Contextualized profile?
The contextualized profile of the performance for individual modelling?, does this profile function the same as human brain? in the sense that it predicts in which environment are the learners and predict the respective personality or any pattern accordingly?
;
L.Todd Rose refer to the education market as a non-functional market, there is not enough transparency, which links to his point that market should recognize the importance for individual learners to own their own data, while under the current circumstance, every company or institution is just trying to innovate on their own platform, and ""hoarding"" data because that's the business model they have to have under the current market of education innovation/ Ed-tech.
;
There is a shift in the kind of patterns that we look for.
In stead of the expected level of population, which is average level, now more on personal patterns across all dimensions.
","","http://chronicle.com/blogs/wiredcampus/why-students-should-own-their-educational-data/54329","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"NUKIAJZ6","journalArticle","1994","Corbett, Albert T.; Anderson, John R.","Knowledge tracing: Modeling the acquisition of procedural knowledge","User Modeling and User-Adapted Interaction","","0924-1868, 1573-1391","10.1007/BF01099821","http://link.springer.com.ezp-prod1.hul.harvard.edu/article/10.1007/BF01099821","This paper describes an effort to model students' changing knowledge state during skill acquisition. Students in this research are learning to write short programs with the ACT Programming Tutor (APT). APT is constructed around a production rule cognitive model of programming knowledge, called theideal student model. This model allows the tutor to solve exercises along with the student and provide assistance as necessary. As the student works, the tutor also maintains an estimate of the probability that the student has learned each of the rules in the ideal model, in a process calledknowledge tracing. The tutor presents an individualized sequence of exercises to the student based on these probability estimates until the student has ‘mastered’ each rule. The programming tutor, cognitive model and learning and performance assumptions are described. A series of studies is reviewed that examine the empirical validity of knowledge tracing and has led to modifications in the process. Currently the model is quite successful in predicting test performance. Further modifications in the modeling process are discussed that may improve performance levels.","1994-12-01","2017-09-14 16:03:36","2017-09-14 16:03:36","2013-04-21 21:21:19","253-278","","4","4","","User Model User-Adap Inter","Knowledge tracing","","","","","","","en","","","","","link.springer.com.ezp-prod1.hul.harvard.edu","","","","","","","Education (general); empirical validity; individual differences; intelligent tutoring systems; Learning; Management of Computing and Information Systems; mastery learning; Multimedia Information Systems; procedural knowledge; Psychology, general; student modeling; User Interfaces and Human Computer Interaction","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"XPWU2ASX","conferencePaper","2012","Siemens, George; Baker, Ryan S. J. d.","Learning Analytics and Educational Data Mining: Towards Communication and Collaboration","Proceedings of the 2Nd International Conference on Learning Analytics and Knowledge","978-1-4503-1111-3","","10.1145/2330601.2330661","http://doi.acm.org/10.1145/2330601.2330661","Growing interest in data and analytics in education, teaching, and learning raises the priority for increased, high-quality research into the models, methods, technologies, and impact of analytics. Two research communities -- Educational Data Mining (EDM) and Learning Analytics and Knowledge (LAK) have developed separately to address this need. This paper argues for increased and formal communication and collaboration between these communities in order to share research, methods, and tools for data mining and analysis in the service of developing both LAK and EDM fields.","2012","2017-09-14 16:03:36","2017-09-14 16:03:36","2015-01-16 03:15:55","252–254","","","","","","Learning Analytics and Educational Data Mining","","","","","ACM","New York, NY, USA","","","","","","ACM Digital Library","","","
Difference between Educational Data Mining and Learning Analytics:
1.EDM is in the tech field; LA is in educational field
2. EDM, automation and tech driven; LA use tech as a tool to enhance human judgement
3. EDM focuses more on individual learner; LA is more holistic
","","","","Collaboration; educational data mining; learning analytics and knowledge","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"SQAG6654","book","2015","Zheng, Alice","Evaluating Machine Learning Models","","","","","http://www.oreilly.com/data/free/evaluating-machine-learning-models.csp?intcmp=il-data-free-lp-lgen_free_reports_page","Data science today is a lot like the Wild West: there’s endless opportunity and excitement, but also a lot of chaos and confusion. If you’re new to data science and applied machine learning, evaluating a machine-learning model can seem pretty overwhelming...","2015-09","2017-09-14 16:03:36","2017-09-14 16:03:36","2015-12-15 18:26:39","","","","","","","","","","","","O'Reily Media","Sebastopol, CA","","","","","","","","","","","http://www.oreilly.com/data/free/evaluating-machine-learning-models.csp?intcmp=il-data-free-lp-lgen_free_reports_page","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"NHJB8FC6","videoRecording","2015","Educause","Why Is Measuring Learning So Difficult?","","","","","https://www.youtube.com/watch?v=_iv8A1pHNYA","Several higher education learning and assessment professionals discuss the difficulties of measuring learning.","2015-08-17","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-17 18:50:57","","","","","","","","","","","","","","","","","","","YouTube","","","Reasons:
