Introduction
Background
Artificial intelligence
-
Machine learning is a subdiscipline of AI that consists of learning algorithms that use available data sources to summarize certain phenomena and further identify patterns. Machine learning systems can be trained or learn to build a predictive model through supervised classification or unsupervised clustering. In education, machine learning can be used to predict students’ learning performance and produce personalized learning pathways (Ciolacu et al., 2018).
-
Deep learning is a type of machine learning technology that uses artificial neural networks through layers of interconnected nodes to simulate the operation of the human brain. Trained deep learning algorithms can make predictions based on very large datasets; this is used, for example, for image recognition (Cheng et al., 2018).
-
Natural language processing is a field of AI related to understanding the human language through the analysis of sentences and the use of algorithms to extract the meaning of words. One well-known application is chatbots that can understand common language requests and respond automatically, thus providing immediate assistance to users. Another example is automatic language translation (Lu et al., 2020).
Artificial intelligence in education
Latin American higher education
Methodology
Search strategy
-
Publication date from July 2016 to June 2021.
-
Published in English, Spanish, or Portuguese.
-
Published in a peer-reviewed journal or conference proceedings.
-
Presenting empirical primary research.
-
Including data relevant to AI applications in Latin American higher education institutions (with a focus on machine learning, deep learning, and natural language processing applications).
Data extraction and analysis
-
Title, author/s, year of publication, country where the study took place.
-
Education topic of the study.
-
Common AI techniques (machine learning, deep learning, and natural language processing) used in the study.
-
Common software tools and AI algorithms used in the study.
-
AI application used in the study.
Results and discussion
ID | Author(s), year | Country | AI tecnique | Tools | Algorithms used | AI application | Education topic | |
---|---|---|---|---|---|---|---|---|
[1] | Bedregal-Alpaca et al. (2020) | Peru | ML (Prediction) | JAVA, SPSS Modeler, SPSS Statistics, EXCEL | MLP, DT (ID3 & C4.5) | Predictive modelling in education | Dropout and retention | |
[2] | Bojorque and Pesántez-Avilés (2020) | Ecuador | ML (Prediction) | n.d. | MLP-ANN | Predictive modelling in education | Teaching performance | |
[3] | Castrillón et al. (2020) | Colombia | ML (Prediction) | WEKA | J48 | Predictive modelling in education | Student performance | |
[4] | Chacón-Sánchez et al. (2020) | Colombia | ML (Classification) | WEKA | J48, J48Graft, NB, RT | Intelligent analytics | Student future development | |
[5] | Choque-Díaz et al. (2018) | Peru | NLP (Chatbot) | IBM Cloud platform, IBM Watson cognitive services | n.d. | Assistive technology (chatbots) | University services | |
[6] | Contreras et al. (2020) | Colombia | ML (Prediction) | Python | DT, SVM, MLP, KNN | Predictive modelling in education | Student performance | |
[7] | Cordero et al. (2020) | Ecuador | NLP (Chatbot) | Scrum, Extreme Programming (XP), IBM Watson™ Assistant | n.d. | Assistive technology (chatbots) | University services | |
[8] | da Fonseca Silveira et al. (2019) | Brazil | ML (Prediction) | Geocode, H2O AI, R | GLM, GBM, RF | Predictive modelling in education | Dropout and retention | |
[9] | Dehon et al. (2018) | Brazil | NLP (Chatbot) | LMS Moodle, Facebook Messenger chatbot, Facebook Notifier (Moodle plug-in) | n.d. | Assistive technology (chatbots) | Teacher-student communication | |
[10] | Delahoz-Dominguez et al. (2020) | Colombia | ML (Classification) | R | DT, RF | Intelligent analytics | University performance | |
[11] | Espinosa Rodríguez et al. (2018) | Mexico | NLP (Chatbot) | Facebook Messenger Chatbot, MongoDB mLAB | n.d. | Assistive technology (chatbots) | Student health and well-being | |
[12] | Fiallos et al. (2017) | Ecuador | NLP (Social Network Analysis) | n.d. | Force Atlas 2, TF-IDF model, LDA model | AI computer-assisted content analysis | University performance | |
[13] | García-González and Skrita (2019) | Colombia | ML (Prediction) | R | CT | Predictive modelling in education | Student performance | |
[14] | García-Vélez et al. (2019) | Ecuador | ML (Prediction) | scikit-learn toolkit | MLP | Predictive modelling in education | Student performance | |
[15] | Gómez Cravioto et al. (2020) | Mexico | ML (Prediction) | WEKA | J48, REPTree, RF | Predictive modelling in education | Student future development | |
[16] | Gutiérrez et al. (2018) | Mexico | ML & NLP (Sentiment Analysis) | R | SVM k-linear, k-radial, k-poly), RF | AI computer-assisted content analysis | Teaching performance | |
[17] | Klos et al. (2021) | Argentina | NLP (Chatbot) | Facebook Messenger Chatbot, SPSS | n.d. | Assistive technology (chatbots) | Student health and well-being | |
[18] | Mendoza Jurado (2020) | Bolivia | ML & NLP (Automatic review) | Python (Bag of Words), Tokenizer class from Keras (Python Deep Learning API) | NLP, MLP-ANN | AI computer-assisted content analysis | Assessment and evaluation | |
[19] | Menezes et al. (2020) | Brazil | DL (Facial recognition) | FaceNet architecture, Image capturing devices | HOG, CNN | Image analytics | Assessment and evaluation | |
[20] | Miranda and Guzmán (2017) | Chile | ML (Prediction) | SQL server, SPSS (MLP, DT), WEKA (BN) | MLP, DT, BN | Predictive modelling in education | Dropout and retention | |
[21] | Nieto et al. (2019) | Colombia | ML (Prediction) | KNIME | DT, RF, LR | Predictive modelling in education | University performance | |
[22] | Okoye et al. (2020) | Mexico | NLP (Sentiment Analysis) | R, Word Cloud | get_nrc_sentiment function get_sentiment function | AI computer-assisted content analysis | Teaching performance | |
[23] | Palacios et al. (2021) | Chile | ML (Prediction) | WEKA | DT, KNN, LR, NB, RF, SVM | Predictive modelling in education | Dropout and retention | |
[24] | Sandoval-Palis et al. (2020) | Ecuador | DL (Prediction) | R, SPSS, Orange | MLP-ANN | Predictive modelling in education | Student performance | |
[25] | Santos et al. (2020) | Brazil | ML (Prediction) | Python | EvolveDTree (GA & DT), KNN, AdaBoost, SVC, MLP, RF, QDA, NB | Predictive modelling in education | Dropout and retention | |
[26] | Sayama et al. (2019) | Brazil | DL & NLP (Reading comprehension) | Python (Natural Language Toolkit), Python (Deep Learning AI) | BiDAF, NLTK library, Tensorflow library | AI computer-assisted content analysis | University services | |
[27] | Tapia-Leon et al. (2017) | Ecuador | NLP (Knowledge Extraction) | PSPP (free version of SPSS), Python (Natural Language Toolkit) | NLTK library | AI computer-assisted content analysis | Teaching performance | |
[28] | Torres Soto et al. (2019) | Mexico | DL (Prediction) | Python (libraries Keras and Tensorflow) | ANN | Predictive modelling in education | Student health and well-being | |
[29] | Ulloa Cazarez and López Martín (2018) | Mexico | ML (Prediction) | n.d. | RBF, MLP, GR | Predictive modelling in education | Student performance | |
[30] | Villaseñor et al. (2017) | Mexico | ML (Classification) | LabSOM system, Scientometric tools (SJCR and SIR) | Self-organizing Map (SOM) family of neural networks | Intelligent analytics | University performance | |
[31] | Visbal-Cadavid et al. (2019) | Colombia | ML (Prediction) | R (Caret & nnet packages) | MLP-ANN | Predictive modelling in education | University performance |
AI applications in higher education
AI application | Study ID | No. of studies |
---|---|---|
Predictive modelling in education | [1], [2], [3], [6], [8], [13], [14], [15], [20], [21], [23], [24], [25], [28], [29], [31] | 16 |
AI computer-assisted content analysis | [12], [16], [18], [22], [26], [27] | 6 |
Assistive technology (chatbots) | [5], [7], [9], [11], [17] | 5 |
Intelligent analytics (classification) | [4], [10], [30] | 3 |
Image analytics (facial recognition) | [19] | 1 |
Predictive modeling in education
AI computer-assisted content analysis
Assistive technology (chatbots)
Intelligent analytics (classification)
Image analytics (facial recognition)
AI techniques, software tools, and algorithms used
AI techniques
AI technique | Type of process | Study ID | No. of studies | Total |
---|---|---|---|---|
ML | Prediction | [1], [2], [3], [6], [8], [13], [14], [15], [20], [21], [23], [25], [29], [31] | 14 | 17 |
Classification | [4], [10], [30] | 3 | ||
NLP | Chatbots | [5], [7], [9], [11], [17] | 5 | 8 |
Social network analysis | [12] | 1 | ||
Sentiment analysis | [22] | 1 | ||
Knowledge extraction | [27] | 1 | ||
DL | Prediction | [24], [28] | 2 | 3 |
Facial recognition | [19] | 1 | ||
ML & NLP | Sentiment analysis | [16] | 1 | 2 |
Automatic review | [18] | 1 | ||
DL & NLP | Reading comprehension | [26] | 1 | 1 |
AI software tools
Main AI tools used | Study ID |
---|---|
R | [8], [10], [13], [16], [22], [24], [31] |
Python | [6], [18], [25], [26], [27], [28] |
SPSS | [1], [17], [20], [24] |
WEKA | [3], [4], [15], [20], [23] |
Facebook Messenger chatbot | [9], [11], [17] |
LMS Moodle | [9] |
AI algorithms
Study ID | DT | J48 | KNN | LR | MLP | NB | RF | SVM |
---|---|---|---|---|---|---|---|---|
[1] | 66 | |||||||
[3] | 91.67 | |||||||
[4] | 62.7 | 61.34 | ||||||
[6] | 55 | 55 | 61 | 66.24 | ||||
[10] | 90 | 88 | 91 | |||||
[14] | 81.5 | |||||||
[15] | 69.9 | 73.5 | ||||||
[17] | 84.9 | 85.2 | ||||||
[18] | 94.4 | |||||||
[20] | 72 | 73 | ||||||
[21] | 83.92 | 84.02 | 84.11 | |||||
[23] | 82.19 | 83.93 | 83.45 | 79.14 | 88 | 83.97 | ||
[24] | 74.5 | |||||||
[25] | 99.38 | 99.29 | 98.67 | 95.59 | 98.55 | |||
[28] | 90 | |||||||
[31] | 90.28 |
Education topics and issues
Educational process (stakeholder) | Education topic | Study ID | No. of studies | Total |
---|---|---|---|---|
Learning (student) | Student performance | [3], [6], [13], [14], [24], [29] | 6 | 11 |
Student health and well-being | [11], [17], [28] | 3 | ||
Student future development | [4], [15] | 2 | ||
Teaching (teacher) | Teaching performance | [2], [16], [22], [27] | 4 | 7 |
Assessment and evaluation | [18], [19] | 2 | ||
Teacher-student communication | [9] | 1 | ||
Administration (educational authority) | Dropout and retention | [1], [8], [20], [23], [25] | 5 | 13 |
University services | [5], [7], [26] | 3 | ||
University performance | [10], [12], [21], [30], [31] | 5 |