CoChat
Sign Up
Cited by 444Online Learning and AnalyticsArtificial Intelligence in EducationEducational Technology and Pedagogy

Artificial Intelligence for Assessment and Feedback to Enhance Student Success in Higher Education

Open access
Hooda, Monika, Rana, Chhavi, Dahiya, Omdev, Rizwan, Ali, Hossain, Md Shamim·2022·Mathematical Problems in Engineering
DOI 10.1155/2022/5215722
Open this paper in CoChat — free accountOpen PDF

Abstract

The core focus of this review is to show how immediate and valid feedback, qualitative assessment influence enhances students learning in a higher education environment. With the rising trend of online education especially in this COVID-19 pandemic, the role of assessment and feedback also changes. Earlier the assessment part is not considered the main focus in learning and teaching in HEIs, but now with the increase in online education, it is observed that the paradigm is shifted toward assessing those activities of students that enhance their learning outcomes. A lot of research work has been done on developing assessment strategies and techniques that can support learning and teaching effectively. Yet, there is limited research that looks at how methods applied in learning analytics can be used and possibly constitutes the assessment process. The objective of this work is to provide an exploratory and comparative study of how assessment and feedback practices can enhance students learning outcomes using AI. The key contribution of this study attempts to capture an outline of the most used artificial intelligence and machine learning algorithms for student success. The results showed that I-FCN performed better than other techniques (ANN, XG Boost, SVM, Random Forest, and Decision Trees) in all measured performance metrics. Also, the result of the comparative analysis study will help the educators, instructors, and administrators on how they could take the advantage of a data-driven approach, design less pressurized, more valid, reliable, constructive assessment findings, and connect the power of assessment and feedback to enhance the learning outcomes.

AI snapshot

Written from the paper’s full text.

TL;DR

This review examines how assessment and feedback practices, supported by AI, machine learning, and learning analytics, can enhance student success in higher education. It proposes an assessment analytics and feedback framework and reports a comparative analysis in which I-FCN outperformed ANN, XG Boost, SVM, Random Forest, and Decision Trees on the OULAD dataset.

Key findings

  • The review reports that assessment and feedback positively influence student outcomes including performance, motivation, engagement, self-regulation, pedagogy, and curriculum/course design.
  • In the comparative analysis, I-FCN performed better than ANN, XG Boost, SVM, Random Forest, and Decision Trees in all measured performance metrics.
  • Reported metrics include I-FCN accuracy 84%, ANN 78%, and Decision Tree 71.37%; I-FCN precision 0.93, with Random Forest and Decision Tree least precise at 0.55; I-FCN recall 0.88, with Random Forest least at 0.49; and I-FCN F1-score 91%, followed by ANN at 76%.
  • The paper also states that learning analytics can inform formative, summative, peer, and self-assessment by using available data for decision-making, monitoring learning, and detecting undesirable learning behaviors.

Methods

  • The paper is an exploratory and comparative review that develops a theoretical assessment analytics and feedback framework based on reviewed literature and case studies.
  • It conducts a comparative performance analysis of I-FCN, ANN, XG Boost, SVM, Random Forest, and Decision Trees using the Open University Learning Analytics (OULAD) dataset, which contains 32,592 students enrolled in 22 module-presentations and seven tables.
  • The models were run in Python using Jupyter notebook, and performance was assessed with accuracy rate, precision, recall rate, and F1-score.

Limitations

  • The paper states that little research-based development exists on how to design assessment and reliable feedback, and that features such as validity and reliability are completely missing from the study.
  • The paper states that security and issues occurring during the assessment process are still missing from the proposed theoretical framework, and calls for more research on lifelong learning, gender, culture, age, cognitive skills, emotions, AGI, and gamification.
  • Evident from the text: the reported comparative results are inconsistent between Section 8 and the Conclusion, such as Decision Tree accuracy being 71.37% in Section 8 but 55% in the Conclusion, and least precision being attributed to Random Forest/Decision Tree at 0.55 in Section 8 but to SVM at 46% in the Conclusion.

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

Integrity signals

Registry

Crossref · 10.1155/2022/5215722

Cites

128 of 128 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

0 of 82 cited sources checked · 0 supported · 0 flagged

  • Findingnone given

    I-FCN performed better than ANN, XG Boost, SVM, Random Forest, and Decision Trees in all measured performance metrics.

    “e results showed that I-FCN performed better than other techniques (ANN, XG Boost, SVM, Random Forest, and Decision Trees) in all measured performance metrics.”
    Quote in the paperSubstantial claim
  • Findingown data

    I-FCN has the highest recall value, that is, 0.88.

    “Recall value of all the techniques is shown in Figure 5, and it is observed that I-FCN has highest value, that is, 0.88.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Random forest and Decision have the least value of precision, that is, 0.55.

    “Random forest and Decision have the least value of precision, that is, 0.55.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Decision tree has the worst performance in terms of accuracy rate, that is, 71.37%.

    “Decision tree has the worst performer in terms of accuracy rate, that is, 71.37%.”
    Quote in the paperNot a substantial claim
  • Findingown data

    Recall value for Random forest technique is least, that is, 0.49.

    “Recall value for Random forest technique is least, that is, 0.49.”
    Quote in the paperNot a substantial claim
  • May combine two claims. 31
  • Classified as probably not a substantial claim. 25

  • May combine two claims.

    Findingnone given

    Recall value of I-FCN has highest value and worst for XGBoost technique.

    “Recall value of I-FCN has highest value and worst for XGBoost technique.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    F1-score recorded for I-FCN is 91%, which is highest among all techniques, followed by ANN with 76%.

    “F1-score recorded for I-FCN is 91% which is highest among all techniques, followed by ANN with 76% as shown in Figure 6.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Findingown data

    I-FCN shows highest performance at 84%, while decision tree has the worst performer, that is, 55% in terms of accuracy rate.

    “I-FCN shows highest performance at 84%, while decision tree has the worst performer, that is, 55% in terms of accuracy rate.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    F1-score recorded for I-FCN is 91% which is highest among all techniques, followed by ANN with 76%, least value of F1-score recorded is for XGBoost.

    “F1-score recorded for I-FCN is 91% which is highest among all techniques, followed by ANN with 76%, least value of F1-score recorded is for XGBoost.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    I-FCN is most precise, that is, 93% in assessing and providing feedback to students, whereas SVM is least precise with a value 46%.

    “Moreover, I-FCN is most precise, that is, 93% in assessing and providing feedback to students, whereas SVM is least precise with a value 46%.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Findingown data

    I-FCN shows highest performance of 84% accuracy, followed by ANN with 78%.

    “It is observed from Figure 3 that I-FCN shows highest performance of 84%, followed by ANN with 78%.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Peer assessment enhances students' academic performance and helps instructors optimize the use of teacher's resources effectively.

    “A recent study [55] presented a meta-analysis that studies the role of peer assessment in enhancing the academic performance of students and helps the instructor in optimizing the use of teacher's resources effectively.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [55] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Self-assessment improves student's motivation, engagement, and outcomes in computer-based, mobile-based, pen-paper based, and e-learning-based education environments.

    “However, there are a significant number of studies giving proof that uncovers and reveals that self-assessment improves student's motivation, engagement, their outcomes in computer-based, mobilebased, pen-paper based, and e-learning-based education environment [49,50].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [49] source

      Not checked in the free run.

    • cites [50] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Formative assessment helps in students' learning process and enhances students' learning outcomes.

    “Formative assessment helps in students' learning process and enhances students learning outcomes [38,39].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [38] source

      Not checked in the free run.

    • cites [39] Z. G. Baleni, 2015, Online formative assessment in higher education: its pros and cons, Electronic Journal of E-Learning

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Formative assessment approaches and skills are superior for meeting HEIs' needs to improve teaching levels, which in turn improves students' learning outcomes and raises their achievement level.

    “Formative assessment (i.e., provide immediate and meaningful feedback to students about the learning outcomes at the end of the course contents) approaches and skills are superior to meet HEIs needs-to improve teaching levels of teachers which in turn improvise students learning outcomes and raise their achievement level [13].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [13] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    The role of assessment in higher education improves grading capacity, motivation values, performance, and advancing learning.

