The DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index; 3 of the 40 sources its claims cite were checked for support.
Artificial intelligence applications in Latin American higher education: a systematic review
Open accessAbstract
Over the last decade, there has been great research interest in the application of artificial intelligence (AI) in various fields, such as medicine, finance, and law. Recently, there has been a research focus on the application of AI in education, where it has great potential. Therefore, a systematic review of the literature on AI in education is therefore necessary. This article considers its usage and applications in Latin American higher education institutions. After identifying the studies dedicated to educational innovations brought about by the application of AI techniques, this review examines AI applications in three educational processes: learning, teaching, and administration. Each study is analyzed for the AI techniques used, such as machine learning, deep learning, and natural language processing, the AI tools and algorithms that are applied, and the main education topic. The results reveal that the main AI applications in education are: predictive modelling, intelligent analytics, assistive technology, automatic content analysis, and image analytics. It is further demonstrated that AI applications help to address important education issues (e.g., detecting students at risk of dropping out) and thereby contribute to ensuring quality education. Finally, the article presents the lessons learned from the review concerning the application of AI technologies in higher education in the Latin American context.
Overview
CoChat Summary
## TL;DR
This systematic review maps 31 empirical studies on AI in Latin American higher education published from July 2016 to June 2021. It finds that AI is used mainly for predictive modelling, content analysis, chatbots, and classification, with dropout/retention and student performance among the most common problems addressed.
## Key findings
- The review included 31 published articles from 7 countries: Mexico (7), Colombia (7), Ecuador (6), Brazil (5), Peru (2), Chile (2), Argentina (1), and Bolivia (1).
- The most common AI application was predictive modelling in education with 16 studies; followed by AI computer-assisted content analysis (6), assistive technology/chatbots (5), intelligent analytics/classification (3), and image analytics/facial recognition (1).
- Machine learning was the most common technique, used in 17 studies; natural language processing appeared in 8, deep learning in 3, and ML+NLP or DL+NLP combinations were also reported.
- The most frequently used algorithms were MLP-ANN, Random Forest (RF), and Decision Tree (DT); the paper says MLP-ANN and RF reported the highest accuracy across the studies, with examples of reported accuracies including 99.38% (DT), 99.29% (KNN), 98.67% (MLP), 95.59% (NB), and 98.55% (RF) in one study.
## Methods
- The paper is a systematic literature review guided by 3 research questions about AI applications, techniques/tools/algorithms, and education topics/issues in Latin American higher education.
- Searches were run in July 2021 across Web of Science, IEEE Xplorer, Scielo, and CAPES Portal for studies published from July 2016 to June 2021 in English, Spanish, or Portuguese.
- The screening process went from 2397 articles to 401 after initial refinement, then 383 after removing 18 duplicates, then 76 after abstract screening, and finally 31 studies after full-text screening and eligibility checks.
## Limitations
- The paper states that there is “a lack of attention to ethics and data privacy” and that few reviewed studies mentioned ethical clearance; it says there is a need for protocols for personal data protection.
- It also notes that the rate of AI adoption in education is still slow compared with medicine, industry, and finance, which constrains how much evidence exists in this area.
- Evident from the text: the review is limited to 4 databases, a 5-year window, and English/Spanish/Portuguese publications, so relevant studies outside those sources, dates, or languages may have been missed.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
3 Valid · 1 Not valid · 30 Not checked · 56 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“AI applications can contribute to forecasting the student dropout rate and determining the factors that affect their performance”
What the sources say
- Not matchedcites Bedregal-Alpaca etal., 2020
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites da Fonseca Silveira etal., 2019
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Partly supportedcites Miranda & Guzmán, 2017 sourceExperimental — accuracy not yet measured
The Abstract reports that data-mining techniques identified variables associated with university student dropout, particularly socioeconomic circumstances and university entrance scores. The Conclusions likewise describe academic results and socioeconomic status as influencing whether students remain enrolled. These passages support identifying factors related to dropout, but not factors that affect student performance. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“AI applications can contribute to forecasting the student dropout rate and determining the factors that affect their performance”
What the sources say
- Not matchedcites Bedregal-Alpaca etal., 2020
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites da Fonseca Silveira etal., 2019
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Miranda & Guzmán, 2017 source
The Methodology (p. 63) describes Bayesian-network, neural-network, and decision-tree classifiers used to predict whether students will drop out. The Abstract reports their predictive accuracy and a retention rate estimated by the decision tree, supporting the claim that these applications can help forecast dropout. (LLM, conf=0.88)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Predictive modelling in education | [1], [2], [3], [6], [8], [13], [14], [15], [20], [23], [24], [25], [28], [29], [31] | 16”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Assistive technology (chatbots) | [5], [7], [9], [11], [17] | 5”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“AI computer-assisted content analysis | [12], [16], [18], [22], [26], [27] | 6”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
49 more claims
Create a free account to see all 90 claims and to verify the 3 references still open.
- It may state two separate claims as one. 11
- Probably not a substantial claim. 30
- The quote only partly states this claim. 2
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Salas-Pilco y Yang (2022) realizaron una revisión sistemática de 139 artículos indexados en Scopus, identificando aplicaciones en modelado predictivo, analítica inteligente y tecnologías de asistencia, y destacando su contribución a la detección temprana del riesgo de deserción [1].”
From Avances, Retos Éticos y Perspectivas de la Inteligencia Artificial (IA) en la Educación de América Latina (2025) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Salas-Pilco et al. (2022) identifican aplicaciones de procesamiento de lenguaje natural que generan retroalimentación automatizada en ensayos y guías de estudio, liberando al profesor de tareas repetitivas [1].”
From Avances, Retos Éticos y Perspectivas de la Inteligencia Artificial (IA) en la Educación de América Latina (2025) · cites this paper as [1]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“AI applications in education also raise ethical considerations, ranging from professional readiness to lapses in rigour, such as not adhering to ethical procedures when collecting data (e.g., Salas-Pilco & Yang, 2022), and ethical and legal issues related to using tools prematurely (Zhang et al., 2023).”
From A meta systematic review of artificial intelligence in higher education: a call for increased ethics, collaboration, and rigour (2024) · cites this paper as Salas-Pilco & Yang, 2022
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“The results revealed that the main AI applications in higher education in Latin America are: (1) predictive modeling, (2) intelligent analytics, (3) assistive technology, (4) automatic content analysis, and (5) image analytics.”
From Artificial intelligence in higher education: the state of the field (2023) · cites this paper as Salas-Pilco and Yang (2022)
Citations
Cites
Systematic Literature Reviews in Software Engineering—A Systematic Literature Review
Kitchenham, B., Pearl Brereton, O., Budgen, D., Turner, M., Bailey, J., & Linkman, S. (2009) · Information and Software Technology · doi:10.1016/j.infsof.2008.09.009 · Cited by 4,537 · cited 1×
“A systematic review explores previous studies to answer specific research questions based on an explicit, systematic, and replicable search strategy, with inclusion and exclusion criteria (Kitchenham et al., 2009; Xiao & Watson, 2019).”
BackgroundArtificial Intelligence in Education: A Review
Chen, L., Chen, P., & Lin, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2988510 · Cited by 4,133 · cited 1×
“The education sector is now significantly influenced by AI research, as AI applications are being used by learners, educators, and administrators and various tools, algorithms, and applications have been developed with the capacity to transform the education field (Chen et al., 2020).”
BackgroundGuidance on Conducting a Systematic Literature Review
Xiao, Y., & Watson, M. (2019) · Journal of Planning Education and Research · doi:10.1177/0739456x17723971 · Cited by 3,467 · cited 1×
“A systematic review explores previous studies to answer specific research questions based on an explicit, systematic, and replicable search strategy, with inclusion and exclusion criteria (Kitchenham et al., 2009; Xiao & Watson, 2019).”
BackgroundExploring the impact of artificial intelligence on teaching and learning in higher education
Popenici, S. A. D., & Kerr, S. (2017) · Research and Practice in Technology Enhanced Learning · doi:10.1186/s41039-017-0062-8 · Cited by 2,019 · cited 2×
“AI is defined as “computing systems that are able to engage in human-like processes such as learning, adapting, synthesizing, self-correction and use of data for complex processing tasks” (Popenici & Kerr, 2017, para.”
BackgroundOverview of artificial intelligence in medicine
Amisha, Malik, P., Pathania, M., & Rathaur, V. K. (2019) · Journal of Family Medicine and Primary Care · doi:10.4103/jfmpc.jfmpc_440_19 · Cited by 1,106
The TESOL Encyclopedia of English Language Teaching
(2018) · Wiley eBooks · doi:10.1002/9781118784235 · Cited by 1,055
AI technologies for education: Recent research & future directions
Zhang, K., & Aslan, A. B. (2021) · Computers and Education: Artificial Intelligence · doi:10.1016/j.caeai.2021.100025 · Cited by 923
Some guidance on conducting and reporting qualitative studies
Twining, P., Heller, R. S., Nussbaum, M., & Tsai, C.-C. (2017) · Computers & Education · doi:10.1016/j.compedu.2016.12.002 · Cited by 291 · cited 1×
“Moreover, Twining et al. (2017) highlighted the importance of qualitative studies—regarding technologies applied in education—in understanding a situation or phenomenon through the identification of themes and patterns in the data.”
BackgroundBorsci, S., Malizia, A., Schmettow, M., van der Velde, F., Tariverdiyeva, G., Balaji, D., & Chamberlain, A. (2022) · Personal and Ubiquitous Computing · doi:10.1007/s00779-021-01582-9 · Cited by 266 · cited 1×
“These applications are being integrated in social networks, websites, and a variety of platforms (Borsci et al., 2021).”
