=Paper=
{{Paper
|id=Vol-3878/68_main_long
|storemode=property
|title=Understanding the Future Green Workforce through a Corpus of Curricula Vitae from Recent Graduates
|pdfUrl=https://ceur-ws.org/Vol-3878/68_main_long.pdf
|volume=Vol-3878
|authors=Francesca Nannetti,Matteo Di Cristofaro
|dblpUrl=https://dblp.org/rec/conf/clic-it/NannettiC24
}}
==Understanding the Future Green Workforce through a Corpus of Curricula Vitae from Recent Graduates==
https://ceur-ws.org/Vol-3878/68_main_long.pdf
Understanding the Future Green Workforce through a
Corpus of Curricula Vitae from Recent Graduates
Francesca Nannetti2, Matteo Di Cristofaro1
1
Department of Studies on Language and Culture, University of Modena and Reggio Emilia, 41121, Italy, IT
2
Marco Biagi Department of Economics, University of Modena and Reggio Emilia, 41121, Italy, IT
Abstract
In view of the much-heralded ecological transition, to stay competitive and participate in the
collective effort to face global warming and climate change, organisations need to select employees
interested in and able to develop environmentally sustainable and innovative ideas. The existing
literature however does not present consistent nor concordant results on the effective interest,
involvement and expertise of Generation Z members – namely, the newest entrants into the
workforce – in green issues. This study presents a corpus-assisted methodology to explore the profile
of the upcoming workforce expected to present itself to companies. With CVs as one of the first
interfaces between candidate and company in the recruitment process, a purpose-built corpus
consisting of Curricula Vitae from recent graduates of the University of Modena and Reggio Emilia
was collected. Data is investigated through a Corpus-Assisted Discourse Studies (CADS) framework,
proposing a novel interaction between structured metadata and textual information. The original
contribution of this approach lies in the extraction of information from the narrative structure of CVs
which, guiding the evaluation and exploration of metadata, ensures that the knowledge value of the
data can be explored in a discursive manner and not reduced to lists of competences and
qualifications.
Keywords
Corpus-Assisted Discourse Studies, Corpus Linguistics, Curriculum Vitae, Green Workforce1
1. Introduction competitive and participate in the collective effort to
face global warming and climate change, organisations
The pursuit of environmentally sustainable growth is need to attract, identify, select and attempt to retain
now more prominently featured on the global policy individuals interested in and able to develop green and
agenda than ever before [1], and the efforts to fight innovative solutions [5]. Even though by 2025 27% of the
climate change and to support transition towards low or workforce will be comprised of individuals from
net-zero carbon energy systems have manifested over Generation Z [6] - namely, those born roughly between
the last decade through the increasing release of the mid-1990s and the early 2010s –, and despite the
international agreements and strategies striving for a growing body of research on this topic [7], the existing
more sustainable future [2]. literature does not present consistent nor concordant
Achieving a successful transition to a more results on the effective interest, involvement and
sustainable economy, however, requires not only expertise of Generation Z in sustainable and
government intervention policies, but also a new environmental issues [8, 9]. Therefore, this study
generation workforce [3] that should be composed of proposes a corpus-assisted methodology to explore the
individuals able to deal with complex issues and Gen Z members’ profile as the newest entrants into the
ambiguous situations associated with sustainable workforce, particularly considering the need for a large
development in unpredictable and often rapidly and well-qualified workforce to effectively manage the
changing circumstances [4]. Consequently, to stay ecological transition. Given the crucial role played by
CLiC-it 2024: Tenth Italian Conference on Computational Linguistics, 0000-0001-7027-2894 (M. Di Cristofaro); 0009-0005-9197-869X (F.