    “e role of assessment in higher education improves their grading capacity, motivation values, performance, and advancing learning [2,3].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [2] source

      Not checked in the free run.

    • cites [3] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Positive effects are seen of peer assessment on students' learning autonomy, including self-skills development and self-motivation.

    “Positive effects are seen of peer assessment on students learning autonomy (i.e., self-skills development, and self-motivation) [14,15].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [14] source

      Not checked in the free run.

    • cites [15] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    The online form of peer assessment is more common than the traditional form, as it acts as an early intervention means by decreasing teacher's intrusion.

    “A review of recent research [14] showed that the online form of peer assessment is more common, as it acts as an early intervention means by decreasing teacher's intrusion than the traditional form of peer assessment.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [14] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Effective peer feedback enhances self-efficacy, metacognition, and academic achievement in higher education.

    “In studies, it is seen that effective peer feedback enhances self-efficacy, metacognition, and academic achievement in HE.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [73][74][75]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Time, scalability, and individual attitudes of staff and students are the major challenges while providing feedback.

    “eir findings show that time, scalability, and individual attitudes of staff and students are the major challenges while providing feedback.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [77] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Assessment helps in improving the performance of students' learning and acts as a key factor in their future attainment.

    “Assessment helps in improving the performance of students learning and acts as a key factor in their future attainment [2].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [2] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    The Learning process for learning analytics contains five main components: ability, data, culture and process, governance and infrastructure, and overall readiness perception.

    “Also, the Learning process [80,81], for LA contains five main components: (1) ability, (2) data, (3) culture and process, (4) governance and infrastructure, and (5) overall readiness perception.”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [80] K. E. Arnold, An exercise in institutional reflection: the learning analytics readiness instrument (LARI)

      Not checked in the free run.

    • cites [81] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Peer and self-assessment promoted student success, their participation in course, and skills.

    “It is also seen that there are numerous studies on peer, and self-assessment arrived at the conclusion that peer, and self-assessment promoted student success, their participation in course and skills [25][26][27][28].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [25][26][27][28]

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    The main purposes of assessment are motivation of students, feedback to students, feedback to teachers, measuring students' performance, measuring students' progress in the course, curriculum/course design, diagnosis, and support of student collaboration.

    “By exploring [57][58][59][60][61][62][63][64], it is found that the main purpose of assessment is as follows: (i) Motivation of students (ii) Feedback to students (iii) Feedback to teachers (iv) Measure students' performance (v) Measure students' progress in the course (vi) Curriculum/Course design (vii) Diagnosis (viii) Support student's collaboration”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [57][58][59][60][61][62][63][64]

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    A case study of STEM students found that a formative assessment strategy helps in decreasing dropout rates and hence improves student's performance.

    “Reference [42] presented a case study of STEM students where formative assessment strategy helps in decreasing dropout rates and hence improves student's performance.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [42] A. C. Finamore, Fostering Stem Formative Assessment for Lifelong Learners source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Other frameworks proposed for learning analytics are the LALA framework with institutional, technological, ethical, and community dimensions, the Rapid Outcome Mapping Approach (ROMA), and the SHEILA Framework.

    “Moreover, other frameworks proposed for LA are the LALA framework consisting of four dimensions: (1) institutional, (2) technological, (3) ethical, and (4) community [82], Rapid Outcome Mapping Approach (ROMA) [83], the SHEILA Framework [84].”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [82] SanagustínM. P.HilligerI.MaldonadoJ.PérezR.RamírezL.Munoz-MerinoP. J.TsaiY. S.OrtizM.BroosT.Zuniga-PrietoM.SheihingE.LALA Framework2019Melbourne, AustraliaMonasha UniversityTechnical Report

      Not checked in the free run.

    • cites [83] Y. S. Tsai, LA policy: developing an institutional policy for learning analytics using the RAPID outcome mapping approach

      Not checked in the free run.

