2020 6th International Conference on Advanced Computing & Communication Systems (ICACCS)

Performance Analysis on Student Feedback using

Machine Learning Algorithms
Sharnitha Katragadda Varshitha Ravi Prasanna Kumar
Student Scholar,IT Department, Student Scholar,IT Department, Student Scholar,IT Department,
VR Siddhartha Engineering College, VR Siddhartha Engineering College, VR Siddhartha Engineering College,
Vijayawada,India Vijayawada,India Vijayawada,India
[email protected] [email protected] [email protected]

G. Jaya Lakshmi
Assistant Professor,IT Department,
VR Siddhartha Engineering College,
Vijayawada,India
[email protected]

Abstract— It investigates opinion mining by means of The focal point is on utilizing Opinion Mining approach for
supervised learning techniques to search out the emotion of the categorizing the student’s feedback received all through
student input bolstered characterized choices of instructing component estimate survey that is accomplished each
and learning. The examination led includes the apparatus of a
semester to understand comments of scholars in regards to
blend of AI and common language preparing systems on
understudy input data accumulated from module investigation
several options of coaching and knowledge like module,
overview consequences of VR Siddhartha Engineering College, teaching, assessments, and so forth. The mined and
Vijayawada. Additionally, to offer a grade by grade preprocessed datasets be subjected to several supervised
clarification of the technique of accomplishment of opinion opinion mining method like aid Vector gadget (SVM),
mining on or after scholar remarks using the open source tool Naive Bayes (NB), Artificial Neural Networks (NN) applied
Python, the work additionally offers a comparative overall the usage of Python, the open supply device accessible for
performance take a look remarks supported, extracted opinion mining. The proportional effectiveness of the
alternatives like examination, teaching and so on. The algorithms in the selected utility circumstance is evaluated
consequences are as compared to be trying to find out higher exploitation accuracy; take into account and accuