scispace - formally typeset
Search or ask a question

How can predict academic performance of student based on digital learning behaviour? 

Best insight from top research papers

To predict academic performance based on digital learning behavior, several approaches have been proposed in the literature. One approach is to use data mining models that consider the weight of different features in academic performance prediction. These models measure the correlationship between each feature and academic performance and assign weights accordingly . Another approach is to employ machine learning algorithms, such as random forest, Bayesian ridge, adaptive boosting, and extreme gradient boosting, to generate predictions based on e-learning data . Additionally, the analysis of online learning behaviors, such as the number of completed assignments, live viewing rate, and replay viewing rate, has been found to be important in predicting academic performance . By combining these approaches, it is possible to accurately predict academic performance based on digital learning behavior and provide targeted support to students at risk of academic failure .

Answers from top 5 papers

More filters
Papers (5)Insight
The paper proposes using machine learning techniques to predict academic performance based on digital learning behavior data collected from various sources on a university campus.
The paper proposes using machine learning models to predict academic performance based on online learning behaviors such as the number of completed assignments, live viewing rate, and replay viewing rate.
The paper uses regression machine learning algorithms, such as random forest and extreme gradient boosting, to predict students' academic performance based on e-learning data.
The paper proposes a data mining model that uses behavioral data from online education platforms to predict academic performance of undergraduates. The model considers the weight of different features and uses support vector machine (SVM) for prediction.
The paper proposes a data mining model that uses behavioral data from online education platforms to predict academic performance of undergraduates. The model measures the correlationship between each feature and academic performance and assigns weights to the features accordingly. The model is constructed based on the weighted multi-feature and support vector machine (SVM).

Related Questions

Impact of technology on the academic performance of students?4 answersThe impact of technology on the academic performance of students is a complex issue. While technology can serve as a facilitator for learning outcomes, improper utilization of technology can hinder effective learning. Mobile phone usage has both positive and negative effects on academic performance, with factors such as gender, age, and connection with the opposite sex influencing outcomes. A study conducted in Uruguay found that technology has a positive impact on the educational environment, improving effectiveness, didactic methods, and academic performance. Another study focused on the personal, emotional, and financial impact of technology on academic performance, with respondents strongly agreeing on the positive effects. However, excessive use of technology at school can lead to lower academic performance, highlighting the need for policy makers and instructors to ensure that technology does not interfere with the learning process.
What are the effects of using digital learning tools on the academic performance?4 answersThe use of digital learning tools has been found to have positive effects on academic performance. Research has shown that incorporating digital resources as part of an active learning proposal can improve the academic performance of future teachers and increase student engagement and participation. Additionally, the utilization of digital textbooks in classrooms has been found to improve students' academic outcomes, academic interest, and learning skills, particularly for low-achieving students. The development of digital technology has also led to the implementation of web-based learning models, which have been effective in improving students' academic performance. These findings highlight the potential of digital learning tools in enhancing academic performance and supporting effective teaching and learning practices.
What are the key academic behaviors that predict student success?3 answersKey academic behaviors that predict student success include exam taking behavior patterns, learning strategies and behaviors such as help-seeking, learning from errors, and reviewing previous mastered topics, and academic behaviors such as academic mindsets, academic perseverance, and social skills. These behaviors have been found to significantly impact student performance and achievement in various studies. By identifying and understanding these behaviors, educators and institutions can better support students in their learning journey and improve their chances of success.
How to improve students digital literacy correlates to their academic performance?5 answersImproving students' digital literacy is crucial for enhancing their academic performance. Research has shown that students' digital literacy competency positively correlates with their ability to perform academic presentation strategies in a digital literacy environment. Using android-based e-modules has been found to significantly enhance students' digital literacy, specifically in subjects like chemical bonding. Additionally, the implementation of online learning systems has been shown to improve students' literacy skills, including their ability to explain scientific phenomena, identify scientific issues, and interpret and use scientific evidence. Furthermore, there is a high positive correlation between students' digital literacy and their academic writing performance in English as a Foreign Language (EFL) instruction. However, the effect of digital literacy on students' overall academic performance, as measured by their CGPA, appears to be insignificant. Therefore, to improve students' digital literacy and its correlation to academic performance, it is recommended to focus on specific subject areas, utilize effective digital learning tools, and integrate digital literacy skills into language instruction.
What is the relationship between digital literacy and students' academic performance?4 answersDigital literacy has a positive relationship with students' academic performance. It has been found that digital literacy improves students' abilities in learning, collaborating, and facing challenges in the digital age, resulting in better academic performance. Additionally, foreign graduate students' digital literacy competency has been found to positively impact their performance in academic presentations. Furthermore, the study suggests that students' information literacy skills, which are a component of digital literacy, are fairly good and contribute to their academic activities. Moreover, the study conducted among Vietnamese students found that higher levels of digital competence, including skills in understanding and using information, technology and computers, communication via e-learning, and effective use of images, are associated with higher study performance. Therefore, it can be concluded that digital literacy plays a significant role in students' academic performance.
What are the effects of digital feedback on student academic performance?4 answersDigital feedback has been found to have various effects on student academic performance. One study found that digital written feedback provided through a learning management system positively influenced students' learning experience and attitude toward learning, and predicted perceived achievement. Another study showed that an auto-feedback activity improved students' capacity for self-regulation and ultimately their academic performance. Additionally, research conducted at an online public school found that students who received digital feedback from teachers showed improvement in their task completions. Furthermore, personalized feedback delivered via digital score reports was found to have a positive impact on student performance, with students who reviewed the reports performing better on final exams. These findings suggest that digital feedback can play a significant role in enhancing student academic performance.

See what other people are reading

How can machine learning be used to improve sentiment analysis?
4 answers
Machine learning can be used to improve sentiment analysis by analyzing the emotions and attitudes expressed in human thinking. Different machine learning algorithms, such as Naive Bayes, SVM, RNNs, CNNs, and LSTM Networks, can be employed for sentiment analysis of data collected from social media platforms and online forums. These algorithms have varying performance depending on the type of data being analyzed, with some algorithms performing better for short texts like tweets and others for longer texts like news articles. Combining multiple algorithms can improve the accuracy of sentiment analysis. Machine learning methods can serve as a potent means of scrutinizing human thoughts and emotions, with implications for applications in marketing, politics, and mental health. Additionally, supervised Gradual Machine Learning (GML) approaches can effectively exploit labeled training data to improve knowledge conveyance in Aspect-Term Sentiment Analysis (ATSA). Sentiment analysis using machine learning techniques is also used to assess user comments and make judgments about their opinions, helping to address the information overload issue in online reviews.
What are the main threats to terrestrial orchids?
4 answers
The main threats to terrestrial orchids include plant collection for human use, wrong habitat management, disturbance to symbionts such as pollinators and mycorrhizal fungi, habitat destruction and fragmentation, climate change, pollution, transportation, disturbance/development for tourism and recreation activities, land clearing for shifting agriculture, and illegal collecting. These threats have led to a decline in wild orchid populations, with terrestrial orchids being particularly vulnerable. Terrestrial orchids have a long life cycle and are highly dependent on mycorrhizal fungi for germination and establishment. The loss of suitable habitats and the depletion of their fungal symbionts further contribute to their decline. Conservation efforts should focus on protecting local healthy populations, implementing sustainable plant collection practices, and addressing the broader threats of habitat destruction, climate change, and illegal collecting.
What are the consequences of inconsistent citations in scientific papers?
4 answers
Inconsistent citations in scientific papers can have several consequences. Firstly, it can lead to underrepresentation of important research networks, such as the Global Seismographic Network (GSN), which may impact operational decisions and funding support for the network. Secondly, inaccurate citations can perpetuate errors within the literature and mislead ongoing research. This can hinder the establishment of the current state of knowledge, identification of gaps in the literature, and proper interpretation and debate of research results. Additionally, chains of inaccurate citations can occur, where inaccurate citations are copied from previous papers, further propagating the inaccuracies. Inaccurate citations were found to be common in biomedical literature, with problems including citation of nonexistent findings and incorrect interpretation of findings. To address these issues, standardized policies, review processes, and actions by authors, mentors, and journals have been proposed.
What are the bias and discrimination of AI?
5 answers
Bias and discrimination in AI systems are significant concerns. Efforts to regulate bias and discrimination in AI systems focus on identifying and minimizing risks rather than outright prohibition. Conversational AI (CAI) in psychotherapy raises ethical risks, as CAI is an algorithm-based system that cannot have a real conversation or relationship. Algorithmic discrimination in AI algorithms manifests as feature-selective discrimination, associative discrimination, and big data-enabled price discrimination. Algorithmic bias in AI systems can generate unfair results and inequalities, potentially leading to discrimination. AI displays biases in the form of data input bias, algorithmic bias, and cognitive bias, influenced by ethnic, gender, intersectional, health, and social biases. These biases can perpetuate or amplify existing biases, highlighting the need for regulation and further research to understand and address AI biases.
What are the results of the clinical trial on meropenem?
4 answers
The clinical trial on meropenem showed that continuous administration of meropenem did not improve the composite outcome of mortality and emergence of pandrug-resistant or extensively drug-resistant bacteria at day 28 in critically ill patients with sepsis. Another study found that megadose meropenem can be considered safe for empirical treatment of nosocomial sepsis. Additionally, a randomized controlled trial is planned to compare the efficacy and safety of conventional regimen and model regimen for meropenem in pediatric severe pneumonia. Another study evaluated the bactericidal activity of meropenem at different doses and found that the World Health Organization-recommended total daily dose of 6 grams daily had greater bactericidal activity compared to a lower dose of 3 grams daily. However, the tolerability of intravenous meropenem, with amoxicillin/clavulanate, was poor at all doses, raising concerns about its utility in second-line regimens.
What are the main factors that influence the career choice of young physicians?
4 answers
