Pro Yearly is on sale from $80 to $50! »

Harnessing the Power of Big Data (FETC 2015)

721933370511ddfcefa5ba0564306e9e?s=47 Adam Smeets
January 21, 2015

Harnessing the Power of Big Data (FETC 2015)

Teachers and school administrators at all levels are inundated with data, at times so large and complex that it becomes difficult to process. Explore opportunities and approaches with Tableau, a data visualization application, that information technology services has utilized at Loyola University Chicago for data-based decision making. This includes connecting to multiple databases, Excel spreadsheets and commingling other data types to visualize and inform decision making. Participants will experience hands-on application of using “big data” sets with Tableau Public, as well as best practices for handling large data sets and how to construct reports/dashboards with the tool.

721933370511ddfcefa5ba0564306e9e?s=128

Adam Smeets

January 21, 2015
Tweet

Transcript

  1. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Harnessing the Power of “Big Data” Data-Based Decision Making, Education and Change Adam Smeets asmeets@dom.edu Director, University Information Systems - Dominican University Doctoral Student, Curriculum and Instruction - Loyola University Chicago Adobe Higher Education Leader and Apple Certified Trainer
  2. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One • Introductions • Common Questions About Big Data • Information, Data and Context… Do They Individually Lie To Us? • Learning Analytics, Big Data and Identifying Action • Working With Big Data With Big Data Tools Agenda
  3. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Introductions • Name • School / District (If Applicable) • Title / Role • How do you use “big data?” • Favorite Attraction at Disney/Universal
  4. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Win a PC/Mac Version of Adobe Presenter and Adobe Captivate In This Session!
  5. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One http://www.winkle.eu/cms/wp-content/uploads/child-ask-question-raise-hand-school.jpg COMMON QUESTIONS ABOUT BIG DATA
  6. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One WHERE IS BIG DATA?
  7. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Where is big data? In 2005, there were 1.3 billion RFID tags in circulation.
 (IBM, 2010) In 2010, there were 30 billion RFID tags in circulation.
 (IBM, 2010) In 2011, there were 35 million contactless tags in circulation.
 (Nielsen, 2011)
  8. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Where is big data? 1 Billion Lines of Code 10TB 10TB 10TB 10TB 10TB 10TB 10TB 10TB 1 Billion Lines of Code ORD to MCO will generate 80TB of data from the engines alone.
  9. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Where is big data? EXIF Tools http://regex.info/exif.cgi Twitter & EXIF Data https://twitter.com/readexifdata
  10. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One WHO IS BIG DATA?
  11. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One HOW “BIG” IS BIG DATA?
  12. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One What is big data? Big data can be described as… • All-encompassing term for any collection of data sets; • Large/complex that it is difficult to process them using traditional data processing applications. • Challenges include analysis, capture, curation, search, sharing, storage, transfer, visualization, and privacy violations.
  13. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  14. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  15. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  16. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  17. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  18. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One http://i.huffpost.com/gen/857744/thumbs/o-PINOCCHIO-facebook.jpg INFORMATION, DATA AND CONTEXT DO THEY INDIVIDUALLY LIE TO US?
  19. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Test scores static for Illinois students
 Malone, T. (2009, October 15). Test scores static for Illinois students. Chicago Tribune.
 Illinois schoolchildren flat-lined on a national math exam last spring and showed little improvement during the last two years in narrowing the achievement gap that divides minority and low-income students from their peers, according to a report released Wednesday. The state results mirror the trend seen elsewhere in the country on the National Assessment of Educational Progress. "Illinois is holding steady, and the nation is holding steady," said spokeswoman Mary Fergus with the Illinois State Board of Education. Is this the full picture? What’s missing? What may account
 for “flat-lined” performance by students? What questions would you ask the writer?
  20. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Magnitude
 The Lie Factor The standard required an increase in mileage from 18 to 27.5, an increase of 53%. The magnitude of increase shown in the graph is 783%, for a whopping lie factor = (783/53) = 14.8! http://www.datavis.ca/gallery/goosed-up.php
  21. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Variation
 The Lie Factor Another key element in making informative graphs is to avoid confounding design variation with data variation. This means that changes in the scale of the graphic should always correspond to changes in the data being represented. This graph violates that principle by using area to show one-dimensional data, giving a lie factor = 2.8. http://www.datavis.ca/gallery/goosed-up.php
  22. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Changing Scales
 The Lie Factor A less obvious way to create a false impression is to change scales part way through an axis. This graph, originally from the Washington Post purports to compare the income of doctors to other professionals from 1939— 1976. http://www.datavis.ca/gallery/goosed-up.php
  23. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Context? The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  24. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Context! The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  25. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Goosed Graphics
 The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  26. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Goosed Graphics
 The Lie Factor
  27. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Goosed Graphics
 The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  28. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One When really…
 The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  29. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Goosed Graphics
 The Lie Factor http://www.datavis.ca/gallery/goosed-up.php
  30. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Equalized Graphics (2004 Election)
 The Lie Factor
  31. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One … By Population The Lie Factor
  32. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One https://classroomaid.files.wordpress.com/2012/10/data-mining2.png LEARNING ANALYTICS, BIG DATA AND IDENTIFYING ACTION
  33. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  34. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Learning Analytics Educational Data Mining Discovery Leveraging human judgment is key; automated discovery is a tool to accomplish this goal Automated discovery is key; leveraging human judgment is a tool to accomplish this goal Reduction & Holism Stronger emphasis on understanding systems as wholes, in their full complexity Stronger emphasis on reducing to components and analyzing individual components and relationships between them Origins Stronger origins in semantic web, "intelligent curriculum," outcome prediction, and systemic interventions Strong origins in educational software and student modeling, with a significant community in predicting course outcomes Adaptation & Personalisation Greater focus on informing and empowering instructors and learners Greater focus on automated adaptation (eg by the computer with no human in the loop) Techniques & Methods Social network analysis, sentiment analysis, influence analytics, discourse analysis, learner success prediction, concept analysis, sense- making models Classification, clustering, Bayesian modeling, relationship mining, discovery with models, visualization A brief comparison of the educational data mining and learning analytics
 (courtesy of George Siemens and Ryan Baker [10])
  35. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Gartner Framework for Personalized Learning Scenarios Gartner (October 2013) - http://www.gartner.com/document/2603417
  36. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Big Data and Education Shared Learning Collaborative Data Store Draft API — RFP Guidance
  37. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Big Data and Education Pre-Class, In Class and Post-Class Pre-Class In Class Post-Class Example Data Use & Purpose Key Activities
  38. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One In Practice - Plickers https://www.plickers.com
  39. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One In Practice - Adaptive Texts
  40. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Education and Big Data Challenges Pre-Class, In Class and Post-Class • Trust • Ownership • False Correlations • Ethical and Legal Procedures • Metadata Standards • Hype http://img1.wikia.nocookie.net/__cb20090406144053/simpsons/images/1/10/PlanetHype.gif
  41. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Education and Big Data Opportunities Pre-Class, In Class and Post-Class Expanding Data and Information • Collaborating with other institutions or schools including government agencies. Government agencies can be a key to obtaining additional contextual data. • Harvesting non-structured data from major student gathering places such as Facebook, usage patterns from apps, and download patterns from various app stores. • Introducing new types of data, including voice capture and facial expression data (from webcams/microphones). http://www.gartner.com/document/2112515
  42. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Education and Big Data Recommendations Pre-Class, In Class and Post-Class • Learn from big data in research - leverage skill that is developed; • Use big data only where there is a chance to discover correlations; • For adaptive learning, collect and correlate data only when there is enough variation in the learning modes examined to provide information that can lead to pedagogical variation. • Make sure to pose a big data question so that the advice gained from it is actionable, for both institutions and individuals; • Big data requires "big thinking," so challenge conventional wisdom. • Take what everyone else sees, and think beyond the obvious. http://www.gartner.com/document/2112515
  43. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Using Big Data as a Planning Tool • Stage 1: Plan with Data • Stage 2: Do the analysis • Stage 3: Check the results • Stage 4: Act on the plan • Stage 5: Monitor in real time • Stage 6: Adjust the impact • Stage 7: Enable experimentation
  44. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One WORKING WITH BIG DATA WITH BIG DATA TOOLS http://www.content4demand.com/wp-content/uploads/2014/12/tools.jpg
  45. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Data Quality • Entry quality: Did the information enter the system correctly at the origin? • Process quality: Was the integrity of the information maintained during processing through the system? • Identification quality: Are two similar objects identified correctly to be the same or different? • Integration quality: Is all the known information about an object integrated to the point of providing an accurate representation of the object? • Usage quality: Is the information used and interpreted correctly at the point of access? • Aging quality: Has enough time passed that the validity of the information can no longer be trusted? • Organizational quality: Can the same information be reconciled between two systems based on the way the organization constructs and views the data?
  46. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One DATACOPIA http://www.datacopia.com
  47. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One EXCEL
  48. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One ZOOMDATA http://demos.zoomdata.com/nhtsa-dashboard/
  49. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One TABLEAU http://www.tableau.com
  50. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Licenses for Teachers and Courses http://www.tableau.com/academic/teaching/licenses Free copy of Tableau Desktop for instructors interested in teaching with Tableau
 at an accredited institution, as well as free software for your entire class.
  51. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Licenses for Students http://www.tableau.com/academic/students
 Full-time students at accredited schools anywhere in the world can get a 1-year license of Tableau Desktop.
  52. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  53. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One
  54. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Dimensions Measures
  55. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Reshaping Tool
  56. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Reshaping Tool • http://kb.tableausoftware.com/articles/knowledgebase/addin-reshaping- data-excel?lang=en-us
  57. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Coffee Chain Demo
  58. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Sample Data File Example In pairs or individually… • Review the provided data file - is it “clean”? If not, make changes to work with a “scrubbed” data file. • Connect the data file to Tableau Public and rename the columns as appropriate. • Sort/move the Dimensions and Measures based on their appropriate location. • Using at least two dimensions and two measures, identify any connections across the data. • Try out an alternative visualization of the data.
  59. Final Cut Pro 7, Level One Final Cut Pro X,

    Level One Harnessing the Power of “Big Data” Data-Based Decision Making and Education Adam Smeets asmeets@dom.edu Director, University Information Systems – Dominican University Adobe Higher Education Leader and Apple Certified Trainer