See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/370073759

A Big Data Analytics-Based Methodology For Social Sustainability Impacts

Evaluation: A Case Study

Article in Procedia Computer Science · April 2023

DOI: 10.1016/j.procs.2023.03.007

CITATION READS

1 226

4 authors:

Lahcen Tamym Lyes Benyoucef

Aix-Marseille Université Aix-Marseille Université
13 PUBLICATIONS 49 CITATIONS 174 PUBLICATIONS 3,560 CITATIONS

SEE PROFILE SEE PROFILE

Ahmed Nait Sidi Moh Driss Moulay El Ouadghiri

Université Jean Monnet - Saint Étienne Université Moulay Ismail
105 PUBLICATIONS 951 CITATIONS 96 PUBLICATIONS 1,021 CITATIONS

SEE PROFILE SEE PROFILE

All content following this page was uploaded by Lahcen Tamym on 18 April 2023.

The user has requested enhancement of the downloaded file.

 Available online at www.sciencedirect.com
Available online at www.sciencedirect.com
Available online at www.sciencedirect.com

ScienceDirect
Procedia Computer Science 00 (2023) 000–000
Procedia
Procedia Computer
Computer Science
Science 00(2023)
220 (2023)32–39
000–000 www.elsevier.com/locate/procedia
www.elsevier.com/locate/procedia

The 14th International Conference on Ambient Systems, Networks and Technologies (ANT)
The 14th International Conference on Ambient
March 15-17, 2023, Systems, Networks and Technologies (ANT)
Leuven, Belgium
March 15-17, 2023, Leuven, Belgium
A
A Big
Big Data
Data Analytics-Based
Analytics-Based Methodology
Methodology For
For Social
Social Sustainability
Sustainability
Impacts
Impacts Evaluation:
Evaluation: A
A Case
Case Study
Study
a,c,∗ a b
Lahcen Tamyma,c,∗,, Lyes
Lahcen Tamym Lyes Benyoucef
Benyoucef a , Ahmed Nait Sidi Mohb , Moulay Driss El
, Ahmed
c Nait Sidi Moh , Moulay Driss El
Ouadghiri
Ouadghiric
a Aix-Marseille University, University of Toulon, CNRS, LIS, Marseille, France
a Aix-Marseille University, University of Toulon, CNRS, LIS, Marseille, France
b Jean Monnet University, Saint Etienne, LASPI, IUT of Roanne, France
b Jean Monnet University, Saint Etienne, LASPI, IUT of Roanne, France
c Moulay Ismail University, IA Laboratory, Meknes, Morocco
c Moulay Ismail University, IA Laboratory, Meknes, Morocco

Abstract
Abstract
Nowadays, Big Data (BD) technology is considered by institutions, enterprises and governments a primary key to addressing
Nowadays, Big Data (BD) technology is considered by institutions, enterprises and governments a primary key to addressing
sustainability challenges. The business ecosystem is becoming more and more complicated, due to large and strong interactions
sustainability challenges. The business ecosystem is becoming more and more complicated, due to large and strong interactions
between the directly involved stakeholders such as suppliers, manufacturers, distributors and customers on one hand, and the indi-
between the directly involved stakeholders such as suppliers, manufacturers, distributors and customers on one hand, and the indi-
rect stakeholders such as the environment and society on the other hand. Thus, moving toward corporate sustainability requires an
rect stakeholders such as the environment and society on the other hand. Thus, moving toward corporate sustainability requires an
accurate understanding of these business partners’ impacts on each other. Indeed, enterprises must incorporate the three sustain-
accurate understanding of these business partners’ impacts on each other. Indeed, enterprises must incorporate the three sustain-
ability dimensions to assess a product, a service, or process performance on environmental, economic, and social aspects. To this
ability dimensions to assess a product, a service, or process performance on environmental, economic, and social aspects. To this
end, this paper presents a big data analytics (BDA) based methodology to analyze the social sustainability impacts of enterprises.
end, this paper presents a big data analytics (BDA) based methodology to analyze the social sustainability impacts of enterprises.
Besides, a real-life case study from the database proposed by the impact-weighted account project (IWAP) team at Harvard busi-
Besides, a real-life case study from the database proposed by the impact-weighted account project (IWAP) team at Harvard busi-
ness school, is used to validate the methodology. The obtained results show the added value of using BDA technology to achieve
ness school, is used to validate the methodology. The obtained results show the added value of using BDA technology to achieve
enterprises’ social Sustainable Development Goals (SDGs) agenda launched by the United Nations.
enterprises’ social Sustainable Development Goals (SDGs) agenda launched by the United Nations.
© 2023
© 2023 The Authors.
Authors. Published by by Elsevier B.V.
B.V.
© 2023 The
The Authors. Published
Published by Elsevier
Elsevier B.V.
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
(https://creativecommons.org/licenses/by-nc-nd/4.0)
This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Peer-review under
under responsibility
responsibilityofofthe
thescientific
Conferencecommittee
Programof Chairs.
the Conference Program Chairs
Peer-review under responsibility of the Conference Program Chairs.
Keywords: Big Data Analytics, Social Sustainability; Sustainable Enterprises; Social Impacts; Sustainable Development Goals.
Keywords: Big Data Analytics, Social Sustainability; Sustainable Enterprises; Social Impacts; Sustainable Development Goals.

