CoChat

Experiences in the use of an adaptive intelligent system to enhance online learners' performance: a case study in Economics and Business courses

Open access
Guerrero-Roldán, Ana-Elena, Rodríguez-González, M. Elena, Bañeres, David, Elasri-Ejjaberi, Amal, Cortadas, Pau · 2021 · International Journal of Educational Technology in Higher Education

The DOI matches its Crossref record; 70 of the 71 references it cites were found in a registry or an index; 1 of the 22 sources its claims cite were checked for support.

Abstract

Several tools and resources have been developed in the past years to enhance the teaching and learning process. Most of them are focused on the process itself, but few focus on the assessment process to detect at-risk learners for later acting through feedback to support them to succeed and pass the course. This research paper presents a case study using an adaptive system called Learning Intelligent System (LIS). The system includes an Early Warning System and tested in a fully online university to increase learners’ performance, reduce dropout, and ensure proper feedback to guide learners. LIS also aims to help teachers to detect critical cases to act on time with learners. The system has been tested in two first-year courses in the fully online BSc of Economics and Business at the Universitat Oberta de Catalunya. A total of 552 learners were participating in the case study. On the one hand, results show that performance is better than in previous semesters when using it. On the other hand, results show that learners' perception of effectiveness is higher, and learners are willing to continue using the system in the following semesters because it becomes beneficial for them.

Overview

CoChat Summary

TL;DR

This case study tested LIS, an adaptive early-warning system, in two fully online first-year Economics and Business courses at Universitat Oberta de Catalunya with 552 consenting learners. It reports better final marks and lower dropout for LIS users and positive learner perceptions of the system’s effectiveness and usefulness.

Key findings

  • Dropout after ALA4 was lower for LIS-signed learners than for not-signed and previous-semester groups: Introduction to enterprise 14.20% vs 32.79% vs 29.24%; Markets and behavior 9.52% vs 31.90% vs 18.2%.
  • Final marks were significantly better for the signed LIS group: Introduction to enterprise signed vs not signed p=0.0048 and signed vs previous semester p=2.6e-16; Markets and behavior signed vs not signed p=2e-6 and signed vs previous semester p=2.2e-6.
  • The GAR model’s global accuracy was >78% at ALA1 and >90% at ALA5 in both courses; TNR was >89%, and TPR exceeded 70% from ALA2. At-risk learners identified ranged from 6.80% to 15.90% in Introduction to enterprise and 9.60% to 14.10% in Markets and behavior.
  • Among 205 post-questionnaire respondents, 75.12% found the dashboard useful, 68.29% agreed or strongly agreed to future LIS use, and more than 60% rated feedback messages, dashboard, and LIS globally as “Like somewhat” or “Like a great deal.”

Methods

  • Mixed action research plus design-and-creation approach; pilot in two first-year 6 ECTS courses, Markets and behavior and Introduction to enterprise, in the fully online BSc of Economics and Business at Universitat Oberta de Catalunya during the February–June 2020 semester.
  • 552 learners consented to participate (44.52% of the total); LIS used a Gradual At-Risk model trained on historical anonymized data with Naive Bayes, Decision Tree, K-Nearest Neighbors, and Support Vector Machine, assigning Green/Yellow/Red/NS1/NS2 risk levels and sending dashboards and emails.
  • Quantitative analysis used the unpaired two-sample Wilcoxon test for final marks, descriptive analysis of dropout and ALA performance, and MARS multivariate regression; the post-questionnaire was administered via Qualtrics with 205 responses on Likert scales.

Limitations

  • Stated: self-selection bias is induced by the Ethical Committee’s consent requirement, since learners who participate in pilots tend to have better performance and a predisposition to test innovative tools.
  • Stated: mortality bias may affect the qualitative analysis because not all pilot participants answered the post-questionnaire, and failed or dropped-out learners likely did not answer; anonymity prevents checking this.
  • Stated: the GAR model becomes invalid if a course’s continuous assessment changes drastically in number or type of activities, requiring contingency models; evident from the reported age distribution, post-questionnaire respondents were skewed younger (31.71% aged 21–25), which may limit generalizability of perception findings.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s41239-021-00271-0

Cites

70 of 70 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Verification

Claims the paper makes

1 Valid · 1 Not valid · 13 Not checked · 96 Own results and interpretations

56 more claims

Create a free account to see all 111 claims and to verify the 21 references still open.

See all claims — free account
  • Probably not a substantial claim. 28
  • It may state two separate claims as one. 28
  • The quote only partly states this claim. 3

Create a free account to see these claims.

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?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

3 of 3

Citations

Cites

Show all 70 references

Research works printed but not linked: 2

  1. Cem, F. (2008). A multi-agent adaptive learning system for distance education (Middle East Technical University). https://www.semanticscholar.org/paper/A-MULTI-AGENT-ADAPTIVE-LEARNING-SYSTEM-FOR-DISTANCE-Cem/bef6e4c4541d2aca91d0de0f1c9cf09def02eedc.
  2. Melton, R. F. (2002). Planning and developing open and distance learning: a quality assurance approach. Planning and developing open and distance learning: a quality assurance approach. London: Routledge Falmer.

Cited by

See all 63

Metadata

Authors
Guerrero-Roldán, A.-E., Rodríguez-González, M. E., Bañeres, D., Elasri-Ejjaberi, A., & Cortadas, P.
Affiliations
Universitat Oberta de Catalunya (ES)
Venue
International Journal of Educational Technology in Higher Education
Published
2021-07-02
Volume
18
Issue
1
ISSN
2365-9440 (ISSN-L)
OpenAlex
W3176899830
Cited by
50
References
71
Citations by year
2026: 7 · 2025: 11 · 2024: 13 · 2023: 14 · 2022: 4 · 2021: 1
FWCI
6.77
Type
journal article
Language
en
Open access
Licence
Locations
  • International Journal of Educational Technology in Higher Education (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • O2 - Repositori Institucional (Universitat Oberta de Catalunya) (submittedVersion, cc-by)
Funders
Universitat Oberta de Catalunya (2018NG001)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
  • Physical Sciences › Computer Science › Artificial Intelligence › Intelligent Tutoring Systems and Adaptive Learning
  • Physical Sciences › Computer Science › Artificial Intelligence › Edcuational Technology Systems
Keywords
adaptive intelligent systems, early warning systems, online learning, school dropout prevention, at-risk students, learner performance, feedback, first-year students, economics and business education, learner perceptions, Universitat Oberta de Catalunya

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 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash).

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: Experiences in the use of an adaptive intelligent system to enhance online learners' performance: a case study in Economics and Business courses. https://app.cochat.ai/papers/10.1186/s41239-021-00271-0
The paper
Guerrero-Roldán, A.-E., Rodríguez-González, M. E., Bañeres, D., Elasri-Ejjaberi, A., & Cortadas, P. (2021). Experiences in the use of an adaptive intelligent system to enhance online learners' performance: a case study in Economics and Business courses. International Journal of Educational Technology in Higher Education. https://doi.org/10.1186/s41239-021-00271-0

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.