Latent Semantic Analysis and Winnowing Algorithm Based Automatic Japanese Short Essay Answer Grading System Comparative Performance

Ratna, Anak Agung Putri; Santiar, Lea; Ibrahim, Ihsan; Purnamasari, Prima Dewi; Luhurkinanti, Dyah Lalita; Larasati, Adisa

doi:10.1109/icawst.2019.8923226

Cited by 8 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Tokenisasi adalah prosedur yang mengubah kalimat menjadi kata-kata individual. Ini melibatkan memisahkan kalimat menjadi unitunit terpisah berdasarkan pemisah yang membentuknya, yang dalam hal ini adalah spasi (" ") [10].…”

Section: ) Tokenisasiunclassified

Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata

Al Rasyid,

Ningsih

2024

jtik

View full text Add to dashboard Cite

This research aims to improve the search for tourist destinations in 50 datasets by using search queries to find relevant documents. By optimizing the search process, the goal is to create an accurate list of tourist destinations based on a given query. To achieve this, researchers used the TF-IDF and Cosine Similarity algorithms to retrieve and compare information, measuring similarity scores between search queries and tourist destinations in the dataset. Finally, the list of tourist destinations is ranked based on the similarity score measurement. The methods used are TF-IDF and Cosine Similarity. The fifty datasets containing text content documents were normalized through pre-processing stages, namely Case Folding, Stopword Removal, and Tokenization. Documents that have been normalized are then processed again through TF-IDF weighting. TF-IDF weighting is also applied to search queries. The similarity calculation between the TF-IDF vector from the document and the TF-IDF vector from the search query is carried out using Cosine Similarity to obtain a similarity score for each document based on the search query. Testing was carried out on 5 different queries, and precision testing results were obtained with an average value of 83%

show abstract

Section: ) Tokenisasiunclassified

Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata

Al Rasyid,

Ningsih

2024

jtik

View full text Add to dashboard Cite

show abstract

“…Tokenizing is a process to change the form of sentences into single words. Cutting sentence based on the delimiter that composes it, namely a space (" ") [24].…”

Section: Tokenizingmentioning

confidence: 99%

Automatic Scoring Using Term Frequency Inverse Document Frequency Document Frequency and Cosine Similarity

Yulita

Untoro

Praseptiawan

et al. 2023

SJI

View full text Add to dashboard Cite

Purpose: In the learning process, most of the tests to assess learning achievement have been carried out by providing questions in the form of short answers or essay questions. The variety of answers given by students makes a teacher have to focus on reading them. This scoring process is difficult to guarantee quality if done manually. In addition, each class is taught by a different teacher, which can lead to unequal grades obtained by students due to the influence of differences in teacher experience. Therefore the purpose of this study is to develop an assessment of the answers. Automated short answer scoring is designed to automatically grade and evaluate students' answers based on a series of trained answer documents.Methods: This is ‘how’ you did it. Let readers know exactly what you did to reach your results. For example, did you undertake interviews? Did you carry out an experiment in the lab? What tools, methods, protocols or datasets did you use The method used is TF-IDF-DF and Similarity and scoring computation. Theword weight used is the term Frequency-Inverse Documents Frequency -Document Frequency (TF-IDF-DF) method. The data used is 5 questions with each question answered by 30 students, while the students' answers are assessed by teachers/experts to determine the real score. The study was evaluated by Mean Absolute Error (MAE).Result: The evaluation results obtained Mean Absolute Error (MAE) with a resulting value of 0.123.Value: The word weighting method used is the Term Frequency Inverse Document Frequency DocumentFrequency (TF-IDF-DF) which is an improvement over the Term Frequency Inverse Document Frequency (TF-IDF) method. This method is a method of weighting words that will be applied before calculating the similarity of sentences between teachers and students.

show abstract

“…The emerging of recent studies incorporating the hybrid framework have been seen the combining the use of linear regression on selected features, derived from an ontology and using LSA to measure content similarity (Contreras et al, 2018), generalizing essay scores through vectorization with artificial neural network and LSA (Loraksa & Peachavanish, 2007) and twostep process classification with SVM and LSA Framework (Ratna et al, 2019a;Ratna, et al, 2019b) The studies reported in Ratna et al (2019c) used two-step grading process as the HF: used Support Vector Machine (SVM) to classify essay's topic and LSA to compute the similarity between student and key answers. A pre-trained SVM model on key answers' topics is meant to rule out unrelated topic essays and to route it to the related key answers Find the most similar content score essay.…”

Section: Hybrid Frameworkmentioning

confidence: 99%

“…The studies report substantial accuracy (>95%) as compared to human raters. The workflow of hybrid framework reported in Ratna et al (2019c) is illustrated in Figure 6.…”

Section: Hybrid Frameworkmentioning

confidence: 99%

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

Lim¹,

Bong²,

Wong³

et al. 2021

JST

View full text Add to dashboard Cite

Automated Essay Scoring (AES) is a service or software that can predictively grade essay based on a pre-trained computational model. It has gained a lot of research interest in educational institutions as it expedites the process and reduces the effort of human raters in grading the essays as close to humans’ decisions. Despite the strong appeal, its implementation varies widely according to researchers’ preferences. This critical review examines various AES development milestones specifically on different methodologies and attributes used in deriving essay scores. To generalize existing AES systems according to their constructs, we attempted to fit all of them into three frameworks which are content similarity, machine learning and hybrid. In addition, we presented and compared various common evaluation metrics in measuring the efficiency of AES and proposed Quadratic Weighted Kappa (QWK) as standard evaluation metric since it corrects the agreement purely by chance when estimate the degree of agreement between two raters. In conclusion, the paper proposes hybrid framework standard as the potential upcoming AES framework as it capable to aggregate both style and content to predict essay grades Thus, the main objective of this study is to discuss various critical issues pertaining to the current development of AES which yielded our recommendations on the future AES development.

show abstract

Latent Semantic Analysis and Winnowing Algorithm Based Automatic Japanese Short Essay Answer Grading System Comparative Performance

Cited by 8 publications

References 6 publications

Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata

Penerapan Algoritma TF-IDF dan Cosine Similarity untuk Query Pencarian Pada Dataset Destinasi Wisata

Automatic Scoring Using Term Frequency Inverse Document Frequency Document Frequency and Cosine Similarity

A Comprehensive Review of Automated Essay Scoring (AES) Research and Development

Contact Info

Product

Resources

About