Your SlideShare is downloading. ×
 Web 2.0 Analytics Knowledge is Power ITC11
Upcoming SlideShare
Loading in...5
×

Thanks for flagging this SlideShare!

Oops! An error has occurred.

×

Saving this for later?

Get the SlideShare app to save on your phone or tablet. Read anywhere, anytime - even offline.

Text the download link to your phone

Standard text messaging rates apply

Web 2.0 Analytics Knowledge is Power ITC11

689
views

Published on

Most of us have been delighted to dabble in and assimilate many tools in the Web 2.0 landscape. Now it is time to increase the value. Overviewing the semantic web and how data is being complied and …

Most of us have been delighted to dabble in and assimilate many tools in the Web 2.0 landscape. Now it is time to increase the value. Overviewing the semantic web and how data is being complied and how analytics is being used in education.
Michael Amick and Kyle Mackie

Published in: Education, Technology

0 Comments
0 Likes
Statistics
Notes
  • Be the first to comment

  • Be the first to like this

No Downloads
Views
Total Views
689
On Slideshare
0
From Embeds
0
Number of Embeds
2
Actions
Shares
0
Downloads
2
Comments
0
Likes
0
Embeds 0
No embeds

Report content
Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
No notes for slide
  • As the semantic web develops and knowledge is mapped, it can be linked to existing analysis models in order to provide personalized and adaptive content for learners. Personalized and adaptive learning has been a dream of educators for decades. Developments with linked data offer new promise in realizing a scalable system of learning.
  • Tapscott, D. and Williams, A. Macrowikinomics .  Rebooting Business and the World.  Toronto, 2010. from pp. 369-371. “In 2005, who would have predicted that hundreds of millions of people would be voluntarily giving up detailed data about themselves, there activities, their likes/dislikes, etc., online every day.  This situation has turned traditional privacy laws and regulations upside down.  Privacy and data protection laws emphasize the responsibility of organizations to collect, use, retain and disclose (“manage”) personal information in a confidential manner.  But collaborative networks, in contrast, encourage individuals themselves to directly and voluntarily publish granular data about themselves (tagged photos, preferences/settings/likes, friends’ lists, groups joined, etc.), short circuiting the obligations of organizations to seek informed consent and to manage this data responsibly according to defined criteria.”
  • in order to protect privacy, all of us will need to change our own online behaviour. Pew (2010): people in their 20s exert more control over their digital reputations than older adults.  Teenagers naturally learn to be protective of their privacy - Nissembaum, NYU Privacy in Context “The Age of Networked Intelligence demands that we step back and consciously design our lives.  We need to decide explicitly what we stand for and whether we are a slave or the master of new technologies.” (Tapscott) “ User-friendly and intuitive controls must be backed with an organization’s commitment to allow users to preserve, as well as maintain, their own privacy, rather than forcing data into the open.”
  • In commercial usage, analytics software may evaluate data mined from purchasing records to allow a web-based retailer to suggest products that might interest customers or allow a search engine to target ads based on an individual’s location and demo- graphic data.  
  • Colleges and universities can harness the power of analytics to develop student recruitment policies, adjust course catalog offerings, determine hiring needs, or make financial deci- sions. In a teaching and learning context, data from such sources as the learning management system, college application forms, and library records can be used to build academic analytics pro- grams that use algorithms to construct predictive models that can identify students at risk for not succeeding academically.
  • stages Goldstein (2005) extraction and reporting analysis and monitoring what if scenarios predictive modeling and simulation automatic triggers and alerts
  •   - evidence-based - informed change - accountability and awareness - increase student success and reduce attrition - allocation of resources and attracting new students - course design, redesign and impactfulness (find out what's working) variability in course design, LMS cannot be a on-size fits all solution Distributed analytics - out of an LMS, learner control LMSes need to build tools for easy export
  • The effectiveness of any analytics tool depends heavily on the fre- quency and character of faculty and student use. Careful and cau- tious interpretation of data is vital: patterns revealed by the data for small cohorts of students might not apply to other cohorts or to larger groups of students. At the departmental level, patterns might confirm program strengths or suggest resource deficiencies. On the institutional plane, predictive models can help align re- sources such as tutorials, online discussions, and library assistance with student need. For the individual student who uses a dash- board to track personal progress, analytics can be a valuable tool for self-assessment and a powerful component of a personal learn- ing environment. Analytics tools might facilitate better communi- cation between faculty and students while empowering students to monitor their coursework and take greater responsibility for their learning. As students, faculty, and instructional designers be- come more aware of the potential of analytical tools, we may start to see tools and LMS plug-ins that are designed specifically to gen- erate meaningful analytics.
  • Both data mining and the use of analytics applications in- troduce a number of legal and ethical considerations, including privacy, security, and ownership. On one hand, institutions might be vulnerable to charges of “profiling” students when they draw conclusions from student data; on the other, they could be seen as irresponsible if they don’t take action when data suggest a student is having difficulty. The best results emerge when an in- stitution has cross-system participation from multiple data sourc- es such as library records, an LMS, registration information, and student applications. But even then the best evaluative algorithms can result in misclassifications and misleading patterns, in part because such programs are based on inferences about what dif- ferent sorts of data might mean relative to student success.    Further, while analytics is correlative, it doesn’t denote causation— something that could send a mixed message to students who might believe that if they participate in a class “at the right level,” they will receive a good grade, irrespective of how much they learn. Even where specific activity correlates with success, it’s not always clear what interventions will be most effective at informing students who appear to be at risk and persuading them to take action. For many institutions, finding the resources for normaliz- ing and warehousing data and the expertise to set up a robust analytics system can be challenging. As learning tools and re- sources move into the cloud, the ability to incorporate that data into an analytics program will depend on policies and technical means to share information across organizations.
  • Transcript

    • 1. Knowledge is Power (I Still Know What You Did Last Summer) Web 2.0 Analytics
    • 2. Overview of Session
      • Topics include:
        • Web Apps and Analysis tools
        • The a testimony to their value
        • The application of intelligent agents and analytics to Education
    • 3.  
    • 4. Blogs
        • ClustrMaps
        • Feedjit
        • Sitemeter
    • 5. YouTube
    • 6. flickr
    • 7. Twitter and Bit.ly
    • 8. Facebook
    • 9. Facebook
    • 10. Value
    • 11. Philontilt
    • 12. Kickstarter
    • 13.  
    • 14. System Analytics
    • 15. Reports
    • 16. Agents
    • 17. Analytics
    • 18. Purdue Signals - Stoplights for student success
    • 19. Carnegie Mellon Open Learning Initiative
    • 20. http://www.youtube.com/watch?v=zrzMhU_4m-g http://www.youtube.com/watch?v=zrzMhU_4m-g
    • 21. Questions?? Comments
    • 22. [email_address] Twitter: @goamick Blog: Learning and Burning online Central Lakes College, Brainerd/Staples, mn Michael Amick Dean of Academic and Technology Services Kyle Mackie Manager, Courseware Services & Dev. [email_address] Twitter: @kylemackie Blog: kylemackie.ca University of Guelph, Ontario, Canada.