A Proposed Framework for Essay Answer Processing based on Computational

Abstract

This paper proposed processing framework in essay answer for Automatic Scoring System based on computational. Framework is built with the initial process by normalizing through stop words removal, building case homogeneous, stemming, common spelling mistakes correction, and acronym and common abbreviation analysis. The next step is to examine the similarity by carrying out similarity and classification analysis. The process in the Framework that has been built using reference essay answers as references that will be examined for similarity with the answer to the question. Similarities are matched by using features generated in the features extraction process. Then the training classification process is carried out to produce the model. The model is used to determine the classification score. Classification scores are validated by looking at the value of accuracy and the resulting similarity scores. This framework can be used to process essay problem patterns which have 2 predetermined classification classes, although for more classifications it can be handled with an improved algorithm implemented.

Gamification on Chatbot-Based Learning Media: a Review and Challenges

“…The second challenge is how we measure the quality of the student's answer. With the growth of natural language processing, it seems not impossible to build a fast response bot that understands the student's question or answer, as research by Herwanto et al that able to achieve an F1 score up to 97,6% [47] [48]. However, the chatbot must empathize with student mistakes, i.e., typos or an almost correct answer.…”

Rancang Bangun Sistem Cerdas Pemberian Nilai Otomatis Untuk Ujian Essai Menggunakan Algoritma Cosine Similarity

“…Adapun perbedaan antara penelitian yang dilakukan sebelumnya adalah pengukuran kemiripan jawaban ujian dengan kunci jawaban penelitian ini menggunakan pendekatan string-based similairty berbeda dengan penelitian (Fauzi et al, 2017), (Rinartha, 2017) dan (Ruslan et al, 2018) yang menggunakan pendekatan corpusbased. Selain itu, penelitian ini tidak bertujuan untuk membuat framework seperti penelitian (Prastowo et al, 2018) atau mengukur perfomansi algoritma pada server (Pramukantoro, 2016) namun mengembangkan sebuah sistem ujian essai berbasis web dengan memanfaatkan cosine similairty agar sistem ujian berbasis komputer memiliki kemampuan memberikan nilai secara otomatis.…”

Selection of the Best K-Gram Value on Modified Rabin-Karp Algorithm

“…After finding a unique hash value in the two data compared then the similarity value between the two is calculated using the Dice Similarity Coefficient. Dice Similarity Coefficient which is used to determine similarity between two documents, two queries, or a document and a query [18,19]. This research aims to determining the k value on K-Gram to decide selection of the best k value in the application of the modified Rabin-Karp algorithm in the removal of modulo in the hashing process to calculate the similarity between documents.…”