    • cites [84] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Curriculum and assessment work together cyclically and recursively to deliver learners and instructors with direction and focus.

    “Curriculum and assessment work together cyclically and recursively to deliver learners and instructors with direction and focus [66].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [66] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The proposed theoretical framework highlights four main focus areas from the findings that can be used to support quality higher education.

    “e proposed theoretical framework highlights the four main focus areas from the findings that can be used to support quality higher education.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    There is a tremendous increase in students' performance after introducing the formative assessment strategy.

    “Results showed that there is a tremendous increase in students' performance after introducing the formative assessment strategy.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [42] A. C. Finamore, Fostering Stem Formative Assessment for Lifelong Learners source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Feedback loops show a trajectory of how students engage in the feedback process, reflect, and make ongoing adjustments during learning to enhance learning strategies.

    “e concept of feedback loops is discussed which shows a trajectory of how students engage themselves in the feedback process, reflect and make ongoing adjustments during their learning process to enhance learning strategies [78].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [78] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    These learning analytics frameworks help HEIs to identify their strengths and weaknesses to enhance quality education.

    “ese frameworks help HEIs to identify their strengths and weaknesses to enhance quality education.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    A formative assessment tool for students improves their final grades by using automated feedback, which helps both students and teachers in improving the learning process.

    “Reference [43] designs a formative assessment tool for students where they improve their final grades by using automated feedback which helps both students and teachers in improving the learning process.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [43] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    After reviewing various presented frameworks for learning analytics, a learning and assessment framework is designed.

    “After reviewing the various presented frameworks for LA (Learning Analytics), finally a learning and assessment framework is designed.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Summative assessment benefits include supporting the instructor in avoiding errors, increasing error correction performance, providing reliable data for accountability purposes, and informing educational plans.

    “From the study reviewed benefits to this method are as follows: (1) support the instructor in avoiding errors; (2) increase their error correction performance; (3) it provides reliable data (e.g., grades and mid-term marks) that can be used for accountability purposes for all kinds of stakeholders (e.g., learners, teachers, and administrators) in higher education environment; and (4) helps in in”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [32][33][34]

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationreasoning

    The proposed theoretical framework is motivated by the potential and opportunities that different types of assessment and feedback offer in an educational environment to enhance learning outcomes.

    “e proposed theoretical framework is motivated by the potential and opportunities that different types of assessment and feedback offered in an educational environment to enhance learning outcomes (see Figure 2).”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    An early learning analytics framework considers six dimensions: stakeholders, internal limitations, external limitations, instruments, data, and objectives.

    “An early framework suggested by [79] considers six dimensions of a LA: (1) stakeholders, (2) internal limitations (required competencies), (3) external limitations (conventions, norms, and time scale), (4) instruments, (5) data, and (6) objectives.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [79] W. Greller, 2012, Translating learning into numbers: a generic framework for learning analytics, Journal of Educational Technology & Society

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Study design and conductnone given

    Security and issues that occur during the assessment process are still missing in the proposed theoretical framework.

    “However, security and issues that occur during the assessment process are still missing in the proposed theoretical framework.”
    • Also stated in: § 9. Conclusion, Limitations, and Future Work · plain
      “However, security and issues that occur during the assessment process are still missing in the proposed theoretical framework.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Peer assessment benefits include making the range of feedback wider and encouraging students to reflect, reducing marking load on teachers and increasing students' self-evaluation skills, and enhancing students' retention rate through motivation and reflection of their own learning.

    “Numerous benefits are observed such as (1) making the range feedback wider and encourages students to reflect, (2) reduces marking load on teachers, and increases students' selfevaluation skills [17,51], and (3) enhances students retention rate through motivation and reflection of their own learning [56].”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [17] source

      Not checked in the free run.

    • cites [51] M. M. Ashenafi, 2019, Online Peer-Assessment Datasets

      Not checked in the free run.

    • cites [56] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Oral presentation, portfolios, articles, test performances, online discussions, and quizzes are the most common products observed during the survey that are assessed using the peer assessment approach.

    “Oral presentation, portfolios, articles, test performances, online discussions, quizzes, etc., are the most common products observed during the survey that are assessed using peer assessment approach [53,54].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [53] source

      Not checked in the free run.

    • cites [54] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Learning analytics assists to monitor carefully students' learning process and purpose, detect undesirable learning behaviors and emotional states, and monitors students learning to provide ongoing to students.

    “assist to monitor carefully students' learning process and purpose, detect undesirable learning behaviors and emotional states and monitors students learning to provide ongoing to students.”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [96] source

      Not checked in the free run.

    • cites [97] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Learning analytics helps institutions during formative, summative, peer, and self-assessment processes by utilizing available data efficiently and effectively in decision-making.

    “Learning analytics helps institutions during formative, summative, peer, and self-assessment processes by utilizing available data efficiently and effectively in decision-making”
    Quote in the paperSubstantial claim0 of 2 sources checked
    • cites [96] source

      Not checked in the free run.

    • cites [97] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Students need to look and recognize feedback when it is available to improve learning.

    “Also, Rossiter [70] put emphasis on the fact that students need to look and recognize feedback when it is available to improve learning.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [70] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    Online learning provides openings as well as limitations for teachers from being deliverers of the educational curriculum to being designers of learning tasks, and provides instructional designs for interactive technologies.

    “From their findings, it is observed that online learning provides openings as well as limitations for teachers from being deliverers of the educational curriculum to being designers of learning tasks, in addition, provides instructional designs for interactive technologies.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [133] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Students experienced greater academic improvement and a positive impact on their learning correlated with active learning pedagogy.

    “[120] showed that the students experienced greater academic improvement and a positive impact on their learning correlated with active learning pedagogy”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [120] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Study design and conductnone given

    Features of assessment like validity and reliability are completely missing in the study to ensure students' achievement of the learning objectives.

    “Features of assessment like validity and reliability are completely missing in the study to ensure students' achievement of the learning objectives.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Detailed feedback helps in enhancing student's achievement and engagement in the learning process.

    “eir research results showed that detailed feedback helps in enhancing student's achievement and engagement in the learning process.”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [124] H. Chin, 2020, Incorporating feedback in online cognitive diagnostic assessment for enhancing grade five students’ achievement in “time”, Journal of Computers in Education

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Premisecitation

    By implementing formative assessment, intime and immediate feedback to struggling students they detect anomalies in the learning contents of the course.

    “us, by implementing formative assessment, intime and immediate feedback to struggling students they detect anomalies in the learning contents of the course.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [95] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    MOOC assessment models that support learner-centered pedagogy, without sacrificing the reliability of the assessment for certification, show positive results, support pedagogy, and motivate learning by decreasing the amount of cheating.

    “Reference [90] develops and validates MOOC assessment models that support learner-centered pedagogy, without sacrificing the reliability of the assessment for certification.e findings of the study show positive results, support pedagogy, and motivate learning by decreasing the amount of cheating.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [90] G. Alexandron, Assessment that matters: balancing reliability and learner-centered pedagogy in MOOC assessment

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    The work by Looi et al. [133] promotes instructors' skills in delivering instruction.

    “promotes instructors' skills in delivering instruction”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [133] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    Engagement, satisfaction, and pass rates of students in the learning environment are not just greatly influenced by learning design but are especially manipulated by how instructors stabilize their learning design activities in the course modules on weekly basis.

    “Findings indicated that engagement, satisfaction, and pass rates of students in the learning environment are not just greatly influenced by learning design but are especially manipulated by how instructors stabilize their learning design activities in the course modules on weekly basis.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [125] source

      Not checked in the free run.

  • Classified as probably not a substantial claim.

    Interpretationnone given

    We have found positive results of various assessment and feedback practices that can enhance the students' learning experience and outcomes.

    “We have found positive results of various assessment and feedback practices that can enhance the students' learning experience and outcomes.”
    Quote in the paperSubstantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    The work by Islam [134] helps in designing curriculum to support high-quality education.

    “Helps in designing curriculum to support high-quality education”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [134] source

      Not checked in the free run.

  • May combine two claims.

