Smart Personal Intelligent Assistant for Candidates of IELTS Exams
| Autor: | J.B. White, S.T.H. Divyanjala, Udara Srimath S. Samaratunge Arachchillage, G.U.D. Fernando, D.P.N.P. Dias, S.S. Senevirathne |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Grammar
business.industry Computer science Decision tree learning media_common.quotation_subject Decision tree computer.software_genre Support vector machine Cohesion (linguistics) Reading (process) Classifier (linguistics) Active listening Artificial intelligence business computer Natural language processing media_common |
| Zdroj: | 2020 2nd International Conference on Advancements in Computing (ICAC). |
| DOI: | 10.1109/icac51239.2020.9357150 |
| Popis: | Many IELTS candidates encounter problems at the examinations and majority of them are unable to achieve their goals even though they strive hard to accomplish their targets. Candidates strive to achieve higher band score in exams, but fail to achieve them due to the ignorance of prevailing weaknesses which have to be identified if they were to succeed. At present, IELTS seems to be the most demanding exam among applicants who are planning to embark their higher studies or migration purposes. Currently, there is no proper mechanism to assist candidates and generate an improvement plan by identifying the weaknesses of them. As a solution, Smart Personal Intelligent Assistant for Candidates Exams (SPIACIE) has been proposed to detect IELTS candidates' weaknesses through an analysis of their answers. The SPIACIE assesses four components (Reading, Writing, Listening, and Speaking) in IELTS exams. This paper is specifically based on the Long Short-Term Memory (LSTM) network model used to analyze the score of grammar and cohesion. To analyze the similarity of the sentences, the cosine proximity technique is proposed to evaluate the paraphrasing of the graph explanations. The final outcome of this application is to generate an improvement plan, developed using Machine Learning (ML) algorithms. The proposed algorithms are; Gaussian naive base for reading exam, support vector machines for listening exam, decision tree classifier for speaking exam, and k-neighbors classifier for writing exam. An improvement plan on the prediction model is provided to increase the band score of the IELTS exams, based on applicants' weakness. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|