This policy brief shows the first results of the IntelComp platform: the use cases of Energy, as a key element for mitigating climate change, and of science and technology in Artificial Intelligence. They indicate that IntelComp has successfully produced topic models and automatic classifiers to address the granularity challenge.
This document translates the conceptual framework of the IntelComp platform into concrete measurements and data sources. It also explains the services of the platform which are required for the calculation of the identified measurements.
This document provides a first look at the rationale and the potential of using Artificial Intelligence-based tools in Science, Technology and Innovation policy. In addition, this deliverable deals with the challenges these tools face.
This deliverable provides a framework of Science, Technology and Innovation policy for the IntelComp platform, which will be tested in three domains: artificial intelligence, climate change/blue economy and health/cancer.
The Graph Analysis toolbox is a number of software components for the computation, processing and analysis of graph collections.
Although the toolbox can be used generally for any type of data sources, it is specially oriented to the processing and analysis of large corpora of scientific documents.
The key modules of the toolbox are:
- Import data from files or SQL / Neo4J databases, for the generation or the enrichment of graphs.
- Generation and processing of graphs.
- Management and processing structured collections of graphs (named supergraphs)
The IntelComp time analysis and trend detection service focuses on the dynamic analysis of the scientific literature, tracking the evolution of disciplines and capturing the emergent research areas or new topics and quantifying their trends. To this end, we automatically expand the Field of Science Taxonomy exploited by the IntelComp classifiers (documented in Deliverable D3.4) to a more fine-grained level by adding three additional levels (Level 4-Level 6) and provide a dynamic mechanism that properly adjusts the lower levels of the hierarchy as new research topics emerge.
This service is a set of ready-to-use automatic classifiers and a collection of training scripts that can be executed to create classifiers for new taxonomies.
The classifiers have been trained on the following taxonomies: Fields of Science and Technology (FOS); Nomenclature of Economic Activities (NACE) Rev.2; International Patent Classification (IPC); and the Sustainable Development Goals (SDGs).
This document provides information about the python-based Topic Modeling toolbox, one of the main services in IntelComp, including a review of the techniques implemented, the description of the architecture of the software, and manuals for the users of the tool.
The system for subcorpus generation (domain classifier) is aimed at facilitating the classification of all documents from a given corpus according to a category that is specified by the user (an expert in the domain).
The Intelcomp NLP pipeline can be defined as a collection of tools that apply the requested transformations to unstructured textual data, which will be used by the Intelcomp services (document classification, subcorpus generation, topic modeling, etc.) as a preliminary step to process the datasets of interest.
This second monitoring report on the execution of the Communication Plan of the Project describes both the communication and dissemination channels and materials developed. It also takes stock of the specific communication and dissemination actions carried out during the first year of the Project.
This deliverable provides an overview of the activities characterizing data management in the project based on the Horizon 2020 policy and FAIR guidelines. This version of the DMP details the types of datasets collected, generated and used within the project, focusing on re-used datasets, and draws a first picture of how they are expected to be handled by / in the IntelComp STI Data Space.