    Premisecitation

    The work by Looi et al. [133] supports student's motivation, relationships, and their well-being.

    “Supports student's motivation, relationships, and their well-being”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [133] source

      Not checked in the free run.

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationreasoning

    The framework can be used to inform higher education institutions to develop strong assessment and feedback strategies and practices for student success and curriculum improvement.

    “It can be used to inform higher education institutions to develop strong assessment and feedback strategies and practices for student success and curriculum improvement.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    Assessment analytics and feedback framework have individually and collectively had an impact upon student success in higher education by influencing quality of learning, quality of teaching, curriculum design, pedagogy, engagement level, motivation, and student retention and progression.

    “Assessment analytics and feedback framework have individually and collectively had an impact upon student success in higher education by influencing the following:”
    Quote in the paperNot a substantial claim
50 of 50

  • The paper relies on this without support.

    There is limited research that looks at how methods applied in AI and learning analytics can be used and possibly constitute the assessment process.

    “ere is limited research that looks at how methods applied in AI and LA can be used and possibly constitute the assessment process.”

  • The paper relies on this without support.

    So far, no measures for student quality have been explored, and the opinions of all participants, including organizations, teachers, learners, and academic staff performance objectives, have been widely overlooked.

    “So far, no measures for student quality have been explored, as well as the opinions of all participants, including organizations, teachers, as well as learners, and also academic staff performance objectives, have been widely overlooked.”

  • The paper relies on this without support.

    Past studies within the arena of AI and learning analytics have assessed students and provided feedback to students without explaining the reasons behind the assessment process.

    “Past studies within the arena of AI and LA have assessed students and provided feedback to students without explaining the reasons behind the assessment process.”

  • The paper relies on this without support.

    There is little review on the type of feedback and what type of feedback is best for what perspective in higher education.

    “Also, there is a little review on the type of feedback and what type of feedback is best for what perspective in HE.”

  • The paper relies on this without support.

    It is not that students are receiving poor or no feedback, but they do not engage or recognize feedback provided to them, regardless of its quality.

    “It is observed that it is not that students are receiving poor or no feedback, but they do not engage or recognize feedback provided to them, regardless of its quality.”

  • The paper relies on this without support.

    If the teaching process is limited and controlled, student assessment quality will also be limited.

    “Further, it is noted earlier, if the teaching process is limited and controlled, student assessment quality will also be limited.”
    “Further, it is noted earlier, if the teaching process is limited and controlled, student assessment quality will also be limited.”

  • The paper relies on this without support.

    AI helps HEIs to improve quality of education by improving students' final outcomes.

    “From researches it is observed that AI helps HEIs to improve quality of education by improving students' final outcomes.”

  • The paper relies on this without support.

    The balance of formative and summative assessment at the program level with formative assessment systematically implemented during learning and teaching can have a positive impact on students learning as well as improve the quality of academic standards.

    “e balance of formative and summative assessment at the program level with formative assessment systematically implemented during learning and teaching can have a positive impact on students learning as well as improve the quality of academic standards.”

  • The paper relies on this without support.

    New methods and a variety of formative and summative assessment can promote students' success.

    “New methods and a variety of formative and summative can promote students' success (i.e., use technology-enhanced learning and innovative assessment methods).”

  • The paper relies on this without support.

    Opportunities for self and peer assessment within the learning and teaching environment enhance student's and teacher's understanding and trust in assessment strategies.

    “Opportunities for self and peer assessment within the learning and teaching environment enhance student's and teacher's understanding and trust in assessment strategies.”

  • The paper relies on this without support.

    Self and peer assessment develops students as an independent learner and prepares self-regulation and employability skills in them and support collaborative learning concept.

    “Self and peer assessment develops students as an independent learner and prepares self-regulation and employability skills in them and support collaborative learning concept.”

  • The paper relies on this without support.

    E-assessment provides pedagogical support, grows practical skills, increases retention rate, and provides a flexible learning environment to learners.

    “It provides pedagogical support, grows practical skills, increases retention rate, and provides a flexible learning environment to learners by using e-assessment methods”

  • The paper relies on this without support.