BackgroundOwoc, M. L., Sawicka, A., & Weichbroth, P. (2021) · IFIP Advances in Information and Communication Technology · doi:10.1007/978-3-030-85001-2_4 · Cited by 222 · cited 1×
“Furthermore, Owoc et al. (2021) indicated that the benefits of AI in education are the following: (a) automation of repetitive and time-consuming activities such as grading or controlling student attendance, (b) use of AI facilitators to support teachers in their classroom work, (c) feedback for…”
Background
Research works printed but not linked: 3
- *García-González, D. J., & Skrita, A. (2019). Predicting academic performance based on students’ family environment: Evidence for Colombia using classification trees. Psychology Society & Education, 11(3), 299–311. https://doi.org/10.21071/psye.v11i3.13947. · doi:10.21071/psye.v11i3.13947
- *Mendoza Jurado, H. F. (2020). Modelos de redes neuronales artificiales, como sustento evaluativo al crecimiento pedagógico virtual en Educación Superior [Artificial neural network models, as evaluative support to virtual pedagogical growth in Higher Education]. Educación Superior, 7(2), 25–36. https://www.scielo.org.bo/pdf/escepies/v7n2/v7n2_a06.pdf.
- Torre, D., & Zapata, G. (2012). Impacto de procesos de aseguramiento de la calidad sobre las instituciones de educación superior: un estudio en siete países [Impact of quality assurance processes on higher education institutions: A study in seven countries]. In M. Lemaitre, & M. Zenteno (Eds.), Aseguramiento de la Calidad en Iberoamérica. Informe 2012 (pp. 115–157). RIL Editores.
Cited by
Artificial intelligence in higher education: the state of the field
Crompton, H., & Burke, D. (2023) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-023-00392-8 · Cited by 2,010
Bond, M., Khosravi, H., De Laat, M., Bergdahl, N., Negrea, V., Oxley, E., Pham, P., Chong, S. W., & Siemens, G. (2024) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-023-00436-z · Cited by 852
“%) reported on findings of ITS diagnosing strengths and gaps, suggesting learning paths and providing automated feedback (Salas-Pilco & Yang, 2022), which can help reduce educator workload (Alam & Mohanty, 2022) and ensure that students receive timely information about their learning (Crompton &…”
BackgroundMethodInfluentialEssel, H. B., Vlachopoulos, D., Tachie-Menson, A., Johnson, E. E., & Baah, P. K. (2022) · International Journal of Educational Technology in Higher Education · doi:10.1186/s41239-022-00362-6 · Cited by 428
Yu, H., & Guo, Y. (2023) · Frontiers in Education · doi:10.3389/feduc.2023.1183162 · Cited by 357
“Generative AI can automatically identify students’ learning weaknesses and bottlenecks through machine learning algorithms and deep learning technology, providing corresponding targeted tutoring and exercises to help students better master learning content and skills (Salas-Pilco and Yang, 2022).”
BackgroundArtificial intelligence and learning analytics in teacher education: A systematic review
Salas-Pilco, S., Xiao, K., & Hu, X. (2022) · Education Sciences · doi:10.3390/educsci12080569 · Cited by 326
Self-citation
Metadata
- Authors
- Salas-Pilco, S. Z., & Yang, Y.
- Affiliations
- Central China Normal University (CN)
- Corresponding author
- Yang, Yuqin
- Venue
- International Journal of Educational Technology in Higher Education
- Published
- 2022-04-18
- Volume
- 19
- Issue
- 1
- ISSN
- 2365-9440 (ISSN-L)
- OpenAlex
- W4223914794
- Semantic Scholar
- 559fb134eb17d97d8118a8dbfab7eae7388142b6
- Cited by
- 330
- References
- 63
- Citations by year
- 2026: 88 · 2025: 110 · 2024: 87 · 2023: 36 · 2022: 8
- FWCI
- 7.60
- Type
- journal article
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- International Journal of Educational Technology in Higher Education (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Central China Normal University (Research Grant No. 1100/30106200286, ZNXBJY202108, CCNUTEIII 2021-11)
- National Natural Science Foundation of China (Grant No. 62107020)
- Ministry of Education of the People's Republic of China (Grant No. 21YJA880078)
- Topics
- Social Sciences › Education › Artificial Intelligence in Education
- Social Sciences › Education › Educational Technology and Pedagogy
- Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
- Keywords
- artificial intelligence in education, higher education, Latin America, machine learning, deep learning, natural language processing, predictive modeling, intelligent analytics, assistive technology, automatic content analysis, image analytics, student dropout prediction, educational management, educational quality
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Artificial intelligence applications in Latin American higher education: a systematic review. https://app.cochat.ai/papers/10.1186/s41239-022-00326-w
- The paper
- Salas-Pilco, S. Z., & Yang, Y. (2022). Artificial intelligence applications in Latin American higher education: a systematic review. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-022-00326-w
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.