Dec 04 — 06, 2024, Pisa, Italy Nannetti)
© 2024 Copyright for this paper by its authors. Use permitted under
matteo.dicristofaro@unimore.it (M. Di Cristofaro); Creative Commons License Attribution 4.0 International (CC BY 4.0).
francesca.nannetti@unimore.it (F. Nannetti)
CEUR
ceur-ws.org
Workshop ISSN 1613-0073
Proceedings
universities in educating and shaping the next applicants’ qualifications and experiences are acquired
generation of professionals [10], a sample of recent over time, their personal, educational and employment
graduate (2022-2023) has been identified as consistent histories are typically presented as a sequential
and representative. Moreover, since in the very early progression over time. Interestingly, the author argues
stages of the selection process screening applicants’ that this “introduces into the CV a temporal dimension
Curricula Vitae (CVs) is a widely used recruitment that suggests a narrative” [21]. Consequently, the
practice to shortlist the best candidates [11], CVs structure of a CV is designed to convey this narrative
constitute the first documented interface between dimension through the co-presence of metadata with
people and companies. biographical information and free fields that give the
Hence, this research is based on a purpose-built candidates the opportunity to express themselves and
corpus [12] consisting of 8,096 Curricula Vitae from reflect on their path. Moreover, [22] suggests that
students who received a certified title at the University writing a CV implies becoming involved in acts of
of Modena and Reggio Emilia during the 2022/2023 engagement and alignment to a specific landscape of
academic year, collected from the AlmaLaurea database. practice.
AlmaLaurea is an interuniversity Consortium Precisely with the aim of enabling a discursive
representing 82 Italian universities, aimed at facilitating perspective on a corpus of CVs, it was essential to
graduates’ access to the job market by helping them to imagine a data structure that would make them readable
connect with companies. In this regard, one of the main by linguistic tools.
services is the database of students’ Curricula Vitae.
Data is investigated through a Corpus-Assisted 3. Methodology
Discourse Studies (CADS) framework - that “set of
studies into the form and/or function of language as As mentioned, the corpus for this study was built from
communicative discourse which incorporate the use of the AlmaLaurea CVs’ database, which serves as the only
computerised corpora in their analyses” [13] - serving a CV form certified by Italian universities. As such it was
novel methodological approach impinging on the considered the repository offering the highest degree of
interaction between CVs structured metadata and authenticity and consistency of the information
textual information. reported by recent graduates. In addition, this made it
possible to obtain a considerable amount of documents
with the same format, thus avoiding critical issues
2. Background related to the variability of available templates.
The present research draws from previous studies and
theoretical frameworks related to skills and jobs geared 3.1. Corpus building workflow
towards environmental sustainability; the attitude of
The AlmaLaurea Information Systems Department at
Generation Z towards the ecological transition; and CVs
UniMoRe extracted from its database all CVs containing
research value.
at least one degree certified by the University of Modena
The multiple dimensions discussed in the literature
and Reggio Emilia during the 2022/2023 academic year.
as green knowledge, green skills, green abilities, green
More specifically, all those students whose CVs contain
attitudes, green behaviour and green awareness [14] fall
at least one with a value
under a comprehensive green competence, the cognitive
between January 1, 2022, and August 31, 2023, and at
aspect of which seems to be the most universally
least one with a value
recognised and emphasised. In particular, the technical
equal to University of Modena and Reggio Emilia.
and analytical expertise on green issues, along with
Dealing with biographical data however raises
problem solving, system thinking, futures thinking and
critical ethical and privacy issues; for this reason
strategic thinking constitute the core of this competence
AlmaLaurea conducted a preliminary data cleaning,
[15, 16, 17, 18].
removing all personal references and contact details.
Considering that Generation Z represents “an essential
Before transmitting the files, further adjustments were
stakeholder in building a sustainable future” [8], much
made based on the CVs’ structure, in order to ensure
discussion still revolves around whether this generation
further anonymisation of the corpus. The remaining
effectively has higher pro-sustainable and pro-
personal data included only gender, date of birth, and
environmental attitudes than the older generations [8,
province of birth. Based on this information, it is not
9].
possible - in the workflow described in this paper - to
In this regard, Curricula Vitae are a source of
identify the individual to whom it refers, either directly
information since they involve detailed and longitudinal
or indirectly.
data about individuals’ educational and professional
Once defined which details to include from each CV
backgrounds, work attitudes, personal interests and
and the fields for the extraction, in December 2023
expectations [19, 20]. According to [21], since
Almalaurea provided for this study 8,096 CVs structured in the English corpus. Because of this incoherence the
as XML. English corpus was excluded from the analysis.
Subsequently, the Italian corpus was loaded on
3.2. Data extraction and formatting #LancsBox X, which was chosen on the basis of its
distinguishing feature, including its efficient metadata
Extraction and formatting of the data was conducted
management. Indeed, due to the nature of the dataset,
through the use of a custom Python script, whose
which includes 8,096 text files each one representing the
function was that of producing a machine-readable XML
CV of a single graduate, it was necessary to rely on a
structure [23] preserving both metadata and textual
tool designed to analyse linguistic data with the ability
contents. The definition of the structure was informed
of filtering through contextual information contained in
by two different but complementary needs: first, to
the metadata.
allow #LancsBox X (v. 4.0.0, [24]) to manage the
The software, however, does not allow the inverse
resulting corpus; second, to ensure that contextual and
procedure, i.e. doing quantitative analysis that is not
textual information in the original dataset could be
linguistic but rather informed by linguistic evidence.
correctly queried and retrieved during the linguistic
Thus, it is necessary to make use of data science
analysis.
techniques, which allow a tabular structure to be built
As suggested in [25, 26], metadata were left in the
from the narrative dimension [21] of CVs. Using a
corpus to allow for filtering and querying procedures,
custom Python script, a first attempt was made to
thus exploiting the possibilities provided by the
produce a data frame recording the progressive
(expected) coexistence in each CV of free fields with
sequence of events and details described in each CV.
textual content and structured metadata. In this respect,
This structure, although still preliminary, allows the
it was found that a significant issue existed in the form
extraction of quantitative and scalar indicators, to be
of the incomplete compilation of the CVs by a
combined with linguistic ones.
considerable number of individuals. Only the year and
An interesting example is the case of digital skills,
province of birth, nationality (unspecified in 4 CVs) and
which are widely assumed to be crucial for the present
sex are mentioned in all 8,096 CVs.
and future of occupations [29]. As shown in Tables 2 and
By executing the Python script, two corpora were
3, the majority of CVs did not include these
obtained – one in English (CV_En) and one in Italian
competences. Of those who assessed their digital skills,
(CV_It) – to accommodate the use of POS tagging.
most considered themselves to be autonomous and not
Using Lingua as language detector and SpaCy as
advanced users.
tokenizer, a check was made on the language used in
each textual content of the two corpora. Results are in
Table 2
Table 1.
Digital competences
Table 1 Commun Content Information
Tokens by language ication creation processing
Corpus Tok_En Tok_It None Tot No Answer 4,835 4,856 4,820
CV_it 208,233 2,771,282 36 2,979,551 None 8 40 6
Basic user 281 888 267
CV_En 233,038 271,256 4 504,298 Autonomous 1,594 1,800 2,037
user
Advanced user 1,378 512 966
Tot 8,096 8,096 8,096
The relatively small percentage of Anglicisms in the
Italian corpus is largely justified by the well-known
presence of “English-induced lexical borrowing into Table 3
Italian” [27], in particular since the most common Digital competences
domains being affected by English loanwords in the 21st Problem Safety
century are economy, technology, the internet and the solving
environment [27], where it is used as a “lingua franca of No Answer 4,850 4,878
communication" [28]. On the other hand, it is the None 34 106
presence of several textual fields identically collected in Basic user 836 973
each corpus but in most cases actually compiled only in Autonomous 1,831 1,754
Italian, along with textual fields effectively filled out in user
English, that leads to a high percentage of Italian tokens Advanced user 545 385
Tot 8,096 8,096
powerful resource for screening biographical
The final corpus loaded on #LancsBox X consists of information through textual information and vice versa.
8,096 texts, 2,597,760 grammar tokens and 2,520,735 It is in fact the combination of the two (textual data
space tokens. Texts were annotated (tagged) for part of and metadata) that enables a linguistic analysis of the
speech, headword and grammatical relation with SpaCy underlying narrative of CVs; a procedure that mixes
model it_core_news_md v.3.7.0, while semantic tagging both qualitative and quantitative perspectives, and that
was performed with PyMUSAS model can be summarised as follows. First CVs are filtered by
it_dual_upos2usas_contextual v0.3.3. Accordingly, some candidates’ characteristics, starting from those
well-known tools in the literature have been used to graduates that wrote a thesis concerning environmental
apply a corpus-assisted methodology to the analysis of sustainability - and are therefore potentially engaged
curricula vitae, thereby combining “the investigation of with topic; then the details as to how they self-assessed
vast quantities of digital textual data with linguistics- themselves regarding two of the most required
informed tools and frameworks of interpretation” [30]. competences in the frame of an overall green competence
- capacity of initiative and problem solving - are
3.3. Data structure acquired, and triangulated with corpus analysis.
Hence, drawing on a comprehensive review of the
The AlmaLaurea CV contains textual fields aiding
intense academic and non-academic debate on green
reflections on one’s social, organisational, technical and
issues, it was possible to identify some recurrent and
artistic competences and outlining a personal
significant topic that would return abstracts relevant to
description of oneself. In addition, applicants are asked
the present analysis. Once a subcorpus with all abstracts
to indicate their professional objective and desired
(3,724) was created on LancsBox X, through wildcard
occupation. With regard to the educational and
searches in both English and Italian, the following words
professional pathway, it is required to reflect on the
and their derivatives from the same root were identified:
competences acquired during these experiences. An
sostenibilità/ sustainability (sostenibil*/ sustainab*),
emphasis is also placed on the thesis work, for which the
cambiamento/ change (cambiament*/ change*),
title, keywords and abstract are requested. For example,
transizione/ transition (transizion*/ transition*),
Figure 1 and Figure 2 show excerpts from CVs in which
energia/energy (energ*). Results are summarized in Table
the sections relating to the professional objective and
4.
desired occupation have been filled.
Table 4
Wildcard searches in thesis abstracts
Value Hits Texts
sostenibil*/sustainab* 789 439
cambiament*/change* 640 474
energ* 569 356
transizion*/transition* 152 102
Figure 1: Professional objective and desired occupation Tot 2,150 1,371
in 006101_it.
Therefore, since collocates are “words which
frequently co-occur, more often than would otherwise
be expected by chance alone” [31] and collocation
analysis is often used to identify discourses in corpus
linguistics, collocates of the aforementioned occurrences
are presented in Figure 3, 4, 5, 6. Given the prevalence of
Italian occurrences, apart from the search for energ*, in
all the other cases the collocates of the Italian terms are
Figure 2: Professional objective and desired occupation shown. More specifically, the first 20 are displayed, with
in 002746_it. stop words removed, Freq.(collocation) >5 and Log Dice
>6.
As shown in Figure 1 and 2, the wealth of available
metadata - biographical information, the educational
and professional background, self-assessment of
personal attitudes and also preferences with respect to
professional career development - arguably represents a
Figure 6: GraphColl for energ* in subcorpus
Figure 3: GraphColl for sostenibil* in subcorpus “tesiabstract_it”
“tesiabstract_it”
From collocation analysis it emerged that, ranked by
Log Dice, the first 4 collocation are: transizione
energetica (11,6) transizione ecologica (11,4),
cambiamento climatico (11,4) and sostenibilità ambientale
(10,8). Deeply zooming in into candidates’
characteristics, the analysis moved to observing how
graduates that included these phrases into their CV’s
textual fields - and therefore seem to be involved in the
topic - self-assessed themselves regarding capacity of
initiative and problem solving. Results are in Figure 7.
