Research has paid less attention to the formalization of education from a systems theory and control perspective, rather than a mere algorithmic one. In this work, the underpinnings of system theory and control are provided, along with a review of their application in education. The review of studies in databases found only seven articles that…

Missing data presents a significant challenge in Educational Data Mining (EDM). Imputation techniques aim to reconstruct missing data while preserving critical information in datasets for more accurate analysis. Although imputation techniques have gained attention in various fields in recent years, their use for addressing missing data in…

The growing popularity of generative artificial intelligence (AI) tools presents new challenges for data quality in online surveys and experiments. This study examines participants' use of large language models to answer open-ended survey questions and describes empirical tendencies in human versus large language model (LLM)-generated text…

Large language models (LLMs), through their exposure to massive collections of online text, learn to reproduce the perspectives and linguistic styles of diverse social and cultural groups. This capability suggests a powerful social scientific application--the simulation of empirically realistic, culturally situated human subjects. Synthesizing…

The integration of artificial intelligence (AI), and particularly generative AI, into research methods is rapidly transforming both academic and industry marketing research, including both methods practices and education regarding these practices. AI application within methods offers new opportunities for enhancing efficiency, automating…

Although there is growing social science research examining how generative AI models can be effectively and systematically applied to text-based tasks, whether and how these models can be used to analyze images remain open questions. In this article, we introduce a framework for analyzing images with generative multimodal models, which consists of…

Purpose: This paper aims to explore how an academic researcher and a practitioner experience scepticism for their qualitative research. Design/methodology/approach: The study applies Olt and Teman's new conceptual phenomenological polyethnography (2019) methodology, a hybrid of phenomenology and duoethnography. Findings: For the…

Asymmetric Likert-type items in research studies can present several challenges in data analysis, particularly concerning missing data. These items are often characterized by a skewed scaling, where either there is no neutral response option or an unequal number of possible positive and negative responses. The use of conventional techniques, such…

RobotReviewer is a tool for automatically assessing the risk of bias in randomized controlled trials, but there is limited evidence of its reliability. We evaluated the agreement between RobotReviewer and humans regarding the risk of bias assessment based on 1955 randomized controlled trials. The risk of bias in these trials was assessed via two…

Background: Randomized controlled trials (RCTs) give unbiased estimates of average effects. However, positive effects for the majority of students may mask harmful effects for smaller subgroups, and RCTs often have too small a sample to estimate these subgroup effects. In many RCTs, covariate and outcome data are drawn from a larger database. For…

In education, machine learning (ML), especially deep learning (DL) in recent years, has been extensively used to improve both teaching and learning. Despite the rapid advancement of ML and its application in education, a few challenges remain to be addressed. In this thesis, in particular, we focus on two such challenges: (i) data scarcity and…

The versatility of ChatGPT extends across diverse domains, including scientific research. This study delves into the transformative prospects of integrating ChatGPT into scientific research, achieved through a SWOT analysis. The analysis explores the model's strengths, which encompass a vast knowledge base, language proficiency, information…

Constant changes to COVID-19 restrictions have required adaptability from social scientists including responding to new challenges such as infiltration by bots. This research note presents unexpected encounters of bot infiltration and recruitment during survey data collection under pandemic conditions. The note draws from a household survey on a…

This dissertation developed a new learner corpus of Japanese and introduced an error and linguistic annotation scheme specifically designed for Japanese particles. The corpus contains texts written by learners who are in the first year to fourth year university level Japanese courses. The texts in the corpus were tagged with part-of-speech and…

We encounter variables with little variation often in educational data mining (EDM) due to the demographics of higher education and the questions we ask. Yet, little work has examined how to analyze such data. Therefore, we conducted a simulation study using logistic regression, penalized regression, and random forest. We systematically varied the…