1. Learning is multi-dimentional, and it is being simplified too much for analyzing.
2. Learning is broad, it is too contextualized to be measured outside its context.
3. Learning in different fields differ, and the availability of tools that can be used to analyze learning also differ across different fields.
4. Learning is personal, and the structure is hard to define, and it is the behaviors that can be captured, not necessarily the progress we made in our brain.
5. The hard part is how to measure, to find reliable and simple proxies indicators to measure learning. Certain indicators can indicate understanding.
6. Learning is complex, a black box, having other cultural and social meanings embedded.
7. A measure of competence is not enough, but also to measure at different time points to draw the conclusion of learning.
8. Measurement, psychological construct or achievement?
9. Analytics, to reveal to the learner the connections that they are making, probably without aware it, reveal more about their connected learning, not just diagnosis.
10. Learning might be a collection of things that we don't understand, regarding measuring it, both over-simplication and complexation are problems.
","","","","Assessment; Education; educational assessment; EDUCAUSE; Higher Education; learners; Learning; Teaching and learning","","","","","","","","","","","","","","","","","","","","","470 seconds","","","","","","","","","","","","","","","","","","","","","","","","","" +"DSECM45V","webpage","2016","Weinersmith, Zach","Saturday Morning Breakfast Cereal","","","","","http://www.smbc-comics.com/index.php?id=3978","","2016-01-05","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-18 18:17:09","","","","","","","","","","","","","","","","","","","","","","
Data Mining Bias.
In statistics, there is one kind of Type 1 error, the data mining bias, regarding enforced data mining trying to find any correlation or even causality that is actually frauds.
And as indicated in the comics, any compulsive finding can be easily manipulated in education policy or intervention, and it is like, what I personally call feeding the students the formula milk powder.
SO definitely data scientists should be extra cautious on any conclusion or intervention they suggest, even the most authentic data can tell a fraud if there is bias embedded.
","","http://www.smbc-comics.com/index.php?id=3978","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"2R3ZGZTN","webpage","2015","RStudio","The Data Wrangling Cheatsheet","","","","","http://www.rstudio.com/wp-content/uploads/2015/02/data-wrangling-cheatsheet.pdf","","2015-01","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-18 18:42:27","","","","","","","","","","","","","","","","","","","","","","Argument of a function is the same as a function call right?
","","http://www.rstudio.com/wp-content/uploads/2015/02/data-wrangling-cheatsheet.pdf","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"ZAKIPC8C","conferencePaper","2014","Clow, Doug","Data wranglers: human interpreters to help close the feedback loop","Proceedings of the Fourth International Conference on Learning Analytics And Knowledge","","","","","","2014","2017-09-14 16:03:36","2017-09-14 16:03:36","","49–53","","","","","","","","","","","ACM","","","","","","","","","","Feedback loop.
Closing the feedback loop to improve learning is at the heart of good learning analytic practice, which asks for high quality data, and also the need for and value of human meaning-making to interpret the data for the further step of transforming the data into actionable intelligence to truly achieve the effectiveness of feedback loop.
And the sector of learning analytics is widely seen as entailing a feedback loop, where the actionable intelligence is produced from data related to learning, to understand leaning and fundamentally to work out the interventions aiming of improving learning.
single-loop learning
double-loop learning
#Reason: A gap in knowledge and practice between the data about learning and the academics who need to be in a position to act to improve teaching provision: a gap that could easily widen as the quantity and complexity of data increases.
#The role of data wranglers: they are not only to analyze the data, but to increase the familiarity of academics with the data sources, to build the learning analytics capacity as part of a Community of Practice.
#Both bottoms-up and top-down for understanding learning and providing actionable intelligence: A bottom-up, grounded approach is necessary for sense making, saying that contextualization helps to understand; and meaningful engagement at the strategic, top-down level is also essential, especially regarding organizational changes that learning analytics aiming to achieve.
;
Human interpreters.
1. The need of multidisciplinary teams, when it comes to interpret the data, in which human interpreters play a key role, concluded from previous literature.
