Literary Review: The Role of Language Assessment in the Call
Centers Industry
Marcial Gustavo Ordonez
1
, Islam Avbievich Mogomedov
2
and Rosa Alba Ordonez
3
1
Universidad Cristiana de Honduras (UCRISH), San Pedro Sula, Honduras
2
Kadyrov Chenchen State University, Grozny, Russia
3
Universidad Tecnológica Centroamericana (UNITEC), San Pedro Sula, Honduras
Keywords: Artificial Intelligence, Call Centers, CTS, CTM.
Abstract: The following work attempts to outline the importance of the using of artificial intelligence in the call centers
in Honduras. Recently, it is a great deal during the COVID-19 outbreak, as the demand for such services risen
dramatically. With demand increase the quality seems to drop. Hence forth, it is the main task of companies
to increase the quality of the agents to sustain their businesses. The work outlines use of artificial intelligence
to understand how correctly each letter, word and sentences are utilised during calls by agents. Some data
collection techniques and analysing algorithms can be used to indicate where agents make mistakes in their
speech. Therefore, the techniques also will be discussed in this work.
1 INTRODUCTION
Call centers are English-speaking companies since
2008, they have expanded their growth in Honduras,
with a significant contribution to 6,489 job in 2016
(La Tribuna, 2017). There are different areas, most of
them hire agents who are dedicated to areas such as
product sales, customer retention, accounts
receivable, customer recovery. These agents are hired
by recruiters and must undergo multiple exams to
obtain a position in the various companies. The exams
that are carried out to be able to work in a call center
are: time it takes to type a certain number of words on
the computer, oral, written, comprehension exams.
These exams are name assessments, an assessment
involve gathering and interpreting data for a variety
of reasons being a challenge process that usually use
questionaries and structures interviews.
After being selected for hiring, people undergo
training in which they must know the products of the
company for which they applied and the processes
they must carry out. This training usually takes a
month, where the future agent must study a manual
during the first two weeks and work is done in pairs.
In the third week they begin to conduct test calls with
real clients, where they are given extensive feedback
on strengths and opportunities for improvement. In
the last week they must continue to make real calls
and put into practice everything they have learned. It
is extensive training and some of the agents do not
make it to the end. One limiting factor is the lack of
data with detailed annotations for language
assessment experiments (Shi, 2013).
People who works in call center should present
themselves as neutralized near native speakers of
some standard English (Forey, 2010). As a result of
the covid pandemic and a neutralized speaking, the
demands of consumers around the world have
increased and, therefore, the services offered by call
centers have become crucial to the new normal (La
Prensa, 2020).
However, some of the biggest problems it has had
is the constant complaints from users about the
agents' accents. And that is where many of the call
center companies have begun to use artificial
intelligence to measure the English level of their
employees. In these applications, a logarithm is used
in which it indicates at what level the pronunciation
of the words is, which letters are being pronounced
incorrectly and which is being pronounced correctly.
In this way, what is intended is to raise the level of
English of the agents. In Honduras there are more
than 450,000 unemployed people, according to the
Ministry of Labor, so a better business climate is
urgently needed to attract investment, say authorities
from the Honduran Council of Private Enterprise (El
Heraldo, 2021).
128
Ordonez, M., Mogomedov, I. and Ordonez, R.
Literary Review: The Role of Language Assessment in the Call Centers Industry.
DOI: 10.5220/0011608300003577
In Proceedings of the 1st International Conference on Actual Issues of Linguistics, Linguodidactics and Intercultural Communication (TLLIC 2022), pages 128-130
ISBN: 978-989-758-655-2
Copyright
c
2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)
The ubiquity of technology has also affected
language assessment and engendered the field of
computer-assisted language testing (CALT),
dedicated to exploring how computers and
technology can be utilized for evaluating different
language skills of non-native speakers (Suvorov,
2013).
2 THEORICAL FRAMEWORK
We strongly encourage authors to use this document
for the preparation of the camera-ready. Please follow
the instructions closely in order to make the volume
look as uniform as possible (Moore and Lopes, 1999).
Please remember that all the papers must be in
English and without orthographic errors.
Do not add any text to the headers (do not set
running heads) and footers, not even page numbers,
because text will be added electronically.
For a best viewing experience the used font must
be Times New Roman, on a Macintosh use the font
named times, except on special occasions, such as
program code (Section 2.3.8).
2.1 Cognitive Translation Studies and
Computer Aided Language
Learning
For AI-based language assessment, several
techniques can be found in the literature. Some of
these techniques facilitate the development of
different programming algorithms to improve user
evaluations. It is necessary to apply cognitive
translation studies (CTS). This CTS consist in the
understanding of how the human brain learns and
achieve more knowledge will develop the mind the
ability to make translations and interpretations in a
more gradually shape (Xiao, 2020). The way people
achieve more information (vocabulary) is biggest
problem learning a new language. A computer aided
language learning (CALL) can help students to learn
in a way that does not feel too aggressive the
environment that permits to have more experiences to
develop more skills before to start in a difficult
scenario (Garrett, 2009).
2.2 Cognitive Translation Model and
Machine Translation
Two important algorithms are often used to develop
software’s solutions, the cognitive translation model
(CTM) and the machine translation (MT). The CTM
is a cognitive translation model it is an algorithm to
help develop a better recognition, identification that
will help to replicate the human cognitive-linguistic
skills. And the MT is other tool to help to achieve
great results of a cognition to replicate the tree of
human thinking, and in this way to perform a better
communicative skill of the student (Gorbis, 2019).
