skip to Main Content

Covalence approach is based on multiple sources of information and relies on web monitoring, artificial intelligence together with human analysis. We oppose ESG data publicly reported by companies (disclosure) to online narrative content reflecting the views of stakeholders such as NGOs and the media (reputation). This approach allows users to track inconsistencies, monitor changes and benefit from timely alternative data. The information is delivered in an actionable format to support ESG risk exposure mitigation and long term value creation.

The data is classified according to 50 Environment, Social, Governance (ESG) criteria inspired by the Global Reporting Initiative’s sustainability reporting guidelines. Due to its high level of granularity it can also be translated into Sustainable Development Goals as well as for thematic and customised approaches.

Integration of ESG indicators disclosed by companies

An increasing number of companies publish ESG indicators on a yearly basis. These indicators are communicated in absolute numbers (eg CO2 emissions in tons), ratios (e.g. % of women on the Board) or in Boolean terms (e.g. existence of a Health and Safety policy in the supply chain: yes / no). Covalence acquires this data from external providers and integrates it into its proprietary ESG scoring system.

Self-reported ESG indicators provide useful knowledge on policies, processes and commitments. They respond to increasing demands for more  transparency in the way a company is making its money. However, the disclosed data is not sufficient to produce a balanced ESG assessment. It is usually highly aggregated, reporting mainly global performance while providing few insights on local practices. It can also be positively biased, celebrating achievements and minimizing problems. The use of additional data from third-party sources is therefore needed to document the perception of stakeholders and shed light on local situations.

Artificial intelligence enabling stakeholder analysis

Stakeholders such as NGOs, governments, trade unions and the media describe the role and activities of companies in positive and negative terms generating either endorsements or controversies. Covalence has specialized since 2001 in the semi-automated analysis of such narrative ESG content. This expertise materialized in the award-winning EthicalQuote reputation index.

We use data gathering and classification tools in order to analyse the narrative content relying on artificial intelligence techniques (machine learning, natural language processing). This process is reinforced by human interventions to classify the content in terms of polarity (positive/negative) and criteria. Our team of analysts thoroughly checks entries proposed by the software, thus ensuring high curation standards. Only sources that are publicly identified and available online are considered.

Today, Covalence database includes more than one million documents from over 50’000 different sources on 3’400 companies that have been classified and curated by more than 600 analysts in collaboration with 30+ universities.

The database leverages the use of machine learning techniques thanks to the expertise of Covalence Scientific Advisor Prof. Patrick Ruch, field expert and professor at the University of Applied Sciences and Arts Western Switzerland.

The use of classification algorithms allows us to fully automatise the collection and pre-classification of information including complex information such as polarity – or sentiment – as well as multiple criteria.

Back To Top