2. Sense-making and social processes are important, because of the complexity of the data we are dealing with, since learning itself is a complex and social process, and the action and intention to interpret the data definitely asks for the ability to contextualize it in understanding and analyzing it.
","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"JU4AKPZG","magazineArticle","2015","Kucirkova, Natalia; FitzGerald, Elizabeth","Zuckerberg is ploughing billions into 'personalised learning' – why?","The Conversation","","","","http://theconversation.com/zuckerberg-is-ploughing-billions-into-personalised-learning-why-51940","Zuckerburg wants to plough billions into personalised learning, but his way may not be the right way.","2015-12-09","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-18 19:14:05","","","","","","","","","","","","","","","","","","","","","","","","https://theconversation.com/zuckerberg-is-ploughing-billions-into-personalised-learning-why-51940","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"86ZVQZRC","videoRecording","2015","Georgia Tech","Feature Selection","","","","","https://www.youtube.com/watch?v=8CpRLplmdqE","","2015-02-23","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-18 19:18:06","","","","","","","","","","","","Youtube","","","","","","","","","","","","https://www.youtube.com/watch?v=8CpRLplmdqE","","","","","","","","","","","","","","","Udacity","","","","","","","","3:13","","","","","","","","","","","","","","","","","","","","","","","","","" +"QJRU4JT8","webpage","2014","Groelmund, Garrett","RStudio Cheat Sheets","RStudio","","","","https://www.rstudio.com/resources/cheatsheets/","","2014-08-01","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-19 21:17:28","","","","","","","","","","","","","","","","","","","","","","
It seems like a very useful resources, just I haven't played with R enough to practice everything.
","","http://shiny.rstudio.com/articles/rm-cheatsheet.html","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"FABPNTVB","journalArticle","2012","Greller, Wolfgang; Drachsler, Hendrik","Translating Learning into Numbers: A Generic Framework for Learning Analytics","Journal of Educational Technology & Society","","1176-3647","","http://www.jstor.org/stable/jeductechsoci.15.3.42","ABSTRACT With the increase in available educational data, it is expected that Learning Analytics will become a powerful means to inform and support learners, teachers and their institutions in better understanding and predicting personal learning needs and performance. However, the processes and requirements behind the beneficial application of Learning and Knowledge Analytics as well as the consequences for learning and teaching are still far from being understood. In this paper, we explore the key dimensions of Learning Analytics (LA), the critical problem zones, and some potential dangers to the beneficial exploitation of educational data. We propose and discuss a generic design framework that can act as a useful guide for setting up Learning Analytics services in support of educational practice and learner guidance, in quality assurance, curriculum development, and in improving teacher effectiveness and efficiency. Furthermore, the presented article intends to inform about soft barriers and limitations of Learning Analytics. We identify the required skills and competences that make meaningful use of Learning Analytics data possible to overcome gaps in interpretation literacy among educational stakeholders. We also discuss privacy and ethical issues and suggest ways in which these issues can be addressed through policy guidelines and best practice examples.","2012","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-09-03 18:55:41","42-57","","3","15","","Journal of Educational Technology & Society","Translating Learning into Numbers","","","","","","","","","","","","JSTOR","","","Validity and Reliability
Is LA, in fact, more as support technology itself while most of the stakeholders actually use it solely to tell the whole story? Apart from guaranteeing the reliability of the data, the external validity of the conclusion draw from learning analytics seems to be an underlying vulnerability of LA? saying if its representativity is valid to draw conclusion on either learning patterns or a particular education intervention, targeting a student population on a rather large scale.
If the answer is NO, then is it one of the reasons for L.Todd Rose to argue that education data should focus, more on individual learning, rather than the expected value of population?
","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"HSQ9RBVR","journalArticle","2015","Konstan, Joseph A.; Walker, J. D.; Brooks, D. Christopher; Brown, Keith; Ekstrand, Michael D.","Teaching Recommender Systems at Large Scale: Evaluation and Lessons Learned from a Hybrid MOOC","ACM Trans. Comput.-Hum. Interact.","","1073-0516","10.1145/2728171","http://doi.acm.org/10.1145/2728171","","2015-04","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-09-03 20:38:02","10:1–10:23","","2","22","","","Teaching Recommender Systems at Large Scale","","","","","","","","","","","","ACM Digital Library","","","","","","","learning assessment; Massively Online Open Course (MOOC)","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"UHSV7RKG","book","2015","Matsuda, Noboru; Furukawa, Tadanobu; Bier, Norman; Faloutsos, Christos","Machine Beats Experts: Automatic Discovery of Skill Models for Data-Driven Online Course Refinement","","","","","http://eric.ed.gov/?id=ED560513","How can we automatically determine which skills must be mastered for the successful completion of an online course? Large-scale online courses (e.g., MOOCs) often contain a broad range of contents frequently intended to be a semester's worth of materials; this breadth often makes it difficult to articulate an accurate set of skills and knowledge (i.e., a skill model, or the QMatrix). We have developed an innovative method to discover skill models from the data of online courses. Our method assumes that online courses have a pre-defined skill map for which skills are associated with formative assessment items embedded throughout the online course. Our method carefully exploits correlations between various parts of student performance, as well as in the text of assessment items, to build a superior statistical model that even outperforms human experts. To evaluate our method, we compare our method with existing methods (LFA) and human engineered skill models on three Open Learning Initiative (OLI) courses at Carnegie Mellon University. The results show that (1) our method outperforms human-engineered skill models, (2) skill models discovered by our method are interpretable, and (3) our method is remarkably faster than existing methods. These results suggest that our method provides a significant contribution to the evidence-based, iterative refinement of online courses with a promising scalability. [For complete proceedings, see ED560503.]","2015-06","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-09-03 20:48:57","","","","","","","Machine Beats Experts","","","","","International Educational Data Mining Society","","en","","","","","ERIC","","","","","http://eric.ed.gov/?id=ED560513","","Automation; Comparative Analysis; Correlation; data; Formative Evaluation; models; Online Courses; Skills","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"UMSMEUP5","bookSection","2016","Hanneman, R.A.; Riddle, M.","Chapter 1: Social Network Data","Introduction to Social Network Methods","","","","http://faculty.ucr.edu/~hanneman/nettext/C1_Social_Network_Data.html","","2016-01-18","2017-09-14 16:03:36","2017-09-14 16:03:36","2016-01-18 20:17:24","","","","","","","","","","","","","","","","","","","","","","","","http://faculty.ucr.edu/~hanneman/nettext/C1_Social_Network_Data.html","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"T7QD6X3J","bookSection","2017","Klerkx, Joris; Verbert, Katrien; Duval, Erik","Learning Analytics Dashboards","The Handbook of Learning Analytics","978-0-9952408-0-3","","","www.solaresearch.org","","2017","2017-09-14 16:03:36","2017-09-14 16:03:36","","","","","","","","","","","","","","Vancouver, BC, Canada","EN","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","1","","","","","","","","","","","","","","","","","","","","","","","","","","" +"92JGVPQH","bookSection","2017","Bergner, Yoav","Measurement and its Uses in Learning Analytics","The Handbook of Learning Analytics","978-0-9952408-0-3","","","http://solaresearch.org/hla-17/hla17-chapter1","Psychological measurement is a process for making warranted claims about states of mind. As such, it typically comprises the following: de ning a construct; specifying a measurement model and (developing) a reliable instrument; analyzing and accounting for various sources of error (including operator error); and framing a valid argument for particular uses of the outcome. Measurement of latent variables is, after all, a noisy endeavor that can neverthe- less have high-stakes consequences for individuals and groups. This chapter is intended to serve as an introduction to educational and psychological measurement for practitioners in learning analytics and educational data mining. It is organized thematically rather than historically, from more conceptual material about constructs, instruments, and sources of measurement error toward increasing technical detail about particular measurement models and their uses. Some of the philosophical differences between explanatory and predictive modelling are explored toward the end.","2017","2017-09-14 16:03:36","2017-09-14 16:03:36","","34-48","","","","","","","","","","","Society for Learning Analytics Research (SoLAR)","Alberta, Canada","","","","","","","","","Psychological Measurement
1. Composition: defining a construct; specifying a measurement model and developing a reliable instrument; analyzing and accounting for various sources of error (including operator error); and framing a valid argument for particular uses of the outcome.
2. Construct
- Construct is used interchangeably with latent variable, while trait is used to imply a construct that is stable over time. (e.g. tape measure provides a scale)
- Psychological constructs, e.g. math ability and extraversion, equating the constructs to scores on instruments used to measure them.
-We can infer an extremely partial list of constructs relevant to learning analytics from the instruments already developed to measure them.
3. Measurement Instruments
-tests, questionnaires, having items or indicators.
4. Error
- random error, unbiased,
- systematic, biased
5. Models to use
- Factor analysis
-Latent class and latent mixture models
-Item Response Theory
6. Explanation and/or Prediction
Learning analytics has been described as a middle space between learning science and analytics, so the field may benefit from understanding the nuances of both perspectives.
","","","","","Lang, Charles; Siemens, George; Wise, Alyssa Friend; Gaševic, Dragan","","","","","","","","","","","","","","","","","","","1","","","","","","","","","","","","","","","","","","","","","","","","","","" +"77XBSA87","bookSection","2017","Brooks, Christopher; Thompson, Craig","Predictive Modelling in Teaching and Learning","The Handbook of Learning Analytics","978-0-9952408-0-3","","","http://solaresearch.org/hla-17/hla17-chapter1","This article describes the process, practice, and challenges of using predictive modelling in teaching and learning. In both the elds of educational data mining (EDM) and learning analytics (LA) predictive modelling has become a core practice of researchers, largely with a focus on predicting student success as operationalized by academic achievement. In this chapter, we provide a general overview of considerations when using predictive modelling, the steps that an educational data scientist must consider when engaging in the process, and a brief overview of the most popular techniques in the eld.","2017","2017-09-14 16:03:36","2017-09-14 16:03:36","","61-68","","","","","","","","","","","Society for Learning Analytics Research (SoLAR)","Alberta, Canada","","","","","","","","","","","","","","Lang, Charles; Siemens, George; Wise, Alyssa Friend; Gaševic, Dragan","","","","","","","","","","","","","","","","","","","1","","","","","","","","","","","","","","","","","","","","","","","","","","" +"AI45PGIM","bookSection","2017","Prinsloo, P; Slade, S","Ethics and Learning Analytics: Charting the (Un)Charted","The Handbook of Learning Analytics","978-0-9952408-0-3","","","https://solaresearch.org/hla-17/hla17-chapter4/","","2017-03","2017-09-14 16:03:36","2017-09-14 16:03:36","","49-57","","","","","","","","","","","Society for Learning Analytics Research","Vancouver, BC","EN","","","","","","","","
Ethics
-Persuasive surveillance, the role and unintended consequences of algorithms.
-ethics and privacy as crucial enablers within learning analytics.
Is it inevitable, for people to realize the importance of the ethics only after a series of misconduct, or even catastrophic consequences? Just like in any other fields?
As in Finance sector, the CFA certificate allocates a huge weight on the ethics, aiming to address the ethics in the finance field, and though the Edtech field can adopt some similar approaches, saying ""inventing"" some kind of certificate exam stressing the importance ethics, but comes to the real world practice, it is the transparency and the regulation of the market increases people's trust on the data users.
But then comes to the question that, who and which entity has the entitlement to regulate? How can we deal with the monopoly of big corporation or any unwanted intervention of the state, or it is inevitably controversial and better than nothing?
It appeals to me that the entitlement of drafting and mapping code of ethics even indicate some sort of sovereign and power relation in the field?
","","","","","","","","","","","","","","","","","","","","","","","","1","","","","","","","","","","","","","","","","","","","","","","","","","","" +"8MKDWF3J","bookSection","2017","Liu, R; Koedinger, K","Going Beyond Better Data Prediction to Create Explanatory Models of Educational Data","The Handbook of Learning Analytics","978-0-9952408-0-3","","","https://solaresearch.org/hla-17/hla17-chapter6/","","2017-03","2017-09-14 16:03:36","2017-09-14 16:03:36","","69-76","","","","","","","","","","","Society for Learning Analytics Research","Vancouver, BC","EN","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","1","","","","","","","","","","","","","","","","","","","","","","","","","","" +"3TMIAKHH","journalArticle","2011","Gelman, A; Niemi, J","Statistical graphics: making information clear – and beautiful","Significance","","","","","","2011-09","2017-09-14 16:03:36","2017-09-14 16:03:36","","134-136","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"97C3DP3G","journalArticle","1984","Wainer, H","How to display data badly","The American Statistician","","","","","","1984","2017-09-14 16:03:36","2017-09-14 16:03:36","","137-147","","2","38","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"963EVMRB","journalArticle","2012","Gelman, A; Unwin, A","Infovis and Statistical Graphics: Different Goals, Different Looks (with discussion)","","","","","","","2012","2017-09-14 16:03:36","2017-09-14 16:03:36","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" +"U22PFWPE","blogPost","2014","Fung, K","Junkcharts Trifecta Checkup: The Definitive Guide","Junkcharts","","","","http://junkcharts.typepad.com/junk_charts/junk-charts-trifecta-checkup-the-definitive-guide.html","","2014","2017-09-14 16:03:36","2017-09-14 16:03:36","","","","","","","","","","","","","","","","","Blog","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","","" \ No newline at end of file