1. Introduction
1. Introduction
In the current business, big data (BD) technology has been considered a primary key to dealing with sustainability
In the current business, big data (BD) technology has been considered a primary key to dealing with sustainability
challenges [1]. The business ecosystem is becoming more and more complicated, due to large interactions between
challenges [1]. The business ecosystem is becoming more and more complicated, due to large interactions between
the involved stakeholders such as suppliers, manufacturers, distributors, and customers. As well as the external stake-
the involved stakeholders such as suppliers, manufacturers, distributors, and customers. As well as the external stake-
holders from the environment and society issues. Thus, moving toward corporate sustainability requires an accurate
holders from the environment and society issues. Thus, moving toward corporate sustainability requires an accurate
understanding of these business partners’ impacts on each other. Indeed, enterprises must incorporate the three sus-
understanding of these business partners’ impacts on each other. Indeed, enterprises must incorporate the three sus-

∗ Corresponding author. Tel.: +33-605-676-973.

∗ Corresponding author. Tel.: +33-605-676-973.
E-mail address: lahcen.tamym@lis-lab.fr
E-mail address: lahcen.tamym@lis-lab.fr

1877-0509 © 2023 The Authors. Published by Elsevier B.V.

1877-0509
This © 2023
is an open The Authors.
access Published by Elsevier B.V.
1877-0509
This is an © 2023
open Thearticle
access article
under
Authors.
under
the CC BY-NC-ND
Published
the CC BY-NC-ND
license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
by Elsevier B.V.
license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Peer-review
This underaccess
is an open responsibility of the Conference
article under Program
the CC BY-NC-ND Chairs.
license (https://creativecommons.org/licenses/by-nc-nd/4.0)
Peer-review under responsibility of the Conference Program Chairs.
Peer-review under responsibility of the scientific committee of the Conference Program Chairs
10.1016/j.procs.2023.03.007
 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39 33
2 L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000

tainability dimensions to assess a product, service, or process performance on environmental, economic, and social
aspects [2]. Furthermore, enterprises must undertake social responsibility (SR) as part of their business activities [3].
SR means benefiting society, not just maximizing shareholders’ value. In addition, the enterprises’ investments must
contribute to the benefit of both environment and society.
Consequently, social issues are universal and related to environmental and economic issues. For instance, high cli-
mate exposure will affect natural resources and result in risks associated with climate change, which will significantly
increase crime and conflict, as well as fluctuating socioeconomic conditions [4]. In addition, it will also aggravate
health problems, especially for those already vulnerable, which will put additional stress and disruption on healthcare
due to increased demands. Thus, enterprises must take actions to reduce emissions related to their daily activities.
In today’s dynamically changing business environment, enterprises are aware of the relationship between environ-
mental, social, and economic issues and their roles in business strategy. Thus, solving these conflicted issues requires
new types of business intelligence. Hence, in order to generate valuable business information, the ability to extract
data from reliable sources is nowadays the most considerable factor in gaining a competitive advantage [5]. Further-
more, big data analytics (BDA) technology enables enterprises to provide quality data in the right format by using
sophisticated business analytics tools, to offer intriguing solutions that can guide enterprises’ sustainability perfor-
mance and their sustainable supply chains (SC). For instance, it enables tracking which enterprises might be linked to
local pollution, human rights abuses, or child labor, to name a few. In addition, it can be used to predict and prevent
risks, and develop innovative skills [6]. Moreover, in terms of social issues, BDA plays a vital role in transparency
and social development [7]. This can be done only if the best actions are taken by stakeholders including enterprise
managers and decision-makers, academic researchers, or policy-makers.
Nevertheless, investigating the benefits of BDA technology in achieving corporate sustainability or sustainabil-
ity analysis (SA) is still in its early stage. The United Nations developed the called ’sustainable development goals
(SDGs)’ agenda in 2015, which aims to bring all society stakeholders together to address social, environmental, and
economic issues [8]. Moreover, there is little understanding of how effectively and efficiently leverage BDA technol-
ogy to address social sustainability issues. In addition, enterprises still don’t use the new BD ecosystem in ways that
benefit people, with a particular focus on society’s most vulnerable citizens.
Hence, examining the potential of leveraging BDA technology in analyzing sustainable enterprises’ impacts on
society, we conduct our research work on corporate environmental impact (CEI), which is a database proposed by
the impact-weighted account project (IWAP) team at Harvard business school [9]. The team of this project devel-
oped a methodology to calculate monetized measures of environmental impacts from operations of different types
of enterprises. Performing these calculations, several established academic database resources have been used (i.e.,
Bloomberg and Thomson Reuters (ASSET4), Exiobase, Environmental Priority Strategies (EPS), AWARE Model,
Waterfund’s Global Water Price, Accounting, and Stock Market Data). These measurements are the impacts on ”safe-
guard subjects” which are the critical resources for human health and well-being [10]. The resources concerned by
their calculation methodology are human health (working capacity (WC)), crop production capacity (CropPC), meat
production capacity (MeatPC), fish production capacity (FishPC), wood production capacity (WoodPC), drinking
water and irrigation water (water production capacity (WaterPCDI)), abiotic resources, and biodiversity. Moreover,
measurements of the emissions’ impacts in terms of United Nations SDGs by mapping each emission’s characteriza-
tion pathways to 17 relevant SDG targets were calculated in this database.
To this end, this paper presents a BDA-based methodology to analyze the social sustainability impacts of en-
terprises. The rest of the paper is organized as follows: Section 2 reviews some BDA applications on sustainable
enterprises’ impacts on society. The proposed BDA-based methodology to analyze social issues, as well as, the case
study definition, are presented in Section 3. Section 4 discusses the obtained numerical results. Finally, Section 5
concludes the paper with some challenges and future work outlines.
2. Literature Review
A large number of existing studies in the broader literature have examined the sustainability issues of enterprises and
their supply chains (SCs). Most of these studies covered how BD technology contributes to enabling enterprises to
achieve sustainable development and gain competitive advantages in hotly competitive and dynamic markets. This
section reviews the recent contributions of BDA to making enterprises socially sustainable and responsible.
34 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39
L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000 3

2.1. Big Data and Big Data Analytics

There exist several definitions of BD in the literature. For instance, BD is large amounts of unstructured and semi-
structured data that businesses may create or data that would take too much time, effort, and money to put into a
relational database for analysis [11]. Furthermore, BD has been characterized by five ’Vs’ that distinguish it from
traditional data. 1) Volume means the significant and exponential increase of BD quantities. 2) Velocity refers to the
speed of collecting, processing, and analyzing data in real, or near real-time. 3) Variety means that the data collected in
BD contexts could be in structured, semi-structured, or unstructured formats. 4) Veracity refers to the trustworthiness
of data sources. 5) Value is the most important characteristic because regardless of BD volume usually it’s not useful
to be valuable. Thus it’s required to convert them into insights to add value to the decision-making process [12].
BDA technology has long been regarded as the primary instrument for processing and analyzing large volumes
of data to derive useful insights and assure the reliability of BD sources. Moreover, BDA has been considered the
”fourth paradigm of science,” a ”new paradigm of knowledge assets,” or ”the next frontier for innovation, compet-
itiveness, and production.” Enterprises are now conscious that employing BDA tools to grasp and understand their
BD would help them stay competitive in the global market. BDA is an emerging technology that enables enterprises
with the management, processing, and analysis of the BD five Vs [13, 11]. It will also allow them to better adapt to
the present fast-paced and constantly changing market environment. Moreover, it will also enable them to generate
relevant ideas for creating long-term value, monitor performance, and develop competitive advantages [14]. BDA ap-
plications provide several benefits in SC management, including lower operating costs, more SC agility, and higher
customer satisfaction [15]. Last but not least, BDA improves data-driven decision-making and develops new methods
to boost corporate efficiency and effectiveness. BDA’s goal is to shake up traditional analysis by enabling agility in
understanding and addressing issues by processing heterogeneous data simultaneously and in real-time processing
and analytics. Finally, machine learning and deep learning technologies, for example, may be used to this end [1]. It’s
worth mentioning that business intelligence (BI) techniques, such as data visualization and sophisticated analytical
approaches like data mining (DM), may be used.
2.2. Big Data Analytics and Sustainable Development
Literature review shows that sustainability and BDA are two buzzwords in the recent business analytics domain.
Indeed, several recent studies have been performed to promote the sustainability of enterprises and their SCs [16].
Enterprises are aware of using BDA technology to streamline their operations and manage their SCs thanks to its
ability to derive insights from raw data. This will enable them to create green goods or provide sustainable services.
Moreover, according to [17], BDA techniques greatly advance economic, environmental, social and ethical, legal, and
political benefits. SA is the realization of corporate sustainability and the integration of SR into the business using
BDA [3, 18]. As a result, enterprises currently can use the most sophisticated BDA tools and techniques to collect and
perform real-time (or near real-time) analysis on massive data that are related to determining sustainability factors,
such as energy and resource use, greenhouse gas emissions, and logistics performances, to name a few. Then, they
generate the necessary insights to guide their sustainability-related initiatives and improve overall resource efficiency.
This scenario analysis will enable them to maintain the linkages between the three pillars of sustainability which
are economic, social, and environmental elements. Accordingly, maintaining the intersections between these three
elements will influence their future sustainable development strategy and performance, positively. In addition, given
the possibilities and opportunities which BD brings to society and business, the United Nations launched in 2017 the
BDA for sustainability plan to help achieve the 17 SDGs [19, 8].
2.3. Big Data Analytics Applications for Social Impacts
Environmental sustainability conserves natural resources and protects global ecosystems including health, well-being,
and environmentally friendly. Indeed, in addition to environmental concerns, several studies suggest that enterprises
must be aware of the interest in considering social sustainability, or SR, due to their huge influence on the whole of
society. To this end, in the current business, sustainable enterprises contribute to promoting the living standards of
societies, improving working conditions, reducing waste, and using resources effectively. Obviously, many cultures
have social difficulties, such as gender equality, child labor, starvation, and working conditions, to name a few [20].
In this regard, there exist some social enterprises in rural regions which started to integrate social sustainability into
their sustainable business models [21]. This enables them to expand their value generation to cover the environment
 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39 35
4 L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000

and society members, calculate their business impacts, and meet the ”base of the pyramid” and low-income groups,
which are often excluded from particular forms of consumption due to price barriers or the nonexistence of markets
for these groups [22]. In doing so, these enterprises offer social services, provide common goods, deliver programs to
educate people, and offer job opportunities.
Therefore, considered as the most powerful tool in current business analytics, BDA has received great attention
lately thanks to its ability to give purpose to data and extract valuable information. Additionally, this will help sustain-
able enterprise managers to drive the best decision-making and increase their performances by influencing individuals,
businesses, and governments that are different members of society [23]. To this end, a large number of existing studies
in the broader literature have examined the role of BDA in promoting social sustainability. For instance, [24] argued
that sentiment analysis generates information on corporate SR or human rights in the SC networks and logistics fields.
Besides, a recent study [25] concluded that healthcare BD analysis allows the best predictions on the future health
conditions that enterprises can benefit from to improve their employees’ health conditions. Furthermore, extensive
literature has discussed how climate change risks impact social sustainability and the role of BDA in addressing these
risks. Thus, [26] showed that climate change is the most pressing concern in food SC safety, such as changes in arable
land, crop yields and soil quality changes, livestock production, growth of mycotoxins, residues of pesticides, and
pathogens. In addition, the study demonstrated how BDA and web-based decision support systems contribute to im-
proving food safety and securing food SC from farm to consumer. Indeed, enterprises in this regard have to take into
consideration sustainable consumption and production concepts [27]. This can be done using BDA to meet the basic
needs of social entities, minimize the use of natural resources, toxic materials, and emissions and wastes, improve life
quality and ensure economic growth.
From the above literature review, we can conclude that sustainability and BDA are two keywords that we hear
all the time. In fact, many methodological innovations were proposed, nevertheless, a few of them have considered
the intersections between the three sustainability dimensions. Moreover, addressing sustainability challenges with the
efficient use of BDA technologies is seen as a promising topic with several real-life applications, such as engineering,
design, manufacturing, and commerce and consumption.
3. Big Data Analytics-Based Methodology
In this section, a BDA-based methodology is presented in order to drive enterprises’ social sustainability using a real
database. These enterprises are operating in different sectors to achieve sustainable development. In this regard, a depth
analysis is performed to show how the impacts that different enterprises exercise on the economy and environment
will affect society.
3.1. Case Study: Corporate Environmental Impact
CEI is a dataset created by the IWAP team at Harvard business school [9]. The team of this project developed a
methodology to calculate monetized measures of environmental impacts from operations of different types of enter-
prises. Performing these calculations, several established academic database resources have been used (i.e., Bloomberg
and Thomson Reuters (ASSET4), Exiobase, Environmental Priority Strategies (EPS), AWARE Model, Waterfund’s
Global Water Price, Accounting, and Stock Market Data). These measurements are the impacts on ”safeguard sub-
jects”, which are the most critical resources for human health and well-being [10]. The resources concerned by the
calculation are human health (i.e., working capacity), CropPC, MeatPC, FishPC, WoodPC, WaterPCDI, abiotic re-
sources, and biodiversity. Moreover, they used characterization pathways, safeguard subjects, and monetary conver-
sion factors from the EPS database [28] to measure the emissions’ impacts in terms of United Nations SDGs, by
mapping each emission’s characterization pathways to 17 relevant SDG targets.
Therefore, the measurements concerned by the IWAP show the performances of their methodology. Indeed, they
illustrate how various environmental impacts can be calculated and integrated into the decision-making process, man-
agement of risks, returns, and impacts, and more efficient and sustainable resource allocation. In doing so, they are able
to calculate the total environmental cost impact for over 2500 organizations with data going back to 2010, broken out
by the safeguard subjects. Besides, comparing organizations of different sizes, which would reasonably be expected to
have different absolute environmental impacts, the total organizational environmental impacts as a percentage of sales
and operating income defined as environmental intensity are calculated. This allows them to estimate environmental
damage per sales unit or operating income. Within their methodology, they considered the default discount rate of 0%
36 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39
L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000 5

Table 1. Sample Statistics

Summary TEC WC FishPC CropPC MeatPC WaterPCDI
Count 4136 4136 4136 4136 4136 4136
Mean -1.4982091721253982E9 -1.003855213736829E9 -310086.93672090216 -1.245727332024189E7 -2789551.3537682267 -4.654193526752256E8
Stddev 6.000031193808253E9 2.8991938047007713E9 824189.7063848815 3.450446119883396E7 7761911.215669795 4.810333329461172E9
Min -1.36228944661009E11 -3.30592624219893E10 -7958361.29063824 -3.48480714585937E8 -7.78934932986797E7 -1.30597121892545E11
Max 1.57277465251449E10 3.86720080034559E9 155444.919188825 1.08174513802071E8 2.32701455270569E7 2.11511873032397E10
SDG1 SDG2 SDG3 SDG4 SDG5 SDG6 SDG8
4136 4136 4136 4136 4136 4136 4136
-4.015290996439707E8 -2.659472157266567E8 -2.6562817032300606E8 -3114306.6953909346 -3114365.0299417847 -4.332214437519523E7 -5014844.605026698
1.1155910922003942E9 7.024183833706778E8 7.01636079155351E8 8626086.788805913 8626193.61239161 1.140725920022496E8 6.118088521736656E7
-1.11702004162576E10 -6.85387387240512E9 -6.84788779515546E9 -8.71201786464842E7 -8.71201786464842E7 -1.12053698691694E9 -1.37263909821984E9
3.26504894592947E9 2.87052319292295E8 2.8697818801901E8 2.70439238308939E7 2.70396385538954E7 4.5485275113638E7 0.0

Table 2. SDGs definitions forms [9]

SDG Definition
SDG1 By 2030, builds the resilience of the poor and those in vulnerable situations and reduces their exposure and vul-
nerability to climate-related extreme events and other economic, social, and environmental shocks and disasters.
SDG2 By 2030, ends hunger and ensures access by all people, particularly the poor and people in vulnerable situations,
including infants, to safe, nutritious, and sufficient food all year round.
SDG3 By 2030, ends all forms of malnutrition, including achieving, by 2025, the internationally agreed targets on stunting
and wasting in children under five years of age, and addresses the nutritional needs of adolescent girls, pregnant
and lactating women, and older persons.
SDG4 By 2030, doubles the agricultural productivity and incomes of small-scale food producers, in particular women,
indigenous peoples, family farmers, pastoralists, and fishers, including through secure and equal access to land,
other productive resources, and inputs, knowledge, financial services, markets and opportunities for value addition
and non-farm employment.
SDG5 By 2030, ensures sustainable food production systems and implements resilient agricultural practices that increase
productivity and production, help maintain ecosystems, strengthen capacity for adaptation to climate change, ex-
treme weather, drought, flooding, and other disasters, and progressively improve land and soil quality.
SDG6 By 2030, ends the epidemics of AIDS, tuberculosis, malaria, and neglected tropical diseases and combat hepatitis,
water-borne diseases, and other communicable diseases.
SDG8 By 2030, substantially reduces the number of deaths and illnesses from hazardous chemicals and air, water, and
soil pollution and contamination.
given the consideration for inter-generational equity, but also they conducted a sensitivity analysis of this assumption
by using a 3% discount rate.
3.2. Sample Selection
By using the IWAP database, we conduct our research work on the social impacts that enterprises from different
activity sectors have on society. To this end, a sample of 714 enterprises from 10 activity sectors located in 59 countries
around the world is selected. This selection is performed using the total environmental cost (TEC) of each activity
sector. Besides, the correlations between variables within the database have been studied in order to select the variables
that have high correlations between them. The statistics on each variable are shown in table 1, where: ’count’ is the
number of observations, ’Mean’ is the arithmetic average of each variable, ’Stddev’ is the standard deviation to
measure spread, and variation of values in each variable, and ’(Min, Max)’ are the minimum and maximum values
respectively of each variable. Hence, a high and significant relationship is found indicating that the impact on FishPC,
CropPC, MeatPC, and WaterPCDI which are critical resources for human-being are highly related to social SDGs
defined in the table 2.
3.3. Big Data Analytics-based Methodology
In this study, Apache Spark (AS) methodology is used due to its advanced execution engine that supports acyclic data
flow and in-memory computing. As well as, it uses Resilient Data Dataset (RDD) as a fundamentally different data
structure abstraction for distributed collection of data objects that may be operated on different nodes of the cluster
in a parallel manner. This gives AS a better computational efficiency than Hadoop MapReduce operations [29]. AS
supports interactivity with Scala, Python, and R shells programming languages. Furthermore, AS enables the use
of MLlib, which is a powerful tool for building machine-learning applications. The framework shown in figure 1
illustrates the use of AS ecosystem within the developed BDA-based methodology.
 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39 37
6 L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000

Fig. 1. Apache spark methodology for social sustainability analytics

4. Results and Discussions

The above short review demonstrates that environmental impact is highly related to social impact. Thus, from their
daily operations and activities, enterprises are exercising huge impacts on the environment. These enterprises belong
to different activity sectors and have different sizes. Within the chosen sample of this study, the total values of TEC
that each sector has on the environment are calculated. In our case, the TEC of each sector is the total monetized
environmental impact from its operations during a specific year (from 2010 to 2019), as shown in figure 2. The figure
shows that the production of electricity and petroleum refinery sectors have the most damage to the environment
in terms of environmental impact monetization. This will lead the two activity sectors to have a highly significant
impact on society. For instance, the results of the performed analysis highlight that increasing environmental damage
intensifies the loss of WC for vulnerable occupations and affects individual labor decisions.

Fig. 2. TEC of each sector

38 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39
L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000 7

Table 3. Multiple regression linear model measures on the predicted social SDGs

R2 MSE maxIter
R2 MSE maxIter
SDG1 0.99996 2.39039e + 06 20
SDG5 0.993932 605538 20
SDG2 0.991115 6.22115e + 07 20
SDG6 0.993698 1.01905e + 07 20
SDG3 0.995059 4.92021e + 07 20
SDG8 0.999966 462468 20
SDG4 0.988784 831817 20

Therefore, our study shows how these enterprises are thinking to be transparent in terms of social impacts, as
well as, how they plan to achieve the social SDGs agenda by 2030. According to the IWAP team, there are some
enterprises that are working collaboratively to achieve SDGs. In addition, enterprises are aware of the importance of
collaboration. Thus, they share creativity, information, actions, resources, risks, duties, and rewards to address urgent
societal challenges [13], even if they belong to different sectors or have different identities. In our case, a prediction
model is built based on TEC and the safeguard subjects in the selected sample to predict the monetization impacts of
the chosen social SDGs. In doing so, multiple regression linear model since the variables in the selected sample are
linearly correlated. Hence, in each case, we consider the target (independent variable (Y)) to be predicted as one of the
SDGs and the features as TEC and the safeguard subjects (dependent variables). Accordingly, to evaluate the model
performances, two metrics are used:
• Mean Squared Error (MSE): it minimizes the loss function between the target value yi and the predicted value
ŷi given by: n
1
MS E = (yi − ŷ)2
n i=1
• R2 : it measures the validity of the regression model given by:
n
(yi − ŷi )2
R = 1 − i=1
2
n 2
i=1 (yi − ȳ)

where ŷi is the estimated value of the independent value for the ith observation by the regression model, and ȳ is the
mean of all observations of the independent variable.
After evaluating the model on each selected SDGs, table 3 shows the obtained performances. The model gives the
best results in terms of prediction accuracy on validation data for all the selected social SDGs. These best results can
be explained as follows:
• the measurements of impact monetization provided by the IWAP are highly accurate and the adopted calculation
methodology is efficient;
• in the proposed database some enterprises are working collaboratively to achieve SDGs agenda;
• the impact on the environment which in its turn influences significantly the safeguard of subjects that are critical
to human well-being and to the prosperity of societies will trigger many social issues.
Thus, there is a high correlation between all these variables, which enables to have good results in terms of social
SDGs predictions.
5. Conclusion and Future Research Directions
In summary, the methodology presented in this paper investigates the potential of BDA technology in achieving
corporate sustainability or sustainability analysis, especially social sustainability. In this regard, this may be considered
as a promising aspect for enterprises to rethink how they design their business model, by integrating social and
environmental stakeholders. Moreover, it will enable them to create economic, environmental, and social sustainable
value in order to gain competitive advantages in the current highly vulnerable markets. Thus, BDA has the ability to
generate valuable business insights that will help sustainable enterprises to achieve SDGs agenda by 2030, launched
by the United Nations. In addition, a real case study was presented in this study based on the corporate environmental
impact database from the impact-weighted account project at Harvard business school. The reason behind using this
database is that social impacts are hard to measure. Thus, the database provides monetization impacts of enterprises’
 Lahcen Tamym et al. / Procedia Computer Science 220 (2023) 32–39 39
8 L. Tamym et al. / Procedia Computer Science 00 (2023) 000–000

