Course selection is a crucial activity for students as it directly impacts their workload and performance. It also time-consuming, prone to subjectivity, often carried out based on incomplete information. This task can, nevertheless, be assisted with computational tools, instance, by predicting performance historical data. We investigate the effects of showing grade predictions through an interactive visualization tool. A qualitative study suggests that in presence predictions, may focus too...

Abstract This study investigates the effects of using design thinking on students’ problem solving and creativity skills, applying a constructivist learning theory. A course where students use for analyzing real problems proposing solution, was evaluated. The involved 910 novice university from different disciplines who worked in teams throughout semester. Data were collected at three times during semester, i.e. beginning (t0), middle (t1) end (t2), after short case study. Each time skill...

Abstract Universities are looking for solutions to engage more students in STEM domains and enhance their learning performance (LP). In this context, gamification is put forward as a solution achieve aim. The present study examined the effect of – building on leaderboards ‐ LP. Furthermore, mediating variables, such intrinsic motivation, self‐efficacy, engagement, background sex, previous gaming experience, undergraduate major, were considered. A pretest‐posttest quasi‐experimental design...

Data science is now impacting the education sector, with a growing number of commercial products and research prototypes providing learning dashboards. From human-centred computing perspective, end-user's interpretation these visualisations critical challenge to design for, empirical evidence already showing that `usable' are not necessarily effective from perspective. Since an educator's visualised data essentially construction narrative about student progress, we draw on body work...

From a human-centred computing perspective, supporting the interpretation of educational dashboards and visualizations by people intended to use them exposes critical design challenges that may often be trivialized. Empirical evidence already shows “usable” are not necessarily effective from an perspective. Since educator’s visualized data is essentially construction narrative about student progress, in this paper, we propose concept “Educational Data Storytelling” as approach for explaining...

Multimodal Learning Analytics is a field that studies how to process learning data from dissimilar sources in order automatically find useful information give feedback the process. This work processes video, audio and pen strokes included Math Data Corpus, set of multimodal resources provided participants Second International Workshop on Analytics. The result this processing simple features could discriminate between experts non-experts groups students solving mathematical problems. main...

The demand for professionals with expertise in Science, Technology, Engineering, and Mathematics (STEM) continues to grow. To meet this demand, universities are actively seeking strategies engage more students STEM disciplines improve their learning outcomes. One promising approach is gamification, specifically using leaderboards. This study investigates the impact of leaderboard-based gamification on performance 175 a calculus course, focus mediating roles autonomous motivation...

Learning analytics has been as used a tool to improve the learning process mainly at micro-level (courses and activities). However, another of key promises Analytics research is create tools that could help educational institutions meso- macro-level gain better insight inner workings their programs, in order tune or correct them. This work presents set simple techniques applied readily available historical academic data provide such insights. The described are real course difficulty...

This paper identifies, by means of video and Kinect data, a set predictors that estimate the presentation skills 448 individual students. Two evaluation criteria were predicted: eye contact posture body language. Machine-learning evaluations resulted in models predicted performance level (good or poor) presenters with 68% 63% correctly classified instances, for postures language criteria, respectively. Furthermore, results suggest certain features, such as arms movement smoothness, provide...

This study examines the effects of a design thinking intervention on first-year students’ teamwork skills from multi-actor perspective. A course was evaluated throughout semester. Six-hundred-and-forty university students participated, guided by twenty-six facilitators. The received in-class training and worked in multi-disciplinary teams to develop solution for real-life problem. In this quasi-experimental study, data were collected twice: middle (t1), at end (t2) course. Each time, rated...

One of the key promises Learning Analytics research is to create tools that could help educational institutions gain a better insight inner workings their programs, in order tune or correct them. This work presents set simple techniques applied readily available historical academic data provide such insights. The described are real course difficulty estimation, dependance curriculum coherence, dropout paths and load/performance graph. description these accompanied by its application from...

This paper proposes a simple estimation of the quality student oral presentations. It is based on study and analysis features extracted from audio digital slides 448 The main goal this work to automatically predict values assigned by professors different criteria in presentation evaluation rubric. Machine Learning methods were used create several models that classify students two clusters: high low performers. created slide accurate up 65%. most relevant for slide-base were: number words,...

This paper summarizes the third Multimodal Learning Analytics Workshop and Grand Challenges (MLA'14). subfield of focuses on interpretation multimodal interactions that occurs in learning environments, both digital physical. is a hybrid event includes presentations about methods techniques to analyze merge different signals captured from these environments (workshop session) more concrete results application predict performance students while solving math problems or presenting classroom...

The present study underpins the design and validation of a Financial Literacy (FL) scale in Latin American Caribbean (LAC) context. Though scales are available, they do not meet contextual characteristics seem to miss out on focus Key Decisions (KFD). Scale was consistent with an extensive literature review (2010–2021). Forty-four items covering dimensions Attitude, Behavior, Knowledge were presented 478 young adults aged 18–30, women 58% them. results reflect robust FL by applying...

The traditional recording of student interaction in classrooms has raised privacy concerns both students and academics. However, the same are happy to share their daily lives through social media. Perception data ownership is key factor this paradox. This article proposes design a personal Multimodal Recording Device (MRD) that could capture actions its owner during lectures. MRD would be able close-range video, audio, writing, other environmental signals. Differently from centralized...

Academic advising brings numerous benefits to the mission of Higher Education Institutions. One central and challenging duty advisors is course recommendation for term planning. This task requires both knowledge study programs as well a thorough analysis students' unique circumstances. Limited time large student population make this overwhelming. As result, an important body research has sought expedite planning via data-oriented decision-support tools. The impact such tools on students been...

Abstract Design Thinking (DT) is considered an innovative and effective pedagogical approach. To enhance the understanding of instructional strategies used by university DT facilitators, we developed Facilitation Behaviour List, instrument that matches with observable behaviours in a course. We present design process validation instrument. Results show instrument's effectiveness capturing course, paving way for future research improved teaching practices.

Course selection is a crucial activity for students as it directly impacts their workload and performance. It also time-consuming, prone to subjectivity, often carried out based on incomplete information. This task can, nevertheless, be assisted with computational tools, instance, by predicting performance historical data. We investigate the effects of showing grade predictions through an interactive visualization tool. A qualitative study suggests that in presence predictions, may focus too...