Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.14 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
Essays are the prominent evaluation parameter of assessing the academic excellence along with linking the different ideas with the ability to recall. The process of assessing essay is notably time consuming when done manually. Manual evaluation is expensive as it takes significant amount of evaluator’s time. Automated evaluation if proved effective will not only reduce the time for evaluation but makes the score realistic compared with human scores. The automated evaluation process could be useful for both educators and learners as it brings the iterative improvements in students' writings. The paper describes an automated essay evaluation system using Machine Learning Techniques such as Linear Regression, Support Vector Regression and Random Forest.
In addition to preprocessing techniques like filling in null values, selecting valid features, normalization we applied cleaning process by removing unnecessary symbols, punctuations and stop-words from the essays in the training set. We have also added extra features like number of sentences, number of words, average word length, type of word using POS tagging, number of spelling mistakes in an essay, number of domain words in an essay, etc. . We have implemented our models using ‘sklearn’ machine learning library. We got satisfactory results with Linear Regression , Support Vector Regression and Random Forest algorithm with Mean Squared Error values 2.88, 1.67 and 0.867 respectively.
Keywords:
machine learning, linear regression, support vector regression, random forest
Cite Article:
"Evaluation of Essay using Machine Learning Techniques", International Journal of Science & Engineering Development Research (www.ijrti.org), ISSN:2455-2631, Vol.7, Issue 11, page no.106 - 113, November-2022, Available :http://www.ijrti.org/papers/IJRTI2211017.pdf
Downloads:
000205072
ISSN:
2456-3315 | IMPACT FACTOR: 8.14 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.14 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator