In the field of learning analytics, mining regularities social interaction and cognitive processing have drawn increasing attention. Nevertheless, in MOOCs, there is a lack investigations on combination behavioral patterns. To fill this gap, study aimed to uncover relationship between interaction, processing, achievements MOOC discussion forum. Specifically, we collected 3925 participants’ forum data throughout 16 weeks. Social network analysis epistemic were jointly adopted investigate...

Dialogue datasets are essential for advancing natural language processing (NLP) tasks. However, many existing lack integrated annotations personality and emotion, limiting models' ability to effectively capture these aspects generate personalized, human-like dialogues, which ultimately impact user experience. To address this challenge, we construct bilingual dialogue in Chinese English, incorporating Big Five traits emotion annotations. We utilize the AutoGen tool within a multi-agent...

Forum discussions in Massive Open Online Courses (MOOCs) play a crucial role promoting learning engagement and academic achievement. In particular, discussion topics significantly influence learners’ emotional cognitive engagement. However, the complex interrelationships among these factors remain underexplored. This study introduces an innovative two-step methodological approach to investigate relationships between topic complexity, engagement, achievement MOOC discussions. Using BERT for...

Massive Open Online Course (MOOC) has been drawn much attention from learners and teachers through the world. MOOC offers a variety of interactive ways, in which course comment panel is used for express students' opinions feelings. These comments generally contain some learning problems, attitudes towards or platform support, etc. The feedback information beneficial exchange ideas among teachers, educational administrators. However, it quite time-consuming to analyze these important entirely...

Course reviews, which is designed as an interactive feedback channel in Massive Open Online Courses, has promoted the generation of large-scale text comments. These data, contain not only learners' concerns, opinions and feelings toward courses, instructors, platforms but also interactions (e.g., post, reply), are generally subjective extremely valuable for online instruction. The purpose this study to automatically reveal these potential information from 50 courses by improved unified topic...

Unlike the other studies on emotional design in multimedia learning, present study differentiated two confounding variables of visual interface and structured content to manipulate instructional material. Specifically, we investigated how aesthetics positive influenced learners' cognitive processes, valences, learning outcomes, subjective experience. Eighty-one college students took part experimental study. They were divided into three groups: a holistic layout group (HPED), local (LPED),...

Abstract Studying the networked nature of social and cognitive aspects learner interactions is key to understanding how successful collaborative learning occurs in asynchronous online discussion forums (AODFs). Guided by network science multiplex analysis, this study compared differences structure properties between (learners as nodes commenting on others' contributions edges) explicitly quoting networks within an AODF. It additionally examined individual measures these two monolayer their...

Abstract Due to an overwhelming amount of student-generated forum posts in small private online courses (SPOCs), students and instructors find it time-consuming challenging effectively navigate track valuable information, such as the evolution topics, emotional behavioral changes relation topics. For solving this problem, study analyzed plenty discussion using improved dynamic topic model, Time Information-Emotion Behavior Model (TI-EBTM). Time, emotion, behavior characteristics were...

A growing body of research has documented that artificial intelligence (AI) the potential to facilitate teaching analysis. However, few studies investigated teachers' attitudes toward AI-based analysis systems. As a tool for analyzing and evaluating quality, willingness use systems will undoubtedly affect application effect Considering evaluative properties intelligent nature systems, we proposed an integrated model by extending technology acceptance with fear evaluation theory trust in AI....

Massive open online courses (MOOCs) provide learners with high-quality learning resources, but drop out frequently. Learners' concerns (e.g. the topics in course content or logistics) and cognitive engagement patterns tentative certain) are considered essential factors affecting learners' completions. However, it is still unclear what different achievement groups focus on each pattern. In this study, we adopted an unsupervised computational model, temporal topic model (TCTM), to...

In a MOOC environment, each student's interaction with the course content is crucial clue for learning analytics, which offers an opportunity to record learner activity of unprecedented scale. online learning, educators and administrators need get informed students' states since performance unsupervised style difficult control. Learning analytics considered as key process provide students evidence-based, analytical contextual outcomes in way making sense their engagements. this conceptual...

Nowadays, Massive Open Online Courses (MOOC) has obtained a rapid development and drawn much attention from the areas of learning analytics artificial intelligence. There are lots unstructured data being generated in online reviews area. The behavioral become more diverse, they prompt emergence big education. To mine useful information these data, we need to use educational mining analysis technique study feelings discussed topics among learners. This paper aims analyze topic hidden MOOC,...

Currently, with the increasing advancement of interactive learning technologies in MOOCs, a large number student-generated comments (SGCs) have been substantially produced two primary emotions (positive and negative). The emotional orientations are typically related specific topics or aspects discussed, which is value to offer abundant academic feedbacks for teachers developers. Especially, negative emotion can be exploited get an in-depth insight problems barriers encountered by learners...

Large quantities of textual posts are increasingly generated in course discussion forums, and the accumulation these data greatly increases cognitive loads on online participants. It is imperative for them to automatically identify potential semantic information derived from discourse interactions. Moreover, existing topic models can discover latent topics or sentimental polarities data, but typically ignore interactive ways discussing topics, thus making it difficult further construct...

The design of social learning analytics (SLA) tools has become a practical means to make available information with goal improve students' regulation, reflection, and engagement in online learning. This design-based research uses the multi-method iteratively design, implement, modify SLA tool that makes social, topic, cognitive students discussions. demonstrates discussions from sematic, aspects. further questionnaire interview methods investigate perceptions about tool's usefulness...

In the discussion forums of massive open online courses (MOOCs), cognitive processing (e.g., insight, certain) is considered an essential factor that can affect learners' learning outcomes, but relationship between them has not been thoroughly investigated. Especially dynamic nature still a significant research gap. this study, we proposed unsupervised topic model named Temporal Cognitive Topic Model (TCTM) to automatically classify processes and obtain conditional probability with topics...

Abstract Background Smart classroom environment has drawn worldwide attention, however, there is still a lack of studies that can explore and analyse potential factors, which affect students' satisfaction with smart classrooms in higher education. Objectives To assess education, this study proposed the model based on TAM ACSI models. Methods A sample 1979 Chinese college students who studied completed survey assessing student environment. And structural equation modelling analysis was used...