Learning analytics is a method to collect, measure, analysis and reporting of data about learners and their interactions with a learning environment. Learning analytics is applying analytics on educational data to infer the student learning process and to provide support.Learning analytics is important course in the data era and it will help the learner to apply analytics on data from education domain and help the students to learn.INTENDED AUDIENCE :Any interested learnersPREREQUISITES :NoneINDUSTRIES SUPPORT :None
Overview
Syllabus
Week 1:Lecture 1:Intro To Data Analytics Lecture 2:What is LA! Definition Lecture 3:Academic Analytics, and Educational Data Mining Lecture 4:Four Levels of Analytics Lecture 5:Descriptive, Diagnostic, Predictive and Prescriptive AnalyticsWeek 2:Lecture 1:Data Collection from Different learning environment Lecture 2:Technology Enhanced Learning, Classroom and MOOC environment Lecture 3:Preprocessing Lecture 4:Ethics in Learning Analytics, Student PrivacyWeek 3:Lecture 1:Intro to Machine Learning Lecture 2:Supervised and Unsupervised learning Lecture 3:Regression, Clustering and Classification Lecture 4:Metrics for ML algorithms –Recall, Precision, Accuracy, F-Score and Kappa Lecture 5:Demo of ML algorithms using OrangeWeek 4:Lecture 1:Descriptive Analytics Lecture 2:Data Visualization Lecture 3:Data visualization using Excel Lecture 4:Dashboard Analytics Lecture 5:Dashboard of Youtube, MOOC Week 5:Lecture 1:Intro to iSAT Lecture 2:iSAT Demo with example Lecture 3:Diagnostic Analysis Lecture 4:CorrelationWeek 6:Lecture 1:Sequential Pattern Mining Lecture 2:SPM tool Demo Lecture 3:Process Mining Lecture 4:ProM Tool DemoWeek 7:Lecture 1:Predictive Analytics Lecture 2:Modeling – Feature Selection Lecture 3:Linear Regression Lecture 4:Demo of Linear Regression using WekaWeek 8:Lecture 1:Decision Tree Lecture 2:Demo of Decision Tree using Orange Lecture 3:Naïve Bayes algorithm Lecture 4:Demo of Naïve BayesWeek 9:Lecture 1:Clustering in predictive algorithm Lecture 2:K-Means clustering Lecture 3:Demo of K-Means clusteringWeek 10:Lecture 1:Text analytics Lecture 2:Words, Token, Stem and lemma Lecture 3:Minimum edit distance Lecture 4:Develop algorithm to automatically grade subjective answers Lecture 5:Demo of Word embeddingWeek 11:Lecture 1:Intro Multimodal Learning Analytics Lecture 2:Eye-gaze data collection Lecture 3:Affective computing Lecture 4:Aligning and analyzing data from Multiple sensorsWeek 12:Lecture 1:Advanced topics in LA Lecture 2:How to apply LA in our class Lecture 3:Data repos, Research papers to read, and where to present your work
Taught by
Prof. Ramkumar Rajendran