The main factors that influence the career choice of young physicians include personal satisfaction, affluence, prestige, better patient outcomes, the diligence of lecturers, the need for work-life balance, and the quality of the clerkship experience. Academic interest and flexibility in working hours are also important factors that positively influence career choice. On the other hand, lack of interest in a particular specialty, perceived workload, and the duration of training schemes can negatively affect career choice. Gender also plays a significant role in influencing career choice among medical students. Mentorship, particularly from subspecialty mentors, is seen as a positive influence on career choice. Financial factors, however, do not seem to have a significant impact on career decisions.
What are the article all about?
4 answers
The articles cover a range of topics. One article discusses the development of a T cell bispecific antibody for the treatment of glioblastoma, a type of brain cancer. Another article focuses on a clinical trial of a novel inhibitor for the treatment of various malignancies in pet dogs. A third article explores the pharmacology and mechanism of action of a glutamine antagonist with potential for treating resistant tumors. The fourth article investigates the role of Wnt5A/FZD2 signaling in conferring resistance to a prostate cancer treatment and proposes a potential therapy targeting Wnt5A. The final article examines the efficacy of lenalidomide, an oral anti-inflammatory agent, for the treatment of Kaposi sarcoma in HIV-infected individuals.
How can AI be used to predict the properties of chemicals?
5 answers
AI can be used to predict the properties of chemicals by leveraging predictive modeling and deep learning techniques. These approaches enable the accurate computation of materials properties and the elucidation and evaluation of the physiological action mechanisms of toxic chemical compounds. By combining AI with DFT-computations, it is possible to compute materials properties more accurately than DFT itself, as demonstrated in the work by Jha et al.. Deep learning methods, such as deepFPlearn, can predict the association between chemical structures and effects on the gene/pathway level, allowing for efficient and systematic chemical risk assessment. Additionally, AI-enabled drug discovery strategies utilize molecular property predictors to achieve superior performance on ADME/Tox prediction tasks by ensembling and integrating different prediction methods, as shown in the work by Oloren ChemEngine. Overall, AI provides a powerful tool for predicting chemical properties, enabling faster screening methods and enhancing our understanding of chemical behavior.
Does adenosine play a role in migraine?
4 answers
Adenosine appears to play a role in migraine pathophysiology. Multiple studies suggest that adenosine signaling is involved in controlling vascular tone and pain transmission in the trigeminovascular system. Adenosine receptor antagonist, caffeine, has been shown to relieve migraine headache. Clinical studies have reported elevated plasma adenosine levels during migraine attacks. In animal models, adenosine A2A receptor activation has been implicated in acetate-induced trigeminal sensitivity, which is associated with hangover headache. Furthermore, blocking adenosine A2A receptor activation and acetate transport into astrocytes prevented trigeminal sensitivity. These findings suggest that adenosine, through its receptors, may contribute to migraine pathogenesis and could be a potential target for migraine treatment. Further research is needed to better understand the specific mechanisms and potential therapeutic implications of adenosine in migraine.
What are the challenges and limitations of using machine learning with small data?
4 answers
Machine learning with small data poses several challenges and limitations. The limited availability of data makes it difficult to achieve reliable model generalization and transferability, leading to poor performance in real-world applications. Small data problems are compounded by issues such as data diversity, imputation, noise, imbalance, and high-dimensionality. Additionally, the small sample size hinders the ability to learn and generalize effectively, which is a key difference between human and artificial intelligence. The nature of experimental organic chemistry often restricts practitioners to small datasets, limiting the application of machine learning techniques. To address these challenges, various techniques have been proposed, including transfer learning, self-supervised learning, and generative models, which have shown promising potential in overcoming the limitations of small data. By adopting a holistic data-centric approach and leveraging statistical analysis, the value of small data can be maximized in chemistry research.
What is inference in the study of motor control?
4 answers
In the study of motor control, inference refers to the process of making predictions and generating behavior based on sensory information and internal models. Active inference, a computational neuroscience perspective, is a theory that formalizes the generation of flexible, goal-directed behavior through the minimization of free energy. It involves processing sensorimotor information, inferring behavior-relevant aspects of the world, and invoking highly flexible, goal-directed behavior. Active inference models can develop latent states known as affordance maps, which signal which actions lead to which effects depending on the local context. In addition to intentional imperatives, active inference also incorporates conflict-resolution imperatives, which aim to resolve multisensory conflicts and align movements with external goals. The active inference framework provides a unifying view of motor control, integrating probabilistic methods, internal models, and optimal control theory.