Phrase self asssesment (0-10) Problem solving Capacity for initiative
transizione energetica 0 5 5
6 1 1
7 0 2
8 4 4
9 5 3
10 3 3
transizione ecologica 0 5 5
Figure 4: GraphColl for cambiament* in subcorpus 7 1 1
“tesiabstract_it” 8 5 5
9 3 3
10 2 2
cambiamento climatico 0 14 14
5 0 1
7 5 1
8 11 15
9 8 7
10 7 7
sostenibilità ambientale 0 11 11
6 1 3
7 6 6
8 18 11
9 12 17
10 6 6
Tot_CVs 133 133
Figure 7: Self-assessment scores for capacity for
initiative and problem solving
Figure 5: GraphColl for transizion* in subcorpus It is worth noting that many students did not fill
“tesiabstract_it” these fields, despite their widely recognised importance.
Among those who did fill them in, there does not appear
to be a prevailing feeling of excellence in these skills, but
rather a cautious confirmation.
Examples provide evidence of the possibilities of
the proposed approach, with the process of zooming in
and zooming out of data enabled by the interface
between metadata and textual information.
4. Methodological contribution Alberto Leone, for their interest and helpfulness in the
realisation of this research.
The current contribution of this paper is mainly
methodological and theoretical, since, starting from a References
gap in the literature, it proposes to collect and analyse a
large number of Curricula Vitae with a novel approach [1] D. Consoli, G. Marin, A. Marzucchi, F. Vona, Do green
impinging on the underlying narrative dimension of jobs differ from non-green jobs in terms of skills and
these documents, a procedure that requires to human capital?, Research Policy 45 (2016) 1046-1060.
triangulate metadata and textual information, and to doi:10.1016/j.respol.2016.02.007.
make use of both linguistic tools and data science [2] R. Bray, A. Mejía Montero, R. Ford, Skills
techniques. deployment for a ‘just’net zero energy transition,
Despite the reliance on standard approaches, the Environmental Innovation and Societal
resulting combination offers both linguists and data Transitions 42 (2022) 395-410.
scientists a novel perspective on CVs, ensuring that the doi:10.1016/j.eist.2022.02.002.
knowledge value of the data can be explored in a [3] R. Vakulchuk, I. Overland, The failure to
discursive manner and not reduced to lists of decarbonize the global energy education system:
competences and qualifications. Preliminary examples Carbon lock-in and stranded skill sets, Energy
show the ability of this method to provide the means to Research & Social Science 110 (2024) 103446. doi:
build a profile of the generation described by the data. 10.1016/j.erss.2024.103446.
Additionally, the resulting details may provide [4] T. Lans, V. Blok, R. Wesselink, Learning apart and
interesting insights to companies seeking to engage together: towards an integrated competence
recent graduates in supporting the ecological transition. framework for sustainable entrepreneurship in
higher education, Journal of Cleaner Production 62
5. Current limitations and further (2014) 37-47. doi:10.1016/j.jclepro.2013.03.036.
[5] S. Ogbeibu, C. J. C. Jabbour, J. Gaskin, A. Senadjki,
research M. Hughes, Leveraging STARA competencies and
The inherent complexity of extracting and exploring green creativity to boost green organisational
data from CVs requires innovative, analytical innovative evidence: A praxis for sustainable
techniques, but the insights gained can provide a development, Business Strategy and the
relevant contribution to the employment landscape’s Environment 30 (2021) 2421-2440.
understanding. The goal currently being worked on is to doi:10.1002/bse.2754.
refine the interplay between the tabular and the [6] I. Marchioni, G. Moretti, G. Tossici, Il valore non
narrative structure of the CVs in order to exploit as far ha età: Persone e organizzazioni oltre il divario
as possible their knowledge value. generazionale, EGEA spa, Milano, 2024.
Moreover, the adoption of a CADS approach to the [7] M. D. Benítez-Márquez, E. M. Sánchez-Teba, G.
analysis of CVs may come in contrast compared with the Bermúdez-González, E. S. Núñez-Rydman,
growing employment of machine learning approaches Generation Z within the workforce and in the
to CVs screening and evaluation [32, 33, 34]. The workplace: A bibliometric analysis, Frontiers in
problematic reductionism of human competence at psychology 12 (2022) 736820.
work, resulted by the widespread inclination to the doi:10.3389/fpsyg.2021.736820.
codification of know-how [35], is potentially amplified [8] T. Yamane, S. Kaneko, Is the younger generation a
by the use of AI tools in hiring processes, especially driving force toward achieving the sustainable
because of their quantification and categorization development goals? Survey experiments, Journal
processes [36, 37]. Scholars also found that candidates of Cleaner Production 292 (2021) 125932. doi:
may perceive algorithms as not able to see how unique 10.1016/j.jclepro.2021.125932.
they are, not considering certain qualitative and [9] B. M. Brand, T. M. Rausch, J. Brandel, The importance
contextual information [37, 38]. of sustainability aspects when purchasing online:
Therefore, further research is being conducted to comparing generation X and generation Z,
determine whether and how an approach that relies on Sustainability 14 (2022) 5689. doi:10.3390/su14095689.
the narrative dimension of CVs can be a valid [10] Y. -C. Wu, J. -P. Shen, Higher education for
alternative, or integration, to such systems. sustainable development: a systematic review,
International Journal of Sustainability in Higher
Acknowledgements Education 17 (2016) 633-651. doi:10.1108/IJSHE-01-
2015-0004.
The authors wish to thank the AlmaLaurea Information [11] M. S. Cole, R. S. Rubin, H. S. Feild, W. F. Giles,
Systems Department, especially in the person of Eng. Recruiters’ perceptions and use of applicant
résumé information: Screening the recent Professional Communication 61 (2017) 48-64. doi:
graduate, Applied Psychology 56 (2007) 319-343. doi: 10.1109/TPC.2017.2747338.
10.1111/j.1464-0597.2007.00288.x. [23] A. Hardie, Modest XML for Corpora: Not a
[12] P. Baker, G. Brookes, D. Atanasova, S. W. Flint, standard, but a suggestion, ICAME journal 38
Changing frames of obesity in the UK press 2008– (2014) 73-103. doi:10.2478/icame-2014-0004.
2017, Social science & medicine 264 (2020) 113403. [24] V. Brezina, W. Platt, #LancsBox X [software],
doi:10.1016/j.socscimed.2020.113403. Lancaster University, 2024. URL:
[13] A. Partington, A. Duguid, C. Taylor. Patterns and http://lancsbox.lancs.ac.uk.
meanings in discourse, John Benjamins Publishing [25] M. Bondi, M. Di Cristofaro, MoReThesisCorpus:
Company, Amsterdam, 2013. Documenting academic language as used in the
[14] C. Cabral, R. Lochan Dhar, Green competencies: theses submitted to the University of Modena and
Construct development and measurement validation, Reggio Emilia, Iperstoria 21 (2023) 9-30. doi:
Journal of Cleaner Production 235 (2019) 887-900. 10.13136/2281-4582/2023.i21.1265.
doi:10.1016/ j.jclepro.2019.07.014. [26] N. Lorenzo-Dus, M. Di Cristofaro, I know this
[15] S. Wilhelm, R. Förster, A. B. Zimmermann, whole market is based on the trust you put in me
Implementing competence orientation: Towards and I don’t take that lightly’: Trust, community
constructively aligned education for sustainable and discourse in crypto-drug markets, Discourse &
development in university-level teaching-and- Communication 12 (2018) 608-626.
learning, Sustainability 11 (2019) 1891. doi: doi:10.1177/1750481318771429.
10.3390/su11071891. [27] V. Pulcini. The Influence of English on Italian:
[16] A. Wiek, L. Withycombe, C. L. Redman, Key Lexical and Cultural Features, Berlin\ Boston, De
competencies in sustainability: a reference Gruyter, 2023.
framework for academic program development, [28] P. Vettorel, V. Franceschi, English and other
Sustainability Science 6 (2011) 203-218. doi: languages in Italian advertising, World Englishes
10.1007/s11625-011-0132-6. 38 (2019) 417-434. doi: 10.1111/weng.12432.
