UKARA: A Fast and Simple Automatic Short Answer Scoring System for Bahasa Indonesia

Herwanto, Guntur Budi; Sari, Yunita; Prastowo, Bambang Nurcahyo; Bustoni, Isna Alfi; Hidayatulloh, Indra

doi:10.26499/iceap.v2i1.95

Cited by 11 publications

(11 citation statements)

References 6 publications

(8 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, adding more types of questions besides multiple choices, such as short essays, might enrich the user's learning experience. The implementation of an automatic essay scoring system [10,11] can be used to evaluate the short answer of the player in this game.…”

Section: Discussionmentioning

confidence: 99%

Designing of english challenge mobile game application as the media of english language learning

Setyadharma¹,

Iryanti²,

Hidayatulloh

et al. 2020

JEATech

Self Cite

View full text Add to dashboard Cite

English became the first foreign language that came to Indonesia in 1967. The human needs of English can already be seen through lots of official scientific works in English and its intense competitions globally. However, still, many people finds it difficult to learn English, for example, the difficulty in understanding tenses, differences between writing, reading and pronouncing. By relying on the latest features on smartphone, which on the mean time, smartphone is one of many gadgets that is the most practical to use in anywhere and anytime, plus, with gaming contents as the best multimedia entertainer application, learning English will be more interactive and easier to use. In this research, Construct 2 is used as The Developer App and Game Development Life Cycle (GDLC) method of Rido Ramadan and Yani Widyani’s version is used as The Development Method. The game system tested by using black box and by giving out Questionnaire for User Interface Satisfaction to 24 respondents, to test the system’s usability. It resulted 80,83% for the whole of the system, meaning that the whole system is quiet interesting in the respondents’s view. Then, the screen display gained 80,41%, this means that the screen display is very interesting and did not confuse the respondents. Technology and information game gained 75,41%, this means that the information contained in the game is quiet good, however, further development is needed. The introduction of the game’s system gained 71,63%, means that some of the system’s ability did not run effectively and needed further repairment and development. The last, usability and user interface gained 76,25%, this means that the game is quiet interactive to the respondents.

show abstract

Section: Discussionmentioning

confidence: 99%

Designing of english challenge mobile game application as the media of english language learning

Setyadharma¹,

Iryanti²,

Hidayatulloh

et al. 2020

JEATech

Self Cite

View full text Add to dashboard Cite

show abstract

“…Towards realizing the practical use of SAS systems in the real world, several researchers have explored outputting useful feedback for an input response [21], utilizing rubrics for scoring [19], and investigating adversarial input in SAS [4], to name a few. In addition, research on various languages has also been reported in recent years, including Indonesian [7], Korean [9], and Japanese [15].…”

Section: Previous Researchmentioning

confidence: 99%

Balancing Cost and Quality: An Exploration of Human-in-the-Loop Frameworks for Automated Short Answer Scoring

Funayama

Sato

Matsubayashi

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Short answer scoring (SAS) is the task of grading short text written by a learner. In recent years, deep-learning-based approaches have substantially improved the performance of SAS models, but how to guarantee high-quality predictions still remains a critical issue when applying such models to the education field. Towards guaranteeing highquality predictions, we present the first study of exploring the use of human-in-the-loop framework for minimizing the grading cost while guaranteeing the grading quality by allowing a SAS model to share the grading task with a human grader. Specifically, by introducing a confidence estimation method for indicating the reliability of the model predictions, one can guarantee the scoring quality by utilizing only predictions with high reliability for the scoring results and casting predictions with low reliability to human graders. In our experiments, we investigate the feasibility of the proposed framework using multiple confidence estimation methods and multiple SAS datasets. We find that our human-in-theloop framework allows automatic scoring models and human graders to achieve the target scoring quality.

show abstract

“…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.…”

Section: A Scoresmentioning

confidence: 99%

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

Hidayatulloh

Pambudi

Surjono

et al. 2021

ELINVO

Self Cite

View full text Add to dashboard Cite

The mobile learning sector has exploded, implying that the e-Learning trend is shifting to mobile platforms. As a result, chatbots have become increasingly popular alternatives for online learning and examinations on mobile platforms. However, it did not provide enough motivation for the student. On the other hand, gamification in a typical e-Learning platform is a widely used technique for increasing students' learning motivation. Therefore, combining gamification with chatbot-based learning and examinations possibly offer benefits, including increase student learning motivation. This study explored the possibilities and future challenges of the development of gamification within chatbot-based learning media. We discussed four aspects: architecture's reliability, security and privacy issue, user’s acceptance and motivation, and gamification feature challenges.

show abstract

UKARA: A Fast and Simple Automatic Short Answer Scoring System for Bahasa Indonesia

Cited by 11 publications

References 6 publications

Designing of english challenge mobile game application as the media of english language learning

Designing of english challenge mobile game application as the media of english language learning

Balancing Cost and Quality: An Exploration of Human-in-the-Loop Frameworks for Automated Short Answer Scoring

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

Contact Info

Product

Resources

About