social impacts. The output of the present study confirmed that BDA can significantly help enterprises of different sizes
and activity sectors to achieve social sustainability and social responsibility.
Finally, this study focused on some selected social issues concerned by some activity sectors. Hence, as perspec-
tives, we expect to expand the presented BDA-based methodology to include other tools and techniques, as well as,
address other social issues in the analysis process.
References
[1] Tamym, L., Benyoucef, L., Nait Sidi Moh, A., El Ouadghiri, M.D.. “Towards Big Data-based Sustainable Business Models and Sustainable
Supply Chain”. In: Emerging Trends in Intelligent Systems & Network Security. Springer International Publishing; 2023, p. 464–474.
[2] Hermundsdottir, F., Aspelund, A.. “Sustainability innovations and firm competitiveness: A review”. Journal of Cleaner Production 2021;280.
[3] Martin, J., Petty, W., Wallace, J.. “Shareholder Value Maximization-Is There a Role for Corporate Social Responsibility?” Journal of Applied
Corporate Finance 2009;21:110–118.
[4] Carter, J.G., Cavan, G., Connelly, A., Guy, S., Handley, J., Kazmierczak, A.. “Climate change and the city: Building capacity for urban
adaptation”. Progress in Planning 2015;95:1–66.
[5] Bahrami, M., Shokouhyar, S., Seifian, A.. “Big data analytics capability and supply chain performance: the mediating roles of supply chain
resilience and innovation”. Modern Supply Chain Research and Applications 2022;.
[6] Maheshwari, S., Gautam, P., Jaggi, C.K.. “Role of Big Data Analytics in supply chain management: current trends and future perspectives”.
International Journal of Production Research 2021;59(6):1875–1900.
[7] Cuquet, M., Vega-gorgojo, G., Lammerant, H., Finn, R., ul Hassan, U.. “Societal impacts of big data: challenges and opportunities in
Europe” 2017;.
[8] United Nations, .. “Transforming our world: the 2030 Agenda for Sustainable Development”. 2015. URL: https://sdgs.un.org/
2030agenda; accessed 20 Sept 2022.
[9] Serafeim, G., Park, D., Freiberg, D., Zochowski, R.. “Corporate Environmental Impact: Measurement, Data and Information”. Harvard
Business School Working Paper 2020;(20-098).
[10] Bengt, S., Sara, P.. “A selection of safeguard subjects and state indicators for sustainability assessments”. The International Journal of Life
Cycle Assessment 2016;21.
[11] Fosso Wamba, S., Akter, S., Edwards, A., Chopin, G., Gnanzou, D.. “How ’big data’ can make big impact: Findings from a systematic
review and a longitudinal case study”. International Journal of Production Economics 2015;165:234–246.
[12] Akter, S., Fosso Wamba, S., Gunasekaran, A., Dubey, R., Childe, S.. “How to improve firm performance using big data analytics capability
and business strategy alignment?” International Journal of Production Economics 2016;182:113–131.
[13] Tamym, L., Benyoucef, L., Nait Sidi Moh, A., El Ouadghiri, M.D.. “A big data based architecture for collaborative networks: Supply chains
mixed-network”. Computer Communications 2021;175:102–111.
[14] Wamba, S.F., Gunasekaran, A., Akter, S., fan Ren, S.J., Dubey, R., Childe, S.J.. “Big data analytics and firm performance: Effects of
dynamic capabilities”. Journal of Business Research 2017;70:356–365.
[15] Nguyen, T., Zhou, L., Spiegler, V., Ieromonachou, P., Lin, Y.. “Big data analytics in supply chain management: A state-of-the-art literature
review”. Computers & Operations Research 2018;98:254–264.
[16] Lv, Z., Iqbal, R., Chang, V.. “Big data analytics for sustainability”. Future Generation Computer Systems 2018;86:1238–1241.
[17] Cuquet, M., Fensel, A.. “The societal impact of big data: A research roadmap for Europe”. Technology in Society 2018;54:74–86.
[18] Deloitte, . “Sustainability Analytics, the three-minute guide”. Tech. Rep.; Deloitte Development LLC; 2012.
[19] Zhang, D., Pan, S.L., Yu, J., Liu, W.. “Orchestrating big data analytics capability for sustainability: A study of air pollution management in
China”. Information & Management 2019;:103231.
[20] United Nations, . “Gender equality and sustainable development”. Tech. Rep.; The Research and Data section of UN Women; 2014.
[21] Richter, R.. “Rural social enterprises as embedded intermediaries: The innovative power of connecting rural communities with supra-regional
networks”. Journal of Rural Studies 2019;70:179–187.
[22] Evans Steveand Fernando, L., Yang, M.. “Sustainable Value Creation From Concept Towards Implementation”. In: Sustainable Manufactur-
ing: Challenges, Solutions and Implementation Perspectives. 2017, p. 203–220.
[23] Chen, H., Chiang, R.H.L., Storey, V.C.. “Business Intelligence and Analytics: From Big Data to Big Impact”. MIS Quarterly 2012;36(4).
[24] Jeble, S., Dubey, R., Childe, S., Papadopoulos, T., Roubaud, D., Prakash, A.. “Impact of big data & predictive analytics capability on
supply chain sustainability”. The International Journal of Logistics Management 2018;29.
[25] Batko, K., Andrzej, . “The use of Big Data Analytics in healthcare”. Journal of Big Data 2022;9.
[26] Talari, G., Cummins, E., McNamara, C., O’Brien, J.. “State of the art review of Big Data and web-based Decision Support Systems (DSS)
for food safety risk assessment with respect to climate change”. Trends in Food Science & Technology 2022;126:192–204.
[27] Dubey, R., Gunasekaran, A., Childe, S.J., Papadopoulos, T., Wamba, S.F., Song, M.. “Towards a theory of sustainable consumption and
production: Constructs and measurement”. Resources, Conservation and Recycling 2016;106:78–89.
[28] Steen, B.. A systematic approach to environmental priority strategies in product development (eps). version 2000–general system characteris-
tics. Gothenburg Centre Environ Assess Prod Material Syst 1999;.
[29] Gupta, A., Deokar, A., Iyer, L., Sharda, R., Schrader, D.. “Big Data & Analytics for Societal Impact: Recent Research and Trends”.
Information Systems Frontiers 2018;20:1–10.

View publication stats