    Feedback is a crucial component for helping students to attain desired learning outcomes.

    “Feedback is a crucial component for helping students to attain desired learning outcomes.”

  • The paper relies on this without support.

    Feedback is important not only for knowledge acquisition but also for learner motivation and satisfaction.

    “It is important not only for knowledge acquisition but also for learner motivation and satisfaction.”

  • The paper relies on this without support.

    Timely and effective feedback is provided by teachers to achieve greater learning.

    “With the empowerment in technology, timely and effective feedback is provided by teachers to achieve greater learning.”

  • The paper relies on this without support.

    Negative feedback discourages the effort and achievement of learners.

    “rough the studies, it is noted that negative feedback discourages the effort and achievement of learners, so it should be carefully crafted and delivered.”

  • The paper relies on this without support.

    Engagement is strongly related to teaching effectiveness and directly affects the students learning outcomes.

    “Engagement is strongly related to teaching effectiveness and directly affects the students learning outcomes.”

  • The paper relies on this without support.

    Student's engagement in the course is directly correlated to course satisfaction and achievement of course learning objectives.

    “From the research studies, it is noted that student's engagement in the course is directly correlated to course satisfaction and achievement of course learning objectives.”

  • The paper relies on this without support.

    Assessment and timely feedback are observed to be the key to unlocking student's engagement in the course.

    “Assessment and timely feedback are observed to be the key to unlocking student's engagement in the course.”

  • The paper relies on this without support.

    Motivation can be accomplished through appropriate assessment and feedback practices and conditions.

    “Motivation can be accomplished through appropriate assessment and feedback practices and conditions.”

  • The paper relies on this without support.

    Self-assessment improves student motivation.

    “Studies showed that self-assessment improves student motivation.”

  • The paper relies on this without support.

    Curriculum/course design is of the key importance in the learning process.

    “Curriculum/course design is of the key importance in the learning process.”

  • The paper relies on this without support.

    A clear and concise course design is fundamental to effective student learning.

    “A clear and concise course design is fundamental to effective student learning.”

  • The paper relies on this without support.

    A well-designed curriculum confirms proper academic and professional development.

    “A well-designed curriculum confirms proper academic and professional development.”
24 of 24

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?

  • GenAI can enhance the efficiency and reliability of assessments.

    “Research by Bearman and Luckin [1] and Hooda, Rana [2] demonstrates how GenAI can enhance the efficiency and reliability of assessments.”

    From Generative AI in Higher Education: Balancing Innovation and Integrity (2025) · cites this paper as [2]

    The Abstract says the paper’s comparative analysis could help educators design more reliable assessment findings, and §2.4 describes reduced marking loads—supporting potential gains in reliability and efficiency. But the paper discusses AI and learning analytics generally, not generative AI specifically; §9 also says validity and reliability were not evaluated in the study. It therefore does not demonstrate the claimed effect for GenAI. (LLM, conf=0.85)

    Experimental — accuracy not yet measured

  • GenAI is rapidly transforming higher education, influencing assessment practices and pedagogical approaches, and offering capabilities for personalised learning and streamlined assessment.

    “Generative Artificial Intelligence (GenAI) has rapidly become a transformative factor in higher education, influencing assessment practices and pedagogical approaches to learning and teaching, offer unprecedented capabilities for personalised learning journeys and streamline assessment processes [1, 2].”

    From Generative AI in Higher Education: Balancing Innovation and Integrity (2025) · cites this paper as [2]

    The Introduction (page unavailable) describes AI applications in higher education, including customized learning, and Section 7 (page unavailable) discusses AI-supported assessment and pedagogical benefits. These passages support the general AI aspects of the claim, but they do not establish that generative AI specifically has rapidly transformed higher education or offers the stated capabilities. (LLM, conf=0.86)

    Experimental — accuracy not yet measured

  • Real-time interpersonal communication, natural language, and immediate feedback can be achieved with the incorporation of artificial intelligence in asynchronous courses.

    “However, this can be achieved with the incorporation of artificial intelligence in asynchronous courses (Hooda et al., 2022).”

