• Rutuja Jadhavrao
• Uma Deshpande
• Akshata Kulkarni
• Mrs Asmita .R. Kamble

In today’s era online learning is prevalent in the educational field. There are many online platforms which provide online objective tests. But, very few platforms which deliver descriptive answers test assessment. It is difficult to assess the scoring of these tests, quizzes or complex descriptive answers. The proposed system should be able to predict scores for descriptive answers and make use of data mining techniques. This paper presents text classification for scoring descriptive answers. The product can be used for evaluating the descriptive answers by using TF-IDF and kNN. The similarity will be calculated between actual and expected answers based on word matching and word order. If the pair of the text matches and has the same order, the similarity is high. To reduce human efforts to analyze descriptive answers, we are developing a system that will automatically evaluate the answers and predict scores using TF-IDF and kNN.

Text matching, kNN (k-Nearest neighbor), TFIDF (term frequency-inverse document frequency)

"Online Score Prediction System for Descriptive Answers", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 5, page no.6-12, May-2020, Available :http://www.jetir.org/papers/JETIR2005302.pdf

"Online Score Prediction System for Descriptive Answers", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 5, page no. pp6-12, May-2020, Available at : http://www.jetir.org/papers/JETIR2005302.pdf