CSU System-wide Learning Analytics Projects
1 like2,085 views
This document discusses system-wide learner analytics projects at Chico State University and across the California State University system. [1] It describes a research study at Chico State that analyzed the relationship between student usage of the learning management system and academic outcomes. [2] It then provides an overview of current learner analytics projects involving the Moodle and Blackboard learning management systems, including establishing common metrics and queries across campuses.
CSU System-wide Learning Analytics Projects
- 1. System-wide LMS Learner Analytics Projects Presenters: Kathy Fernandes and John Whitmer ATSC Virtual Meeting December 13, 2012 Slides @ http://goo.gl/DYqJU
- 2. Agenda 1. Chico State Learner Analytics Research Study • EDUCAUSE Article (http://goo.gl/tESoi) 2. Current Projects • Moodle • Blackboard 2
- 3. 1. CHICO STATE LEARNER ANALYTICS RESEARCH STUDY “Logging on to Improve Achievement” by John Whitmer EdD. Dissertation (UC Davis & Sonoma State) 3
- 4. Case Study: Intro to Religious Studies • Redesigned to hybrid delivery through Academy eLearning 54 F’s • Enrollment: 373 students (54% increase on largest section) .8 • Highest LMS (Vista) usage .6 entire campus Fall 2010 (>250k hits) Density .4 • Bimodal outcomes: .2 • 10% increased SLO mastery • 7% & 11% increase in DWF 0 0 1 2 3 4 Course Grade • Why? Can’t tell with aggregated reporting data 4
- 5. Driving Conceptual Questions 1. How is student LMS use related to academic achievement in a single course section? 2. How does that finding compare to the relationship of achievement with traditional student characteristic variables? 3. How are these relationships different for “at-risk” students (URM & Pell-eligible)? 4. What data sources, variables and methods are most useful to answer these questions? 5
- 6. Variables Student'Characteristic'Independent'Variables' Gender Under Represented Minority (URM) Pell-Eligible High School GPA First in Family to Attend College Student Major (Discipline) Enrollment Status Interaction URM & Gender Interaction URM & Pell-Eligibility Learning Management System Usage Variables Total LMS course website hits Total LMS course dwell time Administrative tool website hits Assessment tool website hits Content tool website hits Engagement tool website hits Dependent'Variable:'Final'Course'Grade''' 6 !
- 7. Clear Trend: Grade w/Mean LMS Hits 7
- 8. Separate Variables: Correlation LMS Use & Student Characteristic with Final Grade LMS Student Use Characteristic > Variables Variables 18% Average 4% Average (r = 0.35–0.48) (r = -0.11–0.31) Explanation of change Explanation of change in final grade in final grade 8
- 9. Combined Variables: Regression Final Grade by LMS Use & Student Characteristic Variables LMS Student Use Characteristic > Variables Variables 25% +10% (r2=0.25) (r2=0.35) Explanation of change Explanation of change in final grade in final grade 9
- 10. At-Risk Students: “Over-Working Gap” 10
- 11. Filtering Data – Lots of “Noise”; Low “Signal” 500 450 400 350 300 382 250 200 150 Raw Average Hits/ 151 Student 100 58 49 Filtered Average 50 26 Hits/Student 54 51 23 36 16 0 Discussion Activity Content Activity Hits Assessment Activity Mail Activity Hits Administrative Hits Hits Activity Hits Final data set: 72,000 records (-73%) 11
- 12. 2. CURRENT PROJECTS 12
- 13. Moodle and Bb Learner Analytics What do these have in common? • Multi-campus CSU groups discussing common analytics questions & query definitions 13
- 14. Moodle vs. Bb Learner Analytics Moodle CIG (18 months old) Blackboard Learn Group Chair: Andrew Roderick, SFSU (just starting) CIG Chair: Terry Smith, CSUEB § DIY, adopt and evaluate § Bb Learn Analytics product available “off the shelf”; solutions from other defined and integrated with Moodlers Peoplesoft § Starting with technical § Pre-built Reports and reporting to build accurate Dashboards to ANYONE on indicators of use campus (admin. or faculty if § 2 rounds of data collection authenticated) already completed and § Charts available inside LMS discussed for Faculty and Student Views 14
- 15. Moodle Reporting & Analytics, Round 1 § Prioritized Moodle Queries from S&PG governance group § Focused on measures of adoption (% faculty, % students, % course sections) § For expediency, campuses reported using current queries used for reporting 15
- 16. “How many sections are using the LMS (out of all sections offered that term)?” CSU_09 671 2,191 CSU_08 1,098 1,162 CSU_06 2,997 7,064 Active Sections Inactive Sections CSU_05 2,492 3,687 CSU_04 553 614 CSU_02 2,270 3,911 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 16
- 17. “How many sections are using the LMS (out of all sections offered that term)?” CSU_09 671 2,191 CSU_08 1,098 1,162 CSU_06 2,997 Use = “visible”+”student activity” 7,064 Active Sections Inactive Sections CSU_05 2,492 3,687 CSU_04 553 Use = “visible” 614 CSU_02 2,270 3,911 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% 17
- 18. Round 2: mCURL (Moodle Common Usage and Learning Analytics) § 8 active CSU & 2 UC campuses – Co-chaired: John Whitmer, CO ATS and Mike Haskell, Cal Poly SLO § Starting with same measures of adoption, prioritizing “wish list” of more advanced analytics § Local database conventions and campus practices make accurate comps. challenging 18
- 19. Faculty LMS Adoption How many faculty are using the LMS in one or more course sections? 19
- 20. mCURL Next Steps § Refine queries for accurate comparative course and student adoption measures § Select additional queries: depth and breadth of use – # tools used – # students in each section – frequency of use § Create repositories for campuses to share unique local queries 20
- 21. Blackboard Analytics for Learn (A4L) § CSU ATS Co-Lab Agreement – working together – Functionality: from early alerts/course reporting to institutional-level analytics – Up to 4 campuses participating (3 confirmed) – Period: December 2012-December 2013 – Individual campus Scope of Work for setup of infrastructure and services § Kick-off meeting next week 21
- 22. Co-Lab Goals 1. Develop methodologies and processes to identify, aggregate, and transform LMS usage data into information for analytics. 2. Improve campus usage of learning analytics for decision-making for student success, curriculum improvement, and technical services. 3. Create shared measures, database reports, and algorithms, drawing on campus best practices and research innovations. 4. Increase campus awareness of applications and technical tools. 5. Document campus efforts and disseminate to other campuses. 6. Provide professional development in learning analytics. 22
- 23. Student at a Glance 23
- 24. Instructor at a Glance 24
- 25. Dean Dashboard 25
- 26. Feedback? Questions? Kathy Fernandes (kfernandes@csuchico.edu) John Whitmer (jwhitmer@calstate.edu) 26