Schedule meeting
PROJECT

Automated analysis of student comments to courses and teachers evaluations

Course survey comments have organic and honest feedback about the quality of the courses and the teacher.

This information is not captured by the survey's closed-ended questions and, given its free-text quality, it is unstructured information that is generally not used in a systematic or quantitative way by the University with which this project was developed.

The objective of this project was to apply natural language processing (NLP), machine learning and data mining methodologies to the free-text comments of courses and teachers evaluations at a university to automatically classify the comments according to their degree of polarity (positive-negative) and according to dimensions and aspects of pedagogy addressed. In addition, topic models were implemented to analyze the topics addressed by students in their comments. The former makes it possible to generate quantitative indicators of the quality of courses and teachers for different relevant dimensions of teaching and to provide feedback to teachers and adjust courses according to such indicators. The second allows identifying recurrent topics that students address in their free-text comments and that are not taken into account in the closed part of the survey, so that quantitative metrics of such dimensions are not generated.

Approach

We worked with about 7.000 comments made by students to courses and teachers during one year. Of these, 2.000 records were manually marked indicating their polarity (positive-negative on a scale of 0 to 3) and the comments were classified into 20 predefined, non-mutually exclusive categories, corresponding to the aspects of teaching addressed in each one. This was done in conjunction with the University's Faculty of Education. The texts were preprocessed and topic models were constructed using Latent Dirichlet Allocation (LDA). The texts were vectorized using Bag of Words and LDA, and machine learning methodologies (Naive Bayes, Logit, SVM, Boosting trees) were trained and their predictive capacity was evaluated to choose the best model.

Results

Automation for the classification of comments according to their degree of polarity (positive-negative). Generation of quantitative indicators of course and teacher quality for different relevant dimensions of teaching and identification of recurrent themes that students address in their free-text comments.

“ It is the glory of science to be of no use…[its true aim]… is to honor of the human spirit ”
Carl Gustav Jacobi
“ Truth and Clarity are Complementary ”
Niels Bohr
“ I have finished a monument more lasting than bronze and higher than the royal structure of the pyramid ”
Scarf
“ Applied mathematics is the bridge connecting pure mathematics with science and technology ”
Prager
“ In truth mathematics can be called the Pleasure Garden of the myriad forms, the Erudite Ocean of Hundred Schools of Philosophy ”
Xu Guangpi
“ Just as the ability to devise simple but evocative models is the signature of the great scientist so overelaboration and overparameterization is often the mark of mediocrity ”
G. Box
“ Since all models are wrong the scientist cannot obtain a “correct” one by excessive elaboration. On the contrary following William of Occam he should seek an economical description of natural phenomena ”
G. Box
“ ..ten thousand years from now there can be little doubt that the most significant event of the 19th century will be judged as Maxwell’s discovery of the laws of electrodynamics ”
R. Feynman
“ The simplicities of natural laws come through the complexities of the language we use for their expression ”
Eugene Wigne
“ We have found that where science has progressed the farthest, the mind has but regained from nature that which the mind has put into nature. We have found a strange foot–print on the shores of the unknown ”
Eddington
“ Reason is, and ought to be the slave of the passions ”
David Hume
“ Every problem in the calculus of variations has a solution, provided the word solution is suitably understood ”
D. Hilbert
“ Applied mathematics is not a definable scientifc field but a human attitude ”
Courant
“ The moment will come when the sun will shine only on a planet of free men, knowing only reason as their master ”
Codorcet
“ Thus mathematics may be defined as the subject in which we never know what we are talking about, nor whether what we are saying is true ”
Bertrand Russell
“ One cannot help having the gut feeling that a real understanding of our universe must somehow involve E_8 [a Lie group comprising a system of 240 vectors in 8–dimensional space] ”
Bertram Kostant
“ Sometimes attaining the deepest familiarity with a question is our best substitute for actually having the answer ”
B.Greene
“ Mathematics is like sexual pleasure, orgasm, only lasting longer ”
André Weil
“ The eternal mystery of the world is its comprehensibility ”
A. Einstein
“ Everything should be made as simple as possible, but not simpler ”
A. Einstein
Previous
Next

Other projects

In Projects, you can learn about real applications of our services, use cases and examples of them.

Pensiones1

Contractual Design for the Management of FONPET

Energia_electrica

Systemic Risk of Electricity Supply

planes-desarrollo1

Inventory Logistics - Multimodal Transportation

transporte_multimodal1

Integrated Development Plans

estrategia_de_deuda_banner

Ministry of Finance and Public Credit (MHCP) defines a Debt Management Strategy

reportes

Asset Allocation Model in an insurance company