Geekly Articles each Day
📜 ⬆️ ⬇️

An attempt to teach students to program how to automate this process


It is this quote from Steve Jobs that greets visitors to the cs.betlabs.ru site as an attempt to motivate students to work harder on their homework and laboratory assignments. Unfortunately, I have no metrics for a quantitative assessment of the influence of motivation from a teacher on student performance. Moreover, I believe that the competitive environment in the study group is a much more important factor in the overall performance indicator. Now this is just a hypothesis, and its verification does not lie in the field of my scientific interests.



Prehistory


Like any postgraduate student, I have to spend 100 hours from the curriculum on teaching in the university. Specifically, I was faced with the task of conducting laboratory classes in the courses “Computer Science and the Basics of Algorithmization” and “Object-Oriented Programming” in C # for first-year students of business computer science . It is important to note the fact that the absolute majority of students thought it was possible, up to now, to consider that they would absolutely not need programming in their current and future activities.


First year


In the first year and the first semester of teaching, I had two study groups with a total of 58 people. Tasks: to carry out tests, check individual homework assignments and set a mark on a 5-point scale on semester work. The mark I set is not final, and the final mark is determined on the lecture exam.


The load was large, it was necessary to do a lot, so very often I heard comments from students about the fact that they would not need this subject in life. I often held explanatory conversations about the fact that my cognitive abilities need to be trained and programming is an excellent tool in order to prepare the brain for systemic and at the same time creative thinking . I do not think that my words found a response in most minds, but it seems to me that a number of students thought and found programming useful for themselves.


Software and Services



How did the control and delivery of DZ


I just got acquainted with the process of conducting laboratory classes, for this I did as the lecturer recommended. Control wrote on paper sheets. All the time laboratory work went on checking homework. I “by sight” checked the work of programs.


Results

Statistics of visits to the page with a list of tasks for homework. In the fall semester, students actively begin to study in mid-November.


At the end of the semester, I conducted an anonymous survey on classic questions about the course and the benefits of the subject. The average usefulness of the subject was estimated at 3.76 , the subject’s fascination was 3.95 , on a five-point scale.


The results on the exams and the marks I predicted in most cases coincided ( precision 90% ). One group managed to show the best result among other training groups of the entire external flow. In my opinion, one of the factors could be the competitive environment formed in the group. I compared the results of the USE of students of both groups, the averages and medians roughly coincide, respectively, and the performance on the exam is noticeably different in the top five.


Second year


It's time for productivity and automation!


The tasks were the same, the students are freshmen again, but this time I decided to increase the KPI by fascination, clarity and usefulness, and not by the final mark on the exam. My students are yesterday's schoolchildren, most of them did not pass the EGE on computer science, in general were absolute zeros in programming. A little inspired by the course of the Harvard CS50 , I decided that the routine should be automated, freeing up time for students' questions and a detailed explanation of the course material.


Software and Services



How did the control and delivery of DZ


The desire to automate the verification of tasks led me to the idea that I would have to teach students to use git. I basically needed a ready, almost perfect boxed solution. This solution was the service HackerRank. This service + aaa (add. Functionality written by me using the official API) allowed me to automatically check the tasks and see the work written off (plagiarism detector). On the preparation of tasks and writing tests takes more time, but it needs to be done only once. It seems someone has written off and not shy: (


Setting semester marks


I would like to dwell on this part in more detail. I promise not to use difficult terms and explain everything on your fingers.


First, I wanted to remove the teacher’s subjectivity in assessing student performance. Second, do not think about what marks someone has, how to consider the final, what should be the scale, etc. Third, take into account virtually any “sneeze” (attendance, activity in class, etc.) of a student as a factor in setting a semester mark.


What data did I collect?



All this merges into one table, is scaled and fed into the input of the K-Means algorithm, the result of which will be mapped between the student and the cluster to which he belongs (marks 2, 3, 4, 5).


We ask the computer to divide the set into 4 subsets in the way it “seems” to be more objective.


import pandas as pd import numpy as np from sklearn.cluster import KMeans from sklearn import preprocessing from sklearn.decomposition import PCA # Learn clu = KMeans(n_clusters=4, random_state=240) clu.fit(processed_data) # Clusters labels = pd.DataFrame(clu.labels_) # Reduce space dimension pca = PCA(n_components=3) pca.fit(processed_data) pca_processed_data = pca.transform(processed_data)

Using the simplest methods of machine learning does not require complex preparation


Here are the marks and clusters in the three-dimensional feature space. Definitely someone needs to put two and automatic :)


image
Student clustering by grades (KMeans)


At first glance, the resulting grades coincide with my view on the performance of specific students. If such an approach is applied universally and the data of the training sample is collected, it will be possible to predict the mark at the end of the semester by the progress in the first month (hypothesis) of training. Thus, it will allow to identify “problem” students in time and offer them help in additional clarification of the material.



Instead of conclusion


Laboratory classes are now fully devoted to the explanation of the material and problem solving. Whether this will show an increase in established KPIs remains an open question.


The HackerRank service for educational purposes described above is not a very convenient tool with the absence of very important and convenient features. According to this classic, Market Research → Customer Development → MVP → pre-seed → seed
... well, you know.


')

Source: https://habr.com/ru/post/320426/

More articles:


All Articles