Artificial Intelligence in Computerized Adaptive Testing

Mujtaba, Dena F.; Mahapatra, Nihar R.

doi:10.1109/csci51800.2020.00116

Cited by 11 publications

(9 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine Learning (ML), particularly through its branches such as deep learning and reinforcement learning, is revolutionizing CAT by enabling sophisticated analysis of large datasets, detailed behavior modeling, and flexible adaptation to diverse testing environments [179]. Despite the ML in CAT is still in its early stages, its potential is evident, with deep learning, natural language processing, and reinforcement learning showing significant promise in enhancing question characterization, scoring processes, and adaptive modeling [117]. This survey aims to provide an overview and understanding of traditional statistical-based and recent ML-based CAT.…”

Section: Background Of Catmentioning

confidence: 99%

“…Machine learning [82], with its ability to learn from data and make precise predictions, offers a viable solution to enhance test efficiency and accuracy within this volatile environment. Previous CAT surveys [24,36,117,156] have largely revolved around the domains of statistics and psychometrics. Given CAT's interdisciplinary nature, this paper seeks to understand and review methodologies from a machine-learning perspective, which is more approachable to a wider readership and sheds light on building strong CAT systems.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Background Of Catmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…Of course, the applications described above are only a small selection of possible applications of ML in the area of psychological assessment and test construction. Others, for example, include enhancing item response modeling and CAT using ML and AI techniques such as deep learning, reinforcement learning, and (Bayesian) optimal experimental design (Keurulainen et al, 2023; Mujtaba & Mahapatra, 2020). Current hindrances to the use of ML in psychological assessment and test construction include a lack of transparency and interpretability (“black box models”) and – especially in the case of CDSS – a lack of trust in AI-based systems.…”

Section: Discussionmentioning

confidence: 99%

The Potential of Machine Learning Methods in Psychological Assessment and Test Construction

Bißantz,

Frick,

Melinscak

et al. 2024

European Journal of Psychological Assessment

View full text Add to dashboard Cite

“…This study also investigated the potential and educational implications of AI-based online assessment. Dealing with education technology, according to Mujtaba & Mahapatra (2020); Zhu (2020), the use of technology in education can provide a more efficient and effective way to assess student learning, as well as improve the quality of instruction. This sentiment is supported by the findings of the current study, which suggest that the AI-based online testing platform was effective in assessing the knowledge of ESP students in Economic Sharia Law.…”

Section: Discussionmentioning

confidence: 99%

Classtime.Com as an Ai-Based Testing Platform: Analysing ESP Students’ Performances and Feedback

Ningsih

2023

JOLLT

View full text Add to dashboard Cite

The use of Artificial Intelligence (AI) technology in education has grown in popularity, especially in online assessments. This research evaluates the effectiveness of an AI-based online testing platform, Classtime.com, in teaching tenses in English for Specific Purposes (ESP). The study uses a mixed-methods approach, collecting data from 246 Economic Sharia Law students who took the midterm exam during the 2022-2023 school year. The results show that the average score on the exam was 88.21, indicating a high overall performance. Females scored higher and more consistently than males. The study suggests that Classtime.com's AI-based testing is an effective tool for teaching tenses in ESP assessment, providing immediate feedback and personalized learning experiences. However, the study's focus on one language subject limits its generalizability to other subjects. Nevertheless, the use of AI-based online testing in ESP assessment can improve language learning outcomes and contribute to effective teaching practices. Future research should explore the use of AI-based online testing platforms in other language subjects, investigate factors influencing student performance, and examine long-term effects on language learning outcomes and attitudes toward language education and assessment.

show abstract

Artificial Intelligence in Computerized Adaptive Testing

Cited by 11 publications

References 28 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

The Potential of Machine Learning Methods in Psychological Assessment and Test Construction

Classtime.Com as an Ai-Based Testing Platform: Analysing ESP Students’ Performances and Feedback

Contact Info

Product

Resources

About