- Students’ voluminous data are easily captured in all its volumes on an ongoing basis.
- Data can be studied for the shortest time frame. Even intra-day analysis is possible. This shortens time to action. Prompt, proactive action is possible.
- Study patterns of students can be documented and examined on a historic basis.
- Predicting Student Performance. Rating them - Which students are slow in tasks assigned? Who are low performers and least performers?
- Drawing up a Risk Matrix for Cohorts.
- LP (Low Performing) student needing help some online help or offsite.
- A student in classroom session or on online learning: Is there disinterestedness, boredom visible? Is there frustration creeping in?
- How often and in what manner do students use educational software? (Blackboard, EBSCO, Turn-it-in, any internal intranet?) When do they really submit; the pattern of submissions.
- What is the inventory of faculty skills?
- Predicting student progression.
- What courses and pedagogical modes attract students?
- Which courses and pedagogical modes deter students?
- Patterns in enrollment.
- Deciphering patterns in student progression.
- Analysis of student dropout ratios and causative factors.
- Student retention trends.
- Predictive models using this type of unconventional data to assess teaching risk.
- Knowing and monitoring the opinion and attitude of the students and stakeholders as opinions, feelings and attitudes about the EI, as discussed on the world wide web.
- Developing a sentiment analysis tool to monitor student reflections.
- Monitoring social platforms and social media websites. Reconnaissance of the social sphere, including social networks, blogs, Facebook and twitter and other relevant sites.
- Leveraging on valuable feedback and insights to improve offerings and services.
- Student profiling to suit personalization.
- Data would reveal the student interests.
- Using student data for cluster analysis
- Student’s propensity towards a certain subject can be measured.
- Data from online usage- from cookies, URL and software metrics – could to identify which online channels the students are using and what they are using them for.
Monday, August 15, 2016
How will Big Data help educational institutions?
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment