Highlight some LA/EDM studies in the introduction

bibliography.bib

@@ -15,6 +15,25 @@
   file = {/home/charlotte/sync/Zotero/storage/UTI4XVZ2/Abu Tair and El-Halees - 2012 - Mining educational data to improve students' perfo.pdf;/home/charlotte/sync/Zotero/storage/II5LNING/25066.html}
 }
 
+@article{akcapinarUsingLearningAnalytics2019,
+  title = {Using Learning Analytics to Develop Early-Warning System for at-Risk Students},
+  author = {Ak{\c c}ap{\i}nar, G{\"o}khan and Altun, Arif and A{\c s}kar, Petek},
+  year = {2019},
+  month = oct,
+  journal = {International Journal of Educational Technology in Higher Education},
+  volume = {16},
+  number = {1},
+  pages = {40},
+  issn = {2365-9440},
+  doi = {10.1186/s41239-019-0172-z},
+  url = {https://doi.org/10.1186/s41239-019-0172-z},
+  urldate = {2024-02-14},
+  abstract = {In the current study interaction data of students in an online learning setting was used to research whether the academic performance of students at the end of term could be predicted in the earlier weeks. The study was carried out with 76\,second-year university students registered in a Computer Hardware course. The study aimed to answer two principle questions: which algorithms and features best predict the end of term academic performance of students by comparing different classification algorithms and pre-processing techniques and whether or not academic performance can be predicted in the earlier weeks using these features and the selected algorithm. The results of the study indicated that the kNN algorithm accurately predicted unsuccessful students at the end of term with a rate of 89\%. When findings were examined regarding the analysis of data obtained in weeks 3, 6, 9, 12,~and 14~to predict whether the end-of-term academic performance of students could be predicted in the earlier weeks, it was observed that students who were unsuccessful at the end of term could be predicted with a rate of 74\% in as short as 3\,weeks' time. The findings obtained from this study are important for the determination of features for early warning systems that can be developed for online learning systems and as indicators of student success. At the same time, it will aid researchers in the selection of algorithms and pre-processing techniques in the analysis of educational data.},
+  langid = {english},
+  keywords = {Academic performance prediction,At-risk students,Early-warning systems,Educational data mining,Learning analytics,Online learning},
+  file = {/home/charlotte/sync/Zotero/storage/C58SJ23T/Akçapınar et al. - 2019 - Using learning analytics to develop early-warning .pdf;/home/charlotte/sync/Zotero/storage/RMSJIVAI/10.1186@s41239-019-0172-z.pdf.pdf}
+}
+
 @article{akcayirFlippedClassroomReview2018,
   title = {The Flipped Classroom: {{A}} Review of Its Advantages and Challenges},
   shorttitle = {The Flipped Classroom},
@@ -952,6 +971,25 @@
   file = {/home/charlotte/sync/Zotero/storage/PSFFZRJP/Danielson and Others - 1976 - Final Report on the Automated Computer Science Edu.pdf}
 }
 
+@inproceedings{daudPredictingStudentPerformance2017,
+  title = {Predicting {{Student Performance}} Using {{Advanced Learning Analytics}}},
+  booktitle = {Proceedings of the 26th {{International Conference}} on {{World Wide Web Companion}}},
+  author = {Daud, Ali and Aljohani, Naif Radi and Abbasi, Rabeeh Ayaz and Lytras, Miltiadis D. and Abbas, Farhat and Alowibdi, Jalal S.},
+  year = {2017},
+  month = apr,
+  series = {{{WWW}} '17 {{Companion}}},
+  pages = {415--421},
+  publisher = {{International World Wide Web Conferences Steering Committee}},
+  address = {{Republic and Canton of Geneva, CHE}},
+  doi = {10.1145/3041021.3054164},
+  url = {https://dl.acm.org/doi/10.1145/3041021.3054164},
+  urldate = {2024-02-14},
+  abstract = {Educational Data Mining (EDM) and Learning Analytics (LA) research have emerged as interesting areas of research, which are unfolding useful knowledge from educational databases for many purposes such as predicting students' success. The ability to predict a student's performance can be beneficial for actions in modern educational systems. Existing methods have used features which are mostly related to academic performance, family income and family assets; while features belonging to family expenditures and students' personal information are usually ignored. In this paper, an effort is made to investigate aforementioned feature sets by collecting the scholarship holding students' data from different universities of Pakistan. Learning analytics, discriminative and generative classification models are applied to predict whether a student will be able to complete his degree or not. Experimental results show that proposed method significantly outperforms existing methods due to exploitation of family expenditures and students' personal information feature sets. Outcomes of this EDM/LA research can serve as policy improvement method in higher education.},
+  isbn = {978-1-4503-4914-7},
+  keywords = {educational data mining (edm),family expenditures,learning analytics (la),student performance prediction,students personal information},
+  file = {/home/charlotte/sync/Zotero/storage/J3NBDBIQ/Daud et al. - 2017 - Predicting Student Performance using Advanced Lear.pdf;/home/charlotte/sync/Zotero/storage/VED4SMRC/daud2017.pdf.pdf}
+}
+
 @article{dawsonAssessmentRubricsClearer2017,
   title = {Assessment Rubrics: Towards Clearer and More Replicable Design, Research and Practice},
   shorttitle = {Assessment Rubrics},
@@ -2502,6 +2540,26 @@
   file = {/home/charlotte/sync/Zotero/storage/35UGGC92/Maertens et al. - 2023 - Dolos 2.0 Towards Seamless Source Code Plagiarism.pdf}
 }
 
+@article{mahLearningAnalyticsDigital2016,
+  title = {Learning {{Analytics}} and {{Digital Badges}}: {{Potential Impact}} on {{Student Retention}} in {{Higher Education}}},
+  shorttitle = {Learning {{Analytics}} and {{Digital Badges}}},
+  author = {Mah, Dana-Kristin},
+  year = {2016},
+  month = oct,
+  journal = {Technology, Knowledge and Learning},
+  volume = {21},
+  number = {3},
+  pages = {285--305},
+  issn = {2211-1670},
+  doi = {10.1007/s10758-016-9286-8},
+  url = {https://doi.org/10.1007/s10758-016-9286-8},
+  urldate = {2024-02-14},
+  abstract = {Learning analytics and digital badges are emerging research fields in educational science. They both show promise for enhancing student retention in higher education, where withdrawals prior to degree completion remain at about 30~\% in Organisation for Economic Cooperation and Development member countries. This integrative review provides an overview of the theoretical literature as well as current practices and experience with learning analytics and digital badges in higher education with regard to their potential impact on student retention to enhance students' first-year experience. Learning analytics involves measuring and analyzing dynamic student data in order to gain insight into students' learning processes and optimize learning and teaching. One purpose of learning analytics is to construct predictive models to identify students who risk failing a course and thus are more likely to drop out of higher education. Personalized feedback provides students with information about academic support services, helping them to improve their skills and therefore be successful in higher education. Digital badges are symbols for certifying knowledge, skills, and competencies on web-based platforms. The intention is to encourage student persistence by motivating them, recognizing their generic skills, signaling their achievements, and capturing their learning paths. This article proposes a model that synthesizes learning analytics, digital badges, and generic skills such as academic competencies. The main idea is that generic skills can be represented as digital badges, which can be used for learning analytics algorithms to predict student success and to provide students with personalized feedback for improvement. Moreover, this model may serve as a platform for discussion and further research on learning analytics and digital badges to increase student retention in higher education.},
+  langid = {english},
+  keywords = {Academic competencies,Digital badges,Generic skills,Learning analytics,Student retention},
+  file = {/home/charlotte/sync/Zotero/storage/2ATKA34V/mah2016.pdf.pdf;/home/charlotte/sync/Zotero/storage/SFY9BQJN/Mah - 2016 - Learning Analytics and Digital Badges Potential I.pdf}
+}
+
 @article{malouffBiasGradingMetaanalysis2016,
   title = {Bias in Grading: {{A}} Meta-Analysis of Experimental Research Findings},
   shorttitle = {Bias in Grading},

book.org

@@ -294,16 +294,30 @@ Learning analytics and educational data mining stand at the intersection of comp
 They are made possible by the increased availability of data about students who are learning, due to the increasing move of education to digital platforms\nbsp{}[cite:@romeroDataMiningCourse2008].
 They can also serve different actors in the educational landscape: they can help learners directly, help teachers to evaluate their own teaching, allow educational institutions to guide their decisions, or even allow governments to take on data-driven policies\nbsp{}[cite:@fergusonLearningAnalyticsDrivers2012].
 Learning analytics and educational data mining are overlapping fields, but in general, learning analytics is seen as focusing on the educational challenge, while educational data mining is more focused on the technical challenge\nbsp{}[cite:@fergusonLearningAnalyticsDrivers2012].[fn::
-The analytics focusing on governments/educational instutions is also called academic analytics.
+The analytics focusing on governments or educational institutions is called academic analytics.
 ]
 
 [cite/t:@chattiReferenceModelLearning2012] defined a reference model for learning analytics based on four dimensions:
 #+ATTR_LATEX: :environment enumerate*
 #+ATTR_LATEX: :options [label={\emph{\roman*)}}, itemjoin={{ }}, itemjoin*={{ }}]
 - What data is gathered and used?
-- Who is targeted by the analsis?
+- Who is targeted by the analysis?
 - Why is the data analysed?
 - How is the data analysed?
+This gives an idea to researchers what to focus on when conceptualizing, executing, and publishing their research.
+
+An example of an Educational Data Mining study is\nbsp{}[cite/t:@daudPredictingStudentPerformance2017], where the students' background (including family income, family expenditures, gender, martial status, ...) is used to predict the student's learning outcome at the end of the semester.
+Evaluating this study using the reference model by\nbsp{}[cite:@chattiReferenceModelLearning2012], we can see that the data used is very personal and hard to collect.
+As mentioned in the study, the primary target audience of the study are policymakers.
+The data is analysed to evaluate the influence of a student's background on their performance.
+The data is analysed using a number of machine learning techniques.
+
+Another example of the research in this field is a study by\nbsp{}[cite/t:@akcapinarUsingLearningAnalytics2019].
+They focus on the concept of an early warning system, where student performance can be predicted early and appropriate action could be undertaken.
+Their study uses data from a blended learning environment, where students can see the lesson's resources, participate in discussions, and write down their own thoughts about the lessons.
+Here, the primary target audience is the student.
+Although the related actions are not yet in scope of the study, the primary goal is to develop such an early warning system.
+Again, a number of machine learning techniques are compared, to determine which one gives the best results.
 
 ** Structure of this dissertation
 :PROPERTIES:
@@ -2396,8 +2410,8 @@ The process of giving feedback on a programming assignment in Dodona is very sim
 
 However, there exists a crucial distinction between traditional code reviews and those in an educational context: instructors often provide feedback on numerous solutions to the same assignment.
 Given that students frequently commit similar errors, it logically follows that instructors repeatedly deliver the same feedback across multiple student submissions.
-In response to this repetitive nature of feedback, Dodona has implemented a feature enabling instructors to save and later retrieve specific annotations.
-This functionality facilitates the reuse of feedback by allowing teachers to search for previously saved annotations.
+In response to this repetitive nature of feedback, Dodona has implemented a feature enabling instructors to save and later retrieve specific messages.
+This functionality facilitates the reuse of feedback by allowing teachers to search for previously saved messages.
 By using this functionality, we have generated data that we can use in this study: code submissions, where those submissions have been annotated on specific lines with messages that are shared over those submissions. 
 
 Note that there are two concepts here, whose distinction is important.
@@ -2573,7 +2587,7 @@ subtree_matches(subtree, pattern):
 
 Checking whether a pattern matches a subtree is an operation that needs to happen a lot of times.
 For some messages, there are many patterns, and all patterns of all messages are checked.
-One important optimization we added was therefore to only execute the algorithm in Listing\nbsp{}[[lst:feedbackmatchingpseudocode]] if the set of labels in the pattern is a subset of the labels in the pattern.
+One important optimization we added was therefore to only execute the algorithm in Listing\nbsp{}[[lst:feedbackmatchingpseudocode]] if the set of labels in the pattern is a subset of the labels in the subtree.
 
 **** Ranking the messages
 :PROPERTIES: