved in progress during the test.

During the administration of the questionnaire, it allows to quickly consolidate the results on the areas of greatest competence, and to investigate in greater depth the areas of lesser preparation in order to effectively discriminate the levels of knowledge of the medium and low performer.

Provides a system of back-office for the comparison of the results of the respondents