A Machine Learning Prediction of Automatic Text Based Assessment for Open and Distance Learning: A Review

Guembe, Blessing; Azeta, A. A.; Misra, Sanjay; Chigozie, Felix; Ahuja, Ravin

doi:10.1007/978-3-030-49339-4_38

Cited by 13 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The developments and progress in the field of automated short answer grading (ASAG) have been previously reviewed in few survey papers [1,2,19]. A unified and comprehensive overview of the entire field can be found in [2], where the developments of analytic components until 2014 were addressed from a historical perspective.…”

Section: Contributionsmentioning

confidence: 99%

“…They highlighted the role and importance of a proper feature set design for effective training of machine learning models. Other published reviews [1] did not discuss further aspects of the developments in the field of ASAG.…”

Section: Contributionsmentioning

confidence: 99%

“…Recent progress in Deep Learning and NLP facilitated the design and analysis of machine learning models for textual data [47,69] and raised the question of their applicability to different application areas, such as AES and ASAG. These advancements and their application to ASAG have not been covered in recent surveys, which only reviewed methods and approaches based on feature extraction used in combination with classical machine learning models [1,2,19]. This research focuses solely on ASAG, for which it is fundamental to construct an effective semantic representation of the answers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Haller¹,

Aldea²,

Seifert³

et al. 2022

Preprint

View full text Add to dashboard Cite

Automated short answer grading (ASAG) has gained attention in education as a means to scale educational tasks to the growing number of students. Recent progress in Natural Language Processing and Machine Learning has largely influenced the field of ASAG, of which we survey the recent research advancements. We complement previous surveys by providing a comprehensive analysis of recently published methods that deploy deep learning approaches. In particular, we focus our analysis on the transition from handengineered features to representation learning approaches, which learn representative features for the task at hand automatically from large corpora of data. We structure our analysis of deep learning methods along three categories: word embeddings, sequential models, and attention-based methods. Deep learning impacted ASAG differently than other fields of NLP, as we noticed that the learned representations alone do not contribute to achieve the best results, but they rather show to work in a complementary way with hand-engineered features. The best performance are indeed achieved by methods that combine the carefully hand-engineered features with the power of the semantic descriptions provided by the latest models, like transformers architectures. We identify challenges and provide an outlook on research direction that can be addressed in the future.

show abstract

Section: Contributionsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Haller¹,

Aldea²,

Seifert³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The study by Meulen [3] noted that companies had increased their investment in big data from 58-75% due to the vast potential it has to offer. Sectors such as the e-commerce space [4], education [5], manufacturing [6], public health [7], weather prediction [8], diabetes prediction (public health) [9], ISSN: 2088-8708  Application of machine learning in cement price prediction … (Adedeji Olushola Afolabi) 5215 earthquake prediction [10], and oil and gas [11] are participating in the big data advanced analytics to assist in its decision making and provide deep insight. Specifically, there is a need to apply big data in planning and decision-making about building materials.…”

Section: Introductionmentioning

confidence: 99%

Application of machine learning in cement price prediction through a web-based system

Afolabi

Abimbola²

2022

IJECE

View full text Add to dashboard Cite

Cement is one of the most common building materials in the construction industry. Simultaneously, its price fluctuation can affect the success or failure of the construction project's performance. The study aimed to develop a web-based platform that uses machine learning algorithms on historical data of cement prices, petrol prices, diesel prices, interest rate, and exchange rate to predict future prices of cement products. The web-based learning platform was developed using hypertext markup language (HTML), cascading style sheet (CSS), MySQL, and hypertext preprocessor (PHP). For building a reliable machine learning model, python language was used to train the system. The front end, the back end, and the machine learning model were integrated with a flask python framework. A system block diagram was designed to show the web-based learning platform's interfaces. The web-based learning platform's system implementation led to the login page, the home page, database page, and cement price analytics interface. In training the machine learning model to make reliable cement price predictions, the study obtained an 80% fitted model in the linear regression. The web-based machine learning platform was able to predict the prices of cement. The rationale behind the machine learning prediction shown by the scatter plot diagram revealed that the cement increases by 250 naira biannually.

show abstract

“…Machine learning offers useful statistical tools for complex nonlinear regression problems and thus can be exploited to obtain more accurate predictions at low computational cost [8][9][10]. Most researchers perform work to establish an effective diagnostic method for the earliest possible diagnosis of the tumor, and also to make it easier to start treatment at earlier stages, and to increase the survivability rate [11].…”

Section: Introductionmentioning

confidence: 99%

Analysis and Classification of Biomedical Data Using Machine Learning Techniques

Panda

Maringanti

2021

Communications in Computer and Information Science

View full text Add to dashboard Cite

Breast cancer research has been the center of discussion on health information technology in recent years, as it is the second largest cause of cancer deaths in women. A biopsy in which tissue is microscopically extracted and analyzed will be used for the detection of breast cancer. The cancer cells are either categorized as cancer or non-cancer. There are various methods for classifying and predicting breast cancer. The proposed work uses a breast cancer dataset from Wisconsin (Diagnostic). The data collection used to track the effectiveness of different machine learning approaches with respect to main parameters including accuracy, F1-score, specificity and recall. The three basic classification models in this paper are i.e., Naïve Bayes, KNN, Decision Tree was used to forecast cancer. The comparative tests show that the proposed Naïve Bayes classifier gives the accuracy of 98.1%, f1 score of 98.3%, specificity of 97.5%, recall of 98.3%.

show abstract

A Machine Learning Prediction of Automatic Text Based Assessment for Open and Distance Learning: A Review

Cited by 13 publications

References 17 publications

Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Survey on Automated Short Answer Grading with Deep Learning: from Word Embeddings to Transformers

Application of machine learning in cement price prediction through a web-based system

Analysis and Classification of Biomedical Data Using Machine Learning Techniques

Contact Info

Product

Resources

About