class: left, bottom, title-slide .title[ # Module 3: Learning Analytics ] .subtitle[ ## EME6356: Learning & Web Analytics ] .author[ ### Dr. Bret Staudt Willet ] .date[ ### June 3, 2024 ] --- class: inverse, center, middle #
**View the slides:** [bretsw.com/eme6356-su24-module3](https://bretsw.com/eme6356-su24-module3) --- class: inverse, center, middle #
<br><br> Looking Back at Module 2 --- #
Data Doubles <img src="img/mirror.jpg" width="640px" style="display: block; margin: auto;" /> -- - How well can data capture our multifaceted selves? -- - Do data shape our identities? --- #
Double-Edged Sword <img src="img/sword.jpg" width="600px" style="display: block; margin: auto;" /> -- - How can data **help**?
alerts and notifications -- - How can data **hurt**?
obsessive checking/tracking --- #
What's the Point? <img src="img/crosswalk.jpg" width="600px" style="display: block; margin: auto;" /> -- - What’s the purpose of knowing how many emails one sends? -- - What if parents showed data patterns to their kids? -- - Could performance analytics help people self-regulate? --- #
Cautions <img src="img/sold.jpg" width="640px" style="display: block; margin: auto;" /> -- - Who **owns** the data? The interpretation of the data? -- - **Bias** exists in human interpretation and is baked into data analytics --- class: inverse, center, middle #
<br><br> Module 2 <br> Final Thoughts? --- class: inverse, center, middle #
<br><br> Module 3: <br> Learning Analytics --- class: inverse, center, middle #
<br><br> **Defining Analytics** --- class: inverse, center, middle #
<br><br> **Defining Analytics** **Measure
Collect
Analyze
Report** --- class: inverse, center, middle #
<br><br> **Learning Analytics** **(Performance at School)** --- #
Performance at School <img src="img/classroom.jpg" width="600px" style="display: block; margin: auto;" /> Measure
Collect
Analyze
Report -- ###
**What might we measure?** --- #
Performance at School <img src="img/classroom.jpg" width="600px" style="display: block; margin: auto;" /> - How did student learning changed when doing school from home, if at all? -- - With whom do students interact in class discussions? -- - From whom do teachers seek professional advice? --- #
Performance at School <img src="img/3-ye-2022.png" width="100%" style="display: block; margin: auto;" /> <div class="caption"> <p>TechTrends article: "The History and Development of Learning Analytics in Learning, Design, & Technology Field" (<a href="https://doi.org/10.1007/s11528-022-00720-1" target="_blank">Ye, 2022</a>)</p> </div> --- class: inverse, center, middle #
<br><br> **Learning Analytics** <br><br> Example 1 --- #
Learning Analytics Example 1 **Online Class Discussions: Social Network Analysis** -- <img src="img/3-sociogram1.png" width="100%" style="display: block; margin: auto;" /> -- ###
**What might we measure?** --- #
Learning Analytics Example 1 **Online Class Discussions: Social Network Analysis** <img src="img/3-sociogram1.png" width="100%" style="display: block; margin: auto;" /> ###
**Next step:** Look at the network by group or by week --- #
Learning Analytics Example 1 **Online Class Discussion - Social Network Analysis** There are quite a few descriptive measures of networks: -- - **Order:** number of nodes/vertices (students, in this case) -- - **Size:** number of edges/connections (responses, in this case) -- - **Reciprocity:** mutuality -- - **Transitivity:** clustering -- - **Diameter:** similar to degrees of separation -- - **Density:** out of all possible connections, percentage that have been made -- - **Node degree:** number of connections -- - **Sentiment score:** how positive or negative in aggregate (see [**LIWC**](https://www.liwc.app/)) -- - Character count, Word count, Length of threads --- class: inverse, center, middle #
<br><br> **Learning Analytics** <br><br> Example 2 --- #
Learning Analytics Example 2 **Massive Online Open Course (MOOC) Discussion - Social Network Analysis** <img src="img/3-article-cover.png" width="600px" style="display: block; margin: auto;" /> **Article:** [A social network perspective on peer supported learning in MOOCs for educators ](http://www.irrodl.org/index.php/irrodl/article/view/1852) (Kellogg, Booth, & Oliver, 2014) --- #
Learning Analytics Example 2 **Massive Online Open Course (MOOC) Discussion - Social Network Analysis** <img src="img/3-data-cover.png" width="600px" style="display: block; margin: auto;" /> **Data source:** [Massively Open Online Course for Educators (MOOC-Ed) network dataset](https://dataverse.harvard.edu/dataset.xhtml;jsessionid=9ad052693563b29056a88d490182?persistentId=doi%3A10.7910%2FDVN%2FZZH3UB&version=&q=&fileTypeGroupFacet=&fileAccess=&fileSortField=name&fileSortOrder=desc)] --- #
Learning Analytics Example 2 **Massive Online Open Course (MOOC) Discussion - Social Network Analysis** <img src="img/3-example2-rq.png" width="100%" style="display: block; margin: auto;" /> --- #
Learning Analytics Example 2 **Massive Online Open Course (MOOC) Discussion - Social Network Analysis** <img src="img/3-sociogram2.png" width="100%" style="display: block; margin: auto;" /> -- ###
**Next step:** Infer network structure --- #
Learning Analytics Example 2 **Massive Online Open Course (MOOC) Discussion - Social Network Analysis** <img src="img/3-sociogram2.png" width="100%" style="display: block; margin: auto;" /> (try using **[brms](https://paul-buerkner.github.io/brms/)**: An R package for Bayesian multilevel models using Stan) --- class: inverse, center, middle #
<br><br> **Learning Analytics** <br><br> Comparing Examples 1 & 2 --- #
Comparing Examples 1 & 2 <img src="img/3-sociograms1-2.png" width="540px" style="display: block; margin: auto;" /> --- #
Comparing Examples 1 & 2 <img src="img/3-table-comparison.png" width="100%" style="display: block; margin: auto;" /> --- class: inverse, center, middle #
<br><br> **Learning Analytics** <br><br> Example 3 --- #
Learning Analytics Example 3 <iframe frameborder="0" id="kaltura_player" src="https://cdnapisec.kaltura.com/p/1038472/sp/103847200/embedIframeJs/uiconf_id/46145191/partner_id/1038472?iframeembed=true&playerId=kaltura_player&entry_id=1_3b8ykrr9&flashvars[streamerType]=auto&flashvars[localizationCode]=en_US&flashvars[leadWithHTML5]=true&flashvars[sideBarContainer.plugin]=true&flashvars[sideBarContainer.position]=left&flashvars[sideBarContainer.clickToClose]=true&flashvars[chapters.plugin]=true&flashvars[chapters.layout]=vertical&flashvars[chapters.thumbnailRotator]=false&flashvars[streamSelector.plugin]=true&flashvars[EmbedPlayer.SpinnerTarget]=videoHolder&flashvars[dualScreen.plugin]=true&flashvars[hotspots.plugin]=1&flashvars[Kaltura.addCrossoriginToIframe]=true&&wid=1_vnbeixuu" title="Kaltura Player" width="720" height="480"></iframe> See the [My Learning Analytics Canvas dashboard](https://its.umich.edu/academics-research/teaching-learning/my-learning-analytics) at University of Michigan --- class: inverse, center, middle #
<br><br> Looking ahead --- #
Semester schedule <img src="img/across-time.jpg" width="720px" style="display: block; margin: auto;" /> - **Module 1:** Introduction to Analytics - **Module 2:** Performance Analytics - **Module 3: Learning Analytics** - **Module 4:** Web Analytics - **Module 5:** Data Visualization - **Module 6:** Ethics in Learning Analytics - **Module 7:** Future of Analytics - **Module 8:** Case Discussions --- #
Module structure <img src="img/workshop.jpg" width="480px" style="display: block; margin: auto;" /> -
Watch -
Explore -
Read -
Discuss -
Create --- #
Upcoming Assignments <img src="img/build.jpg" width="600px" style="display: block; margin: auto;" /> -- ### Discussion (50 points) - Initial video/audio post on Canvas due by second Friday - At least 3 responses due on Canvas by end of Module 3 --- #
Upcoming Assignments <img src="img/build.jpg" width="360px" style="display: block; margin: auto;" /> ### Analytics Problem Plan (100 points) - **due end of Module 3** - "Write a brief report (approximately 750-1000 words) identifying and describing a real-world problem that might be addressed via analytics." - "The emphasis of this assignment is on the conceptualization of the problem and the clear identification of a possible data source." - "Then briefly describe how analytics will be used to solve the problem" - "You will not need to collect actual data related to this problem, just plan for how it would be done." --- class: inverse, center, middle #
<br><br> Questions <hr> **What questions can I answer for you now?** **How can I support you this week?** <hr>
[bret.staudtwillet@fsu.edu](mailto:bret.staudtwillet@fsu.edu) |
[bretsw.com](https://bretsw.com) |
[GitHub](https://github.com/bretsw/) --- class: inverse, center, middle # Learn to Code <img src="img/dsieur.jpg" width="320px" style="display: block; margin: auto;" /> **https://datascienceineducation.com/** --- class: inverse, center, middle #
<br><br> Play in the <br> [Analytics Sandbox](https://bretsw.com/sandbox)
[GitHub repository for code and data](https://github.com/bretsw/sandbox)
[Datasets for practice](https://bretsw.com/post/datasets/)