Please review our proposal for a new moodle report plugin for assisted manual grading of essay questions.
We built a new report plugin for manual grading of essay questions. It is based on quiz_grading_report and builds the grading report in just the same way - with only one main difference: before presenting the student answers for grading, they are roughly sorted by quality in descending order. The score we use for sorting for quality is determined by a webservice. Therefore, in the new moodle plugin, we send relevant data such as question, reference answer and student answer to the webservice and receive the corresponding score for each student answer. The calculation of the score is based on meaning comparison - student answer and reference answer are represented as lists of words omitting all stopwords and all words that already occured in the question. Words are reduced to their lemma forms before calculating the text similarity between these two representations using the Greedy String Tiling algorithm (vgl. Wise (1996)). The intention behind the plugin and first evaluation results may be found in (Kiefer und Pado (2015)).

Here is the link to the repository:
https://github.com/HftKiefer/moodle-plugin-assisted-grading

Here is the link to the war-packaged web service:
http://www.connsulting.de/software/software.htm

Here is the link to the source code of the web service:
https://github.com/HftKiefer/webservice-assisted-grading
https://github.com/HftKiefer/linguistic-analysis-assisted-grading

Installation:
1. Deploy the webservice GA.war on Apache Tomcat
2. Put the folder assistedgrading under server/moodle/mod/quiz/report in your Moodle installation to install it as a new Moodle plugin. You will need to specify the webservice address each time you want to use the grading assistant report, therefore you may want to change the default base address in report.php, line 34. The webservice base adress for example may look like this: 'http://123.456.789.123:8080/GA/webresources/gradingassistant'.

References
C. Kiefer und U. Pado, Freitextaufgaben in Online-Tests: Bewertung und Bewertungsunterstützung. HMD Praxis der Wirtschaftsinformatik, 52(1), 96-107. 2015. (pre-final version available here: http://www.connsulting.de/veroeffentlichungen/veroeffentlichungen.htm)

[Wise 1996] Wise, Michael J.: YAP3: Improved Detection Of Similarities In
Computer Program And Other Texts. In: SIGCSEB: SIGCSE Bulletin (ACM
Special Interest Group on Computer Science Education, ACM Press, 1996, S.
130–134