Performance Factors Analysis (PFA) is considered one of the most important Knowledge Tracing (KT) approaches used for constructing adaptive educational hypermedia systems. It has shown a high ...prediction accuracy against many other KT approaches. While, the desire to estimate more accurately the student level leads researchers to enhance PFA by inventing several advanced extensions. However, most of the proposed extensions have exclusively been improved in a pedagogical sense, as the improvements have mostly been limited to the analysis of students' behaviour during their learning process. In contrast, Machine Learning provides many powerful methods that could be efficient to enhance, in the technical sense, the prediction of student performance. Our goal is to focus on the exploitation of Ensemble Learning methods as an extremely effective Machine Learning paradigm used to create many advanced solutions in several fields. In this sense, we propose a new PFA approach based on different models (Random Forest, AdaBoost, and XGBoost) in order to increase the predictive accuracy of student performance. Our models have been evaluated on three different datasets. The experimental results show that the scalable XGBoost has outperformed the other evaluated models and substantially improved the performance prediction compared to the original PFA algorithm.
Full text
Available for:
BFBNIB, NUK, PILJ, SAZU, UL, UM, UPUK
The Flipped Classroom design has arguably revolutionized teaching across the globe. In this article we report the first comprehensive meta-analysis of its effects on student performance, relative to ...traditional teaching models, across disciplines and education level. We included 198 studies comprising 33,678 students in our meta-analysis. There were 174 studies conducted at the tertiary level, 21 at secondary, and three at primary school level. Overall, the flipped classroom had a moderate positive effect (g = .50) on student performance. The flipped classroom was beneficial regardless of discipline, with effect sizes ranging from weak (i.e., for IT, g = 0.30; k = 14) to strong (i.e., for humanities, g = 0.98; k = 34). Testing of other moderators relating to group sizes, in-class activities, pre-class testing, and the sophistication of a flipped classroom design provide evidence to suggest that the primary contributing factor to the flipped classroom effect is the opportunity it provides for structured, active learning and problem-solving.
•Comprehensive meta-analysis of effects of flipped classroom vs traditional teaching on student performance (k = 198).•Positive moderate effect of flipped classrooms on student performance (g = 0.50).•The flipped classroom is beneficial regardless of discipline and education level.•Effect sizes range from weak (e.g., IT: g = 0.30; k = 14) to strong (e.g., humanities: g = 0.98; k = 34).•Analysis of moderators suggest key ingredient is opportunity for structured, active learning.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
The COVID-19 Pandemic has led to social isolation; however, with the help of technology, education can continue through this tough time. Therefore, this research attempts to explore the Unified ...Theory of Acceptance and Use of Technology (UTAUT) through the expansion of the model. Also, make it relevant to investigate the influence of social isolation, and the moderating role of Corona fear on Behavioral Intention of the Learning Management System and its Use Behavior of Learning Management System among students. The data was analyzed using Partial Least Square (PLS) and Structural Equation Modelling (SEM). The findings show a positive link of Performance Expectancy (PE), Effort Expectancy (EE), Social Influence (SI), and Social Isolation on Behavioral Intention of LMS and, also between Behavioral Intention of LMS and its Use behavior. Moreover, the results of the moderation analysis show that Corona fears only moderates the link of Performance Expectancy and Social influence with Behavioral Intention of LMS. The findings imply the need for improving the LMS experience to increase its Behavioral Intention among students. Finally, the author's recommendation for future researchers is to examine the extended model in other countries and territories to analyze Coronavirus's influence on e-learning acceptance.
Full text
Available for:
NUK, OILJ, SAZU, UKNU, UL, UM, UPUK
Student engagement is widely recognised as an important influence on achievement and learning in higher education and as such is being widely theorised and researched. This article firstly reviews ...and critiques the four dominant research perspectives on student engagement: the behavioural perspective, which foregrounds student behaviour and institutional practice; the psychological perspective, which clearly defines engagement as an individual psycho-social process; the socio-cultural perspective, which highlights the critical role of the socio-political context; and, finally, the holistic perspective, which takes a broader view of engagement. Key problems are identified, in particular poor definitions and a lack of distinction between the state of engagement, factors that influence student engagement, and the immediate and longer term consequences of engagement. The second part of the article presents a conceptual framework that overcomes these problems, incorporating valuable elements from each of the perspectives, to enable a better shared understanding of student engagement to frame future research and improve student outcomes.
Full text
Available for:
BFBNIB, DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Researchers recognize adaptive teaching as a component of effective instruction. Educators adjust their teaching according to the social, linguistic, cultural, and instructional needs of their ...students. While there is consensus that effective teachers are adaptive, there is no consensus on the language to describe this phenomenon. Diverse terminology surrounding the same phenomenon impedes effective communication and comprehensive understanding of this important aspect of classroom instruction. Moreover, researchers have studied this phenomenon using a variety of methods, in various disciplines, with different results. Therefore, our research team completed a comprehensive literature review of the empirical research studying adaptability across academic disciplines. In this article, we describe how adaptive teaching is defined and conceptualized in the education research literature from 1975 to 2014, the methods used to study instructional adaptations, and the results of these studies.
Full text
Available for:
BFBNIB, NMLJ, NUK, OILJ, PNG, SAZU, UKNU, UL, UM, UPUK
Peer assessment has been the subject of considerable research interest over the last three decades, with numerous educational researchers advocating for the integration of peer assessment into ...schools and instructional practice. Research synthesis in this area has, however, largely relied on narrative reviews to evaluate the efficacy of peer assessment. Here, we present a meta-analysis (54 studies,
k
= 141) of experimental and quasi-experimental studies that evaluated the effect of peer assessment on academic performance in primary, secondary, or tertiary students across subjects and domains. An overall small to medium effect of peer assessment on academic performance was found (
g
= 0.31,
p
< .001). The results suggest that peer assessment improves academic performance compared with no assessment (
g
= 0.31,
p
= .004) and teacher assessment (
g
= 0.28,
p
= .007), but was not significantly different in its effect from self-assessment (
g
= 0.23,
p
= .209). Additionally, meta-regressions examined the moderating effects of several feedback and educational characteristics (e.g., online vs offline, frequency, education level). Results suggested that the effectiveness of peer assessment was remarkably robust across a wide range of contexts. These findings provide support for peer assessment as a formative practice and suggest several implications for the implementation of peer assessment into the classroom.
Full text
Available for:
BFBNIB, DOBA, EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, IZUM, KILJ, KISLJ, MFDPS, NLZOH, NMLJ, NUK, OBVAL, OILJ, PILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, SIK, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
Educational institutions and governing practices are increasingly augmented with digital database technologies that function as new kinds of policy instruments. This article surveys and maps the ...landscape of digital policy instrumentation in education and provides two detailed case studies of new digital data systems. The Learning Curve is a massive online data bank, produced by Pearson Education, which deploys highly sophisticated digital interactive data visualizations to construct knowledge about education systems. The second case considers 'learning analytics' platforms that enable the tracking and predicting of students' performances through their digital data traces. These digital policy instruments are evidence of how digital database instruments and infrastructures are now at the centre of efforts to know, govern and manage education both nationally and globally. The governing of education, augmented by techniques of digital education governance, is being distributed and displaced to new digitized 'centres of calculation', such as Pearson and Knewton, with the technical expertise to calculate and visualize the data, plus the predictive analytics capacities to anticipate and pre-empt educational futures. As part of a data-driven style of governing, these emerging digital policy instruments prefigure the emergence of 'real-time' and 'future-tense' techniques of digital education governance.
Full text
Available for:
BFBNIB, NUK, PILJ, SAZU, UL, UM, UPUK
Given their increasing number and the implementation of more energy-intensive treatment methods, wastewater treatment plants (WWTPs) expect to increase energy consumption. In addition, climate change ...presents new challenges to the operation of these facilities, thus being critical to understand how to improve their energy performance and environmental sustainability while ensuring the quality of service provided. This paper reviews the latest publications on the energy performance of municipal WWTPs, particularly on the different phases of the treatment process and the impacting factors. The contextual and underlying factors that influence energy performance were identified, categorized, and analyzed through a broad survey. The most significant factors are the plant size, load factor (plant capacity utilization), and dilution factor. The implementation of anaerobic-anoxic-oxic systems is considered suitable in sensitive areas requiring high pollutant and nutrient removal rates, presenting, in some cases, moderate energy consumption (0.267 kWh/m3), being similar to the conventional activated sludge (0.269 kWh/m3). In more stringent effluent quality requirements, such as wastewater reuse, membrane bioreactors are advised, despite higher consumption (0.33 kWh/m3). Energy improvements can also be achieved by implementing automatization, inverters, and strategies that increase flexibility and adaptability in the operational process. Lastly, given the multidimensional characteristics of the WWTPs assessment, further improvements may be identified if the energy performance of these plants is compared using holistic and multi-criteria approaches, integrating multiple inputs and outputs simultaneously.
•Long-term operation of low installed power equipment deserves more attention.•Energy intensity is mainly influenced by plant's size, load, and influent dilution.•Anaerobic-anoxic-oxic systems are a good option for impoverished areas.•Energy performance must be assessed in a holistic and multi-criteria approach.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Educational researchers and practitioners assert that supportive school and classroom climates can positively influence the academic outcomes of students, thus potentially reducing academic ...achievement gaps between students and schools of different socioeconomic status (SES) backgrounds. Nonetheless, scientific evidence establishing directional links and mechanisms between SES, school climate, and academic performance is inconclusive. This comprehensive review of studies dating back to the year 2000 examined whether a positive climate can successfully disrupt the associations between low SES and poor academic achievement. Positive climate was found to mitigate the negative contribution of weak SES background on academic achievement; however, most studies do not provide a basis for deducing a directional influence and causal relations. Additional research is encouraged to establish the nature of impact positive climate has on academic achievement and a multifaceted body of knowledge regarding the multilevel climate dimensions related to academic achievement.
Full text
Available for:
BFBNIB, NMLJ, NUK, OILJ, PNG, SAZU, UKNU, UL, UM, UPUK
Based on recent findings about teacher learning, a critical analysis of traditional and new approaches to professional development is presented. To a large degree, teacher learning takes place ...unconsciously and involves cognitive, emotional and motivational dimensions. Moreover, teacher learning takes place at various levels. Although these insights may be inconvenient truths to policy-makers, empirical evidence is presented showing that approaches building on the multi-level and multi-dimensional nature of teacher learning are effective at influencing teacher behaviour. Hence, in teacher learning, the connection with the person of the teacher is crucial. Practical consequences for professional development are discussed.
Full text
Available for:
BFBNIB, NUK, PILJ, SAZU, UL, UM, UPUK
PDF
