China
Africa
Explore chapters and articles related to this topic
Artificial Intelligence, Machine Learning and Smartphone-Internet of Things (S-IoT) for Advanced Student Network and Learning
Published in Thiruselvan Subramanian, Archana Dhyani, Adarsh Kumar, Sukhpal Singh Gill, Artificial Intelligence, Machine Learning and Blockchain in Quantum Satellite, Drone and Network, 2023
With the help of ML technology, teachers can dive deep into data and simplify it for the students. The teachers can analyze various contents and make appropriate conclusions from them. Learning analytics also helps the student by suggesting them the most appropriate path and learning methodologies for them (Iatrellis et al., 2020). Another most important feature of ML is predictive analysis. It helps the teachers to understand the students’ mindset and specific needs of the students. It also helps the faculty of a learning institution and parents to make appropriate decisions to get the best outcome for the students. ML can also be used for assessing the students’ performance more accurately than a human can perform. This technology provides valid and reliable analysis of the student’s performance by lowering the chances of error. A personalized learning approach is useful to make a tailor-made pathway for the individual students and spot their issues (Conati et al., 2018).
Impact of AI on Teaching Pedagogy and its Integration for Enhancing Teaching-Learning
Published in Prathamesh Churi, Shubham Joshi, Mohamed Elhoseny, Amina Omrane, Artificial Intelligence in Higher Education, 2023
Bhagwan Toksha, Trishul Kulkarni, Prashant Gupta
The rationale behind increasing interest in adopting ML algorithms is that they create possibilities for adaptive learning systems. The amalgamation of item response theory and ML algorithms resulted in an innovative system for dealing with the difficulty of supplying content to new users of adaptive learning systems (Pliakos et al., 2019). The ML algorithm-based system was able to predict the appropriate levels of content for new users. The consent of the learner participant to let their information be collected and processed is an important as well as dynamic parameter in EDM. The consent provided by the learners varies over socioeconomic, ethnic and gender bases. The use of learners’ educational data for learning analytics raises an ethical dilemma around how to maintain privacy about learners’ data collection and its further usage. Furthermore, there is a possibility that the learners’ feedback in the learning analytics may skew predictive models, as well as unintentional incorporation of biases and disproportionate opting out of predictive models (Li et al., 2021).
Software and Technology Standards as Tools
Published in Jim Goodell, Janet Kolodner, Learning Engineering Toolkit, 2023
Jim Goodell, Andrew J. Hampton, Richard Tong, Sae Schatz
Analytics, or the systematic computational analysis of data, is central to the investigation phase of the learning engineering process introduced in Chapter 1. Learning analytics is the use of “data mining, machine learning, natural language processing, visualization, and human-computer interaction approaches among others to provide educators and learners with insights that might improve learning processes and teaching practice.” 19 Learning analytics capabilities may be integrated as standalone applications that are used after a learning event, such as in the Kaplan worked problems example in Chapter 6. They can also be integrated into real-time operations, for instance, built into cloud-based streaming architectures or incorporated directly into a software system, such as an adaptive engine in an intelligent tutor to provide just-in-time feedback to learners, as described in the Generalized Intelligent Framework for Tutoring example in Chapter 5.
Learning analytics techniques and visualisation with textual data for determining causes of academic failure
Published in Behaviour & Information Technology, 2020
Clara Nkhoma, Duy Dang-Pham, Ai-Phuong Hoang, Mathews Nkhoma, Tram Le-Hoai, Susan Thomas
Organisational factors play important roles in ensuring the viability of any learning analytics solutions. Different stakeholders are expected to be actively involved throughout the learning analytics process (Siemens 2013; Daniel 2015), such as the involvement of administrative and academic staff during the data collection and intervention stages with the identified ‘at risk’ students, and the support from the university management to facilitate such process. A critical issue of the deployment of learning analytics focuses on ensuring the ethical collection and analysis of students’ personal data (Ferguson 2012; Daniel 2015). Particularly for the case of identifying underperforming students with learning analytics, Lawson et al. (2016) cautioned that the labelling of students as ‘at risk’ could lead to an abusive power relationship, since the student data are not de-identified and can be accessed by different stakeholders when they provide support to these students. As such, clear ethical and information governance frameworks are required at institutions for ensuring the appropriate collection and usage of student data for detecting ‘at risk’ cases.
Exploring the Relationships between Reading Behavior Patterns and Learning Outcomes Based on Log Data from E-Books: A Human Factor Approach
Published in International Journal of Human–Computer Interaction, 2019
Chengjiu Yin, Masanori Yamada, Misato Oi, Atsushi Shimada, Fumiya Okubo, Kentaro Kojima, Hiroaki Ogata
Learning analytics is an emerging discipline that is concerned with developing methods for exploring the unique types of data that are derived from educational settings and using those methods to more effectively understand student learning (Baker & Yacef, 2009; Yin et al., 2013b). Long and Siemens (2011) demonstrated that learning analytics aids in the analysis and reporting of data on learners and their contexts. This information can foster a more effective understanding of learning processes and optimize learning and its environments. The primary aim of learning analytics is to enhance learning outcomes and the overall learning process in computer-supported education. Learning analytics can aid teachers and learners to search for unobserved patterns and underlying information in learning processes (Agudo-Peregrina, Iglesias-Pradas, Conde-González, & Hernández-García, 2014). Analyzing learning behavior patterns is a critical topic in learning analysis.
Supporting Self-Regulated Learning in Online Learning Environments and MOOCs: A Systematic Review
Published in International Journal of Human–Computer Interaction, 2019
Jacqueline Wong, Martine Baars, Dan Davis, Tim Van Der Zee, Geert-Jan Houben, Fred Paas
The present set of research synthesized in this literature review reveals a substantial shortage in the area of human factor-dependent learning interventions. We, therefore, outline three recommendations to guide and advance future research. First, harness learning analytics to provide adaptive support. Part of the promise of learning analytics is its potential for adaptive, personalized learning environments that cater instruction precisely to each learner’s unique needs. This is helpful in the near-term because these random assignments expose every type of person to each condition evenly. As more studies are run and we learn more about how various human conditions benefit differently from certain approaches to learning and SRL strategies, we can begin to strategically target interventions to the populations who we can safely predict will benefit most from them. Given the rise in MOOCs’ popularity and research efforts, there will soon be a substantial corpus of MOOC experiments offering deeper insights on how to design and deploy scalable, targeted interventions. Once we have a corpus of research that sheds light on which interventions are best for certain types of learners, we can cater MOOC instruction to best fit the individual learner needs.