Evaluating Environmental, Social, and Governance (ESG) from a Systemic Perspective: An Analysis Supported by Natural Language Processing

The contemporary world scenario demands initiatives to address current societal challenges. Among them, the Environmental, Social, and Governance (ESG) criteria have received prominent attention. Traditionally, ESG is adopted to handle investments. 

Therefore, by adopting interdisciplinary and integrative approaches, ESG has the potential to bring insights, measurements, understandings, and evaluations on how companies and their economic processes affect society in several layers, from a local to regional and global view. 

This study presents a comprehensive analysis of 55,000 publications supported by Natural Language Processing (NLP) techniques on the aspects of ESG-related topics from a systemic standpoint. The adopted methodology is summarized in Fig.1.

Fig.1. Data flow steps, composed of data collection, preprocessing, modeling, analysis, and visualization.

The ESG theme has been studied extensively, following a linear trend (Squared error, r²: 0.992 and Pearson’s coefficient: 0.996). However, even with this increasing attention, it is essential to remark that there are challenges to data availability that conducts a non-balanced context between Environmental, Social, and Governance aspects, as presented in Figs. 2, 3 and 4 (in which the red bars on the left (from zero to -n) represent those categories with a negative perception. Meanwhile, the blue bars on the right side (from zero to +n) represent the categories with a positive perception).

Fig.2. Perception of publications concerning E-related categories.

Concerning the E criteria (Fig.2), besides the increasing initiatives related to energy management and ghg emissions, there are several challenges to overcome, for example, the lack of investments, regulation, and inspection in most countries, especially in developing economies.  It is especially visible when referring to core categories, such as water and wastewater management (WHO and UNICEF, 2021).

 If individuals have no access to adequate water and sanitation services, how can they set ambitious goals for other categories? How is it possible to find balance in the face of such contrasts? What is the role of organizations and stakeholders in front of it?

Fig.3. Perception of publications concerning S-related categories.

In the S context (Fig.3), labor practices and employee health and safety issues were found. It may result in violations of fundamental human rights, freedom of association, and a safe, physical and mental environment. Prior studies have shown that providing a psychologically safe environment is critical to promote collaborative and co-responsibility attitudes.

It further enables employees to express themselves, especially regarding their feelings and concerns, as well as exchange experiences and knowledge (DeMarco and Lister, 2013; Edmondson, 2018; Newman et al., 2015; Perazzoli et al., 2022c). Consequently, the negative perception of these criteria is basically related to violating such standards and regulations (Crête, 2016; Fiaschi et al., 2020; He et al., 2022; Utz, 2019). 

The persistence of business-related infringements and abuses should be a subject of priority concern and urgent attention. Solely, voluntary disclosure approaches are not enough. Despite the advances in mandatory standards, the last decades’ experience has demonstrated that just legal measures, without awareness, are insufficient to ensure respect for fundamental rights (European Commission, 2022a; United Nations, 2021). Such observations bring us to the core of decision-making: Governance

Fig.4. Perception of publications concerning G-related categories.

With respect to G (Fig.4), business ethics has demonstrated failure, meaning problems with moral norms, accountability, transparency, justice, and rights. When ethical attributes are ignored in charge of certain advantages. It may lead to detrimental circumstances, including fraud, corruption, bribery, facilitation payments, misrepresentation, bias, negligence, the spread of misinformation, violation of human rights, among others.

Just to name a few examples, the Bhopal gas tragedy (1984) in India, the Exxon Valdez oil spill disaster (1989), the Enron scandal (2001), the Volkswagen emissions scandal (2015), the Facebook-Cambridge Analytica data breach (2018), and the Brumadinho dam disaster (2019) provides us lessons about the diversity of and potential ethical consequences associated with such practices (Crête, 2016; Sehnem et al., 2020; Tayşir and Pazarcık, 2013; Utz, 2019; Wilson, 2019).

Given the potentially deleterious consequences of such behaviors and aiming to avoid a systemic collapse, it is crucial not just the establishment of good ethical standards through a formal code of ethics, credos, ethical values statement, and/or codes of conduct (Ki et al., 2012; Lee et al., 2014). But also their incorporation into the daily practices, both at the individual and organizational level. Furthermore, societal challenges will only be successfully addressed when ethical foundations are placed at the base of decision-making processes (Armstrong, 2020; Dyck and Manchanda, 2021; Ferrell, 2021; Konadu et al., 2022).

Furthermore, by adopting the General System Theory, it is possible to characterize ESG in terms of its connected parts, interaction with external medium, equifinality, feedback, and anamorphism. Such analysis brings valuable information, serving as a support tool in decision-making processes involving ESG, thus, promoting a more sustainable society and world.

If you are interested in more details, check here:

– Paper: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4244534
– Dataset: https://zenodo.org/record/6981641#.Y0UQG3UzZH4

Keywords: ESG, Data analytics, Natural Language Processing, Systemic View, Sustainability, Transdisciplinarity.

Cite as:

Perazzoli, S., Joshi, A., Ajayan, S., de Santana Neto, J.P. (2022) Evaluating Environmental, Social, and Governance (ESG) from a Systemic Perspective: An Analysis Supported by Natural Language Processing. SSRN ejournal, https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4244534

Perazzoli, S., Joshi, A., Ajayan, S., de Santana Neto, J.P. (2022). Evaluating Environmental, Social, and Governance (ESG) from a Systemic Perspective – Dataset (1.0). Zenodo. https://doi.org/10.5281/zenodo.6981641

Do you want to know more details and enjoy this novelty? Contact us.

Deixe um comentário

O seu endereço de e-mail não será publicado. Campos obrigatórios são marcados com *