Skip to main content

Home/ Learning Analytics/ Group items tagged questions

Rss Feed Group items tagged

Filter: All | Bookmarks | Topics Simple Middle
Tony Searl

Nothing New About Asking Questions. The Right Ones. - Neoteny - 0 views

tonysearl.posterous.com/out-asking-questions-the-right

questions #lak12 BD BigData analytics data tools learning connectivism

shared by Tony Searl on 05 Feb 12 - No Cached
  • Tony Searl on 05 Feb 12
     
    There are plenty of reasons to be skeptical about the BD market. But big data probably deserves a place in overall enterprise IT strategy for generating business insight. Best practices include generating a list of important challenges or questions that the current approach to data does not address. Could big data deliver the answers enterprises are looking for? If so, then it's all about discipline. A disciplined, targeted approach to big data - one focused on answering very specific questions. (my emphasis - I'll get to those later)
Phillip Long

http://www.ifets.info/journals/17_4/4.pdf - 0 views

www.ifets.info/...4.pdf

adaptive_learning EDM learning_analytics systematic_review

shared by Phillip Long on 26 Oct 14 - No Cached
  • Phillip Long on 26 Oct 14
     
    Papamitsiou, Z., & Economides, A. (2014). Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence. Educational Technology & Society, 17 (4), 49-64. This paper aims to provide the reader with a comprehensive background for understanding current knowledge on Learning Analytics (LA) and Educational Data Mining (EDM) and its impact on adaptive learning. It constitutes an overview of empirical evidence behind key objectives of the potential adoption of LA/EDM in generic educational strategic planning. We examined the literature on experimental case studies conducted in the domain during the past six years (2008-2013). Search terms identified 209 mature pieces of research work, but inclusion criteria limited the key studies to 40. We analyzed the research questions, methodology and findings of these published papers and categorized them accordingly. We used non-statistical methods to evaluate and interpret findings of the collected studies. The results have highlighted four distinct major directions of the LA/EDM empirical research. We discuss on the emerged added value of LA/EDM research and highlight the significance of further implications. Finally, we set our thoughts on possible uncharted key questions to investigate both from pedagogical and technical considerations.
Tony Searl

U. of Texas Adopts Plan to Publish Performance Data on Professors and Campuses - Facult... - 2 views

chronicle.com/...128800

texas data performance lak12 siemens learninganalytics

shared by Tony Searl on 29 Aug 11 - No Cached
  • help ensure that taxpayers are getting their money's worth
    • Tony Searl
      Tony Searl on 29 Aug 11
       
      as I attempted to raise during LAK11, intent is critical. If LAK is primarily accountability driven, then more complex outcomes available IF questioning of data is deeper, may be missed (or ignored/buried/not sought)
  • Among other things, the system will report such factors as research expenditures, publications, teaching evaluations, and external support.
    • Tony Searl
      Tony Searl on 29 Aug 11
       
      myschool is already developing into such a site. Insightful LAK, with holistic intention, not narow agendas, is preferable. Metrics, data, inclusions and questions need bipartisan support IF education is to be apolitical.
  • That was a swipe at the Texas Public Policy Foundation, a conservative think tank supported by Gov. Rick Perry that has advocated a controversial blueprint known as the "Seven Solutions" to higher education
    • Tony Searl
      Tony Searl on 29 Aug 11
       
      Perry, potential president? Fascinating 2012 election
  • ...2 more annotations...
  • It also calls for a review system in which outside experts analyze the performance of individual colleges within the system's universities.
    • Tony Searl
      Tony Searl on 29 Aug 11
       
      intent, questions asked, data deemed inclusive, all crucial for LAK outcomes. Enormous potential for misrepresentations exist IF analytics is poorly conceived and managed.
  • Mr. Powell said the database would allow students, parents, legislators, and others to easily examine detailed data about how different campuses and departments performed.
    • Tony Searl
      Tony Searl on 29 Aug 11
       
      exact definition of intent of our 2 year old myschool data
  • Tony Searl on 29 Aug 11
     
    The plan unveiled on Thursday designates money to create a "dashboard"-an interactive, online database-to give students, parents, and legislators access to detailed measures of departments' and colleges' productivity and efficiency. Data on individual professors will probably also be included, although Dr. Cigarroa stressed that each campus would be able to develop its own system of metrics and the details have not yet been worked out
hansdezwart

7 Data Blogs To Explore - ReadWriteCloud - 1 views

www.readwriteweb.com/...7-data-blogs.php

bigdata blogs lak11 week2

shared by hansdezwart on 23 Jan 11 - No Cached
  • hansdezwart on 23 Jan 11
     
    Several weeks ago, I posted a question on Quora asking for the best data blogs. There have been 26 replies with dozens of blogs recommended.
Vanessa Vaile

LAK11: Big Data Small Data « Viplav Baxi's Meanderings - 0 views

learnos.wordpress.com/...lak11-big-data-small-data

data lak11 analytics week2 tools connectivism #lak11 #evomlit education

shared by Vanessa Vaile on 23 Jan 11 - No Cached
  • which data is more appropriate - BIG or small
  • most discussion about big data centres on quantity
  • other elements you mention – implication, new models, new decision making approaches – all flow from this abundance of data.
  • ...15 more annotations...
  • Increased data quantity requires new approaches
  • Is small beautiful? Look at the following links. Big Data, Small Data New Age of Innovation (Prahalad) So you like Big Data
  • reading on Insurers and the work done by Levitt and Dubner on Freakonomics tells us clearly that data not earlier thought relevant or causal can be an efficient predictor.
  • Secondly, strategies designed on BIG data
  • may overpower small data strategies
  • Thirdly, BIG data also has BIG impacting factors.
  • Fourthly, actions taken on BIG data will have big consequences,
  • Lastly, if everybody, big or small, started using BIG analytics, to make decisions
  • companies would anyway lose the competitive differentiator that analytics brings to them.
  • Corresponding to the question, how big does BIG need to be, the question I have is - how small really is small.
  • defining patterns that emerge from very small pieces of data (e.g. synchronicity)
  • how tools for SNA and analysis of BIG data can apply to Learning and Knowledge Analytics
  • at the other end it embraces how small changes can cause long term variations
  • not easy to analyze the small data
  • data that is small enough not to be generalizable
Tony Searl

Dueling algorithms - 1 views

web.mit.edu/...dueling-algorithms-0318.html

dueling algorithms

shared by Tony Searl on 19 Mar 11 - No Cached
  • Tony Searl on 19 Mar 11
     
    According to Eva Tardos, Jacob Gould Schurman Professor of Computer Science at Cornell University, the researchers' paper "is more the beginning of research than a definitive result or end product." The researchers' models make several simplifying assumptions - including the number of competitors - that make the math easier but limit their applicability. Nonetheless, "just raising the questions is an important step forward," Tardos says.
1 - 6 of 6
Showing 20▼ items per page