Feedback is an essential component of scaffolding for learning. provides insights into the assistance learners in terms achieving learning goals and improving self-regulated skills. In online courses, feedback becomes even more critical since instructors students are separated geographically physically. this context, allows instructor to customize content according students' needs. However, giving a challenging task instructors, especially contexts large cohorts. As result, several automatic...

The explosive growth of online education environments is generating a massive volume data, specially in text format from forums, chats, social networks, assessments, essays, among others. It produces exciting challenges on how to mine data order find useful knowledge for educational stakeholders. Despite the increasing number applications mining published recently, we have not found any paper surveying them. In this line, work presents systematic overview current status Educational Text...

Open-ended assessments play a pivotal role in enabling instructors to evaluate student knowledge acquisition and provide constructive feedback. Integrating large language models (LLMs) such as GPT-4 educational settings presents transformative opportunity for assessment methodologies. However, existing literature on LLMs addressing open-ended questions lacks breadth, relying limited data or overlooking question difficulty levels. This study evaluates GPT-4's proficiency responding spanning...

Learning analytics aims to analyze data from students and learning environments support at different levels. Although is a recent field, it reached high level of maturity, especially in its applications for higher education. However, little the research targets other educational levels, such as school. This paper reports results systematic literature review (SLR) focused on adoption schools. More specifically, SLR followed four steps: search, selection relevant studies, critical assessment,...

This paper presents an approach to automatic labeling of the content messages in online discussion according categories social presence. To achieve this goal, proposed is based on a combination traditional text mining features and word counts extracted with use established linguistic frameworks (i.e., LIWC Coh-metrix). The best performing classifier obtained 0.95 0.88 for accuracy Cohen's kappa, respectively. also provides some theoretical insights into nature presence by looking at...

Feedback is a crucial element of student's learning process. It enables students to identify weaknesses and improve self-regulation. However, studies show this be an area great dissatisfaction in higher education. With ever-growing course participation numbers, delivering effective feedback becoming increasingly challenging task. The efficacy will depend on four levels feedback; namely, about the self, task, process or Hence, paper explores use automated content analysis examine provided by...

Abstract Researchers are increasingly interested in enabling teachers to monitor and adapt gamification design the context of intelligent tutoring systems (ITSs). These contributions rely on teachers’ needs preferences adjust according student performance. This work extends previous studies perception their cognitive effort dedication creating monitoring educational resource recommendations a simulated gamified platform. study compares perceptions workload using one three scenarios— manual,...

This paper presents a study that examined automated cross-language classification of online discussion messages for the levels cognitive presence, key construct from widely used Community Inquiry (CoI) model learning. Specifically, we 1,500 Portuguese language using classifier trained on corpus 1,747 English messages. In study, random forest was developed small set 108 validated indicators psychological processes, linguistic coherence, and structure. The obtained 67% accuracy Cohen's κ 0.32,...

In online learning, teachers need constant feedback about their students' progress and regulation needs. Learning Analytics Dashboards for process-oriented can be a valuable tool this purpose. However, few such dashboards have been proposed in literature, most of them lack empirical validation or grounding learning theories. We present teacher-facing dashboard co-designed evaluated through an iterative design process involving visualization experts. also reflect on our by discussing the...

Feedback plays a crucial role in student learning. Learning analytics (LA) has demonstrated potential addressing prominent challenges with feedback practice, such as enabling timely based on insights obtained from large data sets. However, there is insufficient research looking into relations between expectations of and their experience LA-based feedback. This paper presents pilot study that examined students' feedback, offered the OnTask system, taking consideration factors...

Textual cohesion is an essential aspect of a formally written text, related to linguistic mechanisms that connect elements such as words, sentences, and paragraphs. Several studies have proposed approaches estimate textual in essays automatically. There limited research aims study the extent which use machine learning can predict different languages (not just English). This paper reports on findings aimed propose evaluate automatically Portuguese English. The regression-based models grounded...

Feedback is an essential component of any learning experience. It allows students to identify gaps in their and improve self-regulation. However, providing useful feedback a challenging time-consuming task. In digital environments, this challenge even more significant due large number students. Thus, paper reports on the findings analysis quality provided by instructors online course. The also proposes supervised machine algorithm that can presence good practices messages sent environment....

Feedback is a crucial element in helping students identify gaps and assess their learning progress. In online courses, feedback becomes even more critical as it one of the resources where teacher interacts directly with student. However, growing number enrolled learning, challenge for instructors to provide good quality that helps student self-regulate. this context, paper proposed content analysis text provided by based on different indicators feedback. A random forest classifier was...

This article investigates the impact of educational contexts on automatic classification online discussion messages according to cognitive presence, an essential construct community inquiry model. In particular, work reported in analyzed written Brazilian Portuguese from two different courses that were subject areas (biology and technology) had teaching presence discussions. The study explored a set 127 features random forest classifier automatically recognize phases messages. results showed...

Learning analytics (LA) adoption is a challenging task for higher education institutions (HEIs) since it involves different aspects of the academic environment, such as information technology infrastructure, human resource management, ethics, and pedagogical issues. Therefore, necessary to provide with supporting instruments deal these challenges. Although there has been much research on factors that are associated LA in HEIs, less specific models can be used guide actual adoption. In this...

Abstract Background Study Peer feedback has been used as an effective instructional strategy to enhance students' learning in higher education. Objectives This paper reports on the findings of explorative study that aimed increase our understanding nature and role peer process a computer‐supported collaborative (CSCL) setting. Exploring what types are used, how they relate each other related academic performance important implications for students teachers. Methods was conducted education It...