[17] S. L. Pan, R. Nishant, Artificial intelligence for [29] P. Rikala, G. Braun, M. Järvinen, J. Stahre, R.
digital sustainability: An insight into domain- Hämäläinen, Understanding and measuring skill
specific research and future directions, gaps in industry 4.0—a review, Technological
International Journal of Information Management Forecasting and Social Change 201 (2024) 123206.
72 (2023) 102668. doi: doi:10.1016/j.techfore.2024.123206.
10.1016/j.ijinfomgt.2023.102668. [30] M. Di Cristofaro, Corpus Approaches to Language
[18] K. Brundiers, M. Barth, G. Cebrian Gisela, M. in Social Media, Routledge, New York, 2023.
Cohen, L. Diaz, S. Doucette-Remington, W. Dripps doi:10.4324/9781003225218.2023.
Weston, G. Habron, N. Harre, M. Jarchow, Key [31] M. Gillings, G. Mautner, P. Baker, Corpus-assisted
competencies in sustainability in higher discourse studies, Cambridge, Cambridge
education—toward an agreed-upon reference University Press, 2023.
framework, Sustainability Science 16 (2021)13-29. [32] B. Cowgill, Bias and productivity in humans and
doi: 10.1007/s11625-020-00838-2. algorithms: Theory and evidence from resume
[19] M. S. Cole, H. S. Field, W. F. Giles, S. G. Harris, screening, Columbia Business School 29, Columbia
Recruiters’ inferences of applicant personality University, 2020.
based on resume screening: do paper people have [33] G. Abitova, A. Serikov, V. Nikulin, M.
a personality?, Journal of Business and Psychology Rakhimzhanova, G. Shuteyeva, K. Kulniyazova,
24 (2009) 5-18. doi: 10.1007/s10869-008-9086-9. System for Talent Acquisition: Integrating AI,
[20] J. Dietz, I. Chompalov, B. Bozeman, E. Lane, J. Automation, and Data Analysis in HR, in:
Park, Using the curriculum vita to study the career International Conference on Artificial Intelligence
paths of scientists and engineers: An exploratory in Information and Communication ICAIIC,
assessment, Scientometrics 49 (2000) 419-442. doi: Osaka, Japan, 2024, pp. 792-799.
10.1023/a:1010537606969 doi:10.1109/ICAIIC60209.2024.10463365.
[21] C. Lipovsky, The CV as a multimodal text, Visual [34] V. Dishankan, A. R. F. Shafana, AI-Driven
Communication 13 (2014) 429-458. doi: Candidate Profiling: A Comprehensive Review of
10.1177/147035721349786. Methodologies, Technologies, and Future
[22] G. M. Fillenwarth, M. McCall, C. Berdanier, Directions, Journal of Information and
Quantification of engineering disciplinary Communication Technology (2023) 9-12.
discourse in résumés: A novel genre analysis with [35] G. de Terssac, Come cambia il lavoro, 1st it. ed.,
teaching implications, IEEE Transactions on Etas Libri, Milano, 1993.
[36] D. Pessach, G. Singer, D. Avrahami, H. C. Ben-Gal,
E. Shmueli, I. Ben-Gal, Employees recruitment: A
prescriptive analytics approach via machine
learning and mathematical programming,
Decision Support Systems 134 (2020) 113290. doi:
10.1016/j.dss.2020.113290.
[37] D. T. Newman, N. J. Fast, D. J. Harmon, When
eliminating bias isn’t fair: Algorithmic
reductionism and procedural justice in human
resource decisions, Organizational Behavior and
Human Decision Processes 160 (2020) 149-167. doi:
10.1016/j.obhdp.2020.03.008.
[38] M. Lavanchy, P. Reichert, J. Narayanan, K. Savani,
Applicants’ fairness perceptions of algorithm-
driven hiring procedures, Journal of Business
Ethics 188 (2023) 125-150. doi: 10.1007/s10551-022-
05320-w.