3 THEORICAL FRAMEWORK
When carrying out a literary review of the call center
industry, it was observed that the most important
language for this industry is English one author show
interest in studies of multilingual call centers
(Woydack). All the investigations showed that the
assessments are carried out through some computer
system, only one talks about the disadvantage of
using this systems (Douglas, 2007).
Dr. J. Lockwood is the author who appears most
in topics related to call center and language
assessment (Lockwood, 2012; Lockwood, 2015). The
countries that study this topic the most are the
Philippines with 38% followed by China with 25%,
as shown in figure 1. On the other hand, no research
was found on Honduras, even though artificial
intelligence applications are carried out in other
sectors such as agribusiness (Caballero, 2020;
Fernandez, 2021), healthcare (Sorto, 2020) and
logistics (Avila, 2020).
Some papers show interesting results about using
computer base assessments for example the
demonstration of s a viable alternative to using
features based on content models trained on large sets
of pre-scored responses (Evanini, 2013). The
qualitative analysis of communication problems that
impact call centers quality and universal language
functions (Xu, 2010; Friginal, 2008).
Figure 1: Call Centers Countries.
Call Centers Countries
Manila China USA Austria Phillipine
Literary Review: The Role of Language Assessment in the Call Centers Industry
129
4 CONCLUSIONS
Call centers industry is growing up in Honduras it is
important to develop more technical assessments to
improve and prepare more people for these jobs.
Although there are some artificial intelligence
applications in the country, there is no research for
strengthen the learning of other languages. As future
research, the development of an algorithm that
evaluates the level of English and the influence of
accents is proposed to better prepare students for the
call center technician career.
REFERENCES
La Tribuna, 2017. Call Centers un servicio en continuo
crecimiento.
Shi, Q., Li, K., Zhang, S., Chu, S. M., Xiao, J., Ou, Z., 2013.
Spoken English Assessment System for Non-Native
Speakers Using Acoustic and Prosodic Features. p. 4.
Forey, G., Lockwood, J., 2010. Globalization,
Communication and the Workplace: Talking Across
The World.
La Prensa, 2020. Pandemia hace aumentar servicios de
'call centers.
El Heraldo, 2021. La otra cara de la cuarentena: los
hondureños que no tienen ingresos durante la
emergencia.
https://www.elheraldo.hn/especiales/coronavirus/la-
otra-cara-de-la-cuarentena-los-hondurenos-que-no-
tienen-ingresos-PAEH1371349.
Suvorov, R., Hegelheimer, V., 2013. Computer-Assisted
Language Testing. The Companion to Language
Assessment. pp. 594-613.
Xiao, K., Martín, R. M., 2020. Cognitive Translation
Studies: Models and methods at the cutting edge.
Linguistica Antverpiensia, New Series – Themes in
Translation Studies. 19.
Garrett, N., 2009. Computer-Assisted Language Learning
Trends and Issues Revisited: Integrating Innovation.
The Modern Language Journal. 93. s1. pp. 719-740.
Gorbis, B., Hills, B., 2019. Cognitive Machine Translation
Model: POVs and Musketeer Classes as Algorithms of
Shared Reality. p. 8.
Woydack, J. Language management and language work in
a multilingual call center: An ethnographic case study.
Revista Internacional de Organizaciones. 23.
Douglas, D., Hegelheimer, V., 2007. ASSESSING
LANGUAGE USING COMPUTER TECHNOLOGY.
Annual Review of Applied Linguistics. 27. pp. 115-132.
Lockwood, J., 2012. Are We Getting the Right People for
the Job? A Study of English Language Recruitment
Assessment Practices in the Business Processing
Outsourcing Sector: India and the Philippines. The
Journal of Business Communication (1973). 49. 2. pp.
107-127.
Lockwood, J., 2015. What does the Business Processing
Outsourcing industry want from English language
assessment? Prospect. 23. 2. pp. 60-75.
Caballero, E. M. T., Duke, A. M. R., 2020. Implementation
of Artificial Neural Networks Using NVIDIA Digits
and OpenCV for Coffee Rust Detection. 5th
International Conference on Control and Robotics
Engineering (ICCRE). pp. 246-251.
Fernandez, O. A., Ordóñez-Ávila, J. L., Magomedov, I. A.,
2021. Evaluation of parameters in a neural network for
detection of red ring pest in oil palm. AIP Conference
Proceedings. 2442. 1. p. 030015.
Sorto, A., Marquez, T., Carrasco, A., and Ordoñez, J., 2020.
Face Recognition and Temperature Data Acquisition
for COVID-19 Patients in Honduras. J. Phys.: Conf.
Ser. 1710. 1. p. 012009.
Avila, J. L. O., 2020. Study Case: Teleoperated Voice
Picking Robots prototype as a logistic solution in
Honduras, 5th International Conference on Control and
Robotics Engineering (ICCRE)
. pp. 19-24.
Evanini, K., Xie, S., Zechner, K., 2013. Prompt-based
Content Scoring for Automated Spoken Language
Assessment. Proceedings of the Eighth Workshop on
Innovative Use of NLP for Building Educational
Applications. pp. 157-162.
Xu, X., Wang, Y., Forey, G., Li, L., 2010. Analyzing the
Genre Structure of Chinese Call-Center
Communication. Journal of Business and Technical
Communication. 24. 4. pp. 445-475.
Friginal, E., 2008. Threats to the sustainability of the
outsourced call center industry in the Philippines:
implications for language policy. Lang Policy. 8. 1. p.
51.
TLLIC 2022 - I INTERNATIONAL CONFERENCE "ACTUAL ISSUES OF LINGUISTICS, LINGUODIDACTICS AND
INTERCULTURAL COMMUNICATION"
130