    From Effects of Generative AI on Engagement and Performance Within Asynchronous Online Courses (2026) · cites this paper as Hooda et al., 2022

    Section 1.2 (page unavailable) discusses asynchronous online courses and says web-based learning can provide real-time, timely feedback. Section 7 mentions natural language processing in e-learning, but neither passage establishes that incorporating AI into asynchronous courses achieves real-time interpersonal communication or natural-language interaction. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

  • AI can evaluate students' responses and provide feedback based on the evaluation in formative assessment.

    “In formative assessment, AI can evaluate students’ responses and provide feedback based on the evaluation [15, 18, 43, 50].”

    From Comparing Student Preferences for AI-Generated and Peer-Generated Feedback in AI-driven Formative Peer Assessment (2025) · cites this paper as [18]

    Section 2.2 (Formative Assessment; page unavailable) describes a formative-assessment tool that gives automated feedback, and Section 7 (page unavailable) describes feedback based on students’ performance in formative assessments. Neither passage establishes that AI evaluates students’ responses to generate that feedback. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • AI can enhance assessment and feedback itself.

    “Hooda et al. (2022) further indicate that AI can enhance assessment and feedback itself, suggesting that redesign is not only defensive but pedagogically generative.”

    From From AI Literacy to AI Fluency: A Developmental Framework for Higher Education (2026) · cites this paper as Hooda et al., 2022

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.

  • Decision-tree accuracy is reported as both 71.37% and 55%

    Major

    The comparative analysis gives decision-tree accuracy as 71.37%, but the conclusion gives it as 55%. Both describe the same model's accuracy in the analysis.

  • Conflicting claims about the lowest precision

    Major

    The comparative analysis says Random Forest and Decision Trees have the lowest precision at 0.55, whereas the conclusion calls SVM the least precise at 46%. A precision of 46% is below 0.55.

2 of 2

Cites

Flagged first, then by citations

Research works printed but not linked: 4

  1. G. S. Sriram, 2022, Challenges of cloud compute load balancing algorithms. International research, Journal of Modernization in Engineering Technology and Science, 4, 1186
  2. A. Álvarez-Arana, 2020, Improving assessment using visual learning analytics, Educ. Knowl. Soc, 21
  3. JainA.Multi-class classification to track students’ academic outcome2019DublinNational College of IrelandDoctoral dissertation
  4. H. Karimi, 2014, A deep model for predicting online course performance, Cse Msu Educ, 192, 302

Cited by

Sorted by citations

Related

Authors
Hooda, M., Rana, C., Dahiya, O., Rizwan, A., & Hossain, M. S.
Affiliations
  • Maharshi Dayanand University (IN)
  • Lovely Professional University (IN)
  • King Abdulaziz University (SA)
  • Hajee Mohammad Danesh Science and Technology University (BD)
Corresponding author
Hossain, Md Shamim
ORCID
Venue
Mathematical Problems in Engineering
Publisher
Wiley
Published
2022-05-05
Volume
2022
Pages
1-19
ISSN
  • 1024-123X (ISSN-L)
  • 1563-5147
DOI
10.1155/2022/5215722
OpenAlex
W4228997948
Semantic Scholar
d21c15a28720bd920875076bb9c3d8879e98d8e1
Cited by
444
References
128
Citations by year
2026: 98 · 2025: 182 · 2024: 127 · 2023: 28 · 2022: 9
FWCI
66.89
Type
journal article
Language
en
Open access
Licence
Locations
  • Mathematical Problems in Engineering (publishedVersion, cc-by)
  • RePEc: Research Papers in Economics (submittedVersion)
Topics
  • Physical Sciences › Computer Science › Computer Science Applications › Online Learning and Analytics
  • Physical Sciences › Computer Science › Information Systems › Artificial Intelligence in Education
  • Physical Sciences › Computer Science › Artificial Intelligence › Educational Technology and Pedagogy
Keywords
artificial intelligence in education, student assessment, feedback, student success, learning outcomes, online learning, COVID-19 pandemic, learning analytics, machine learning algorithms, student performance prediction

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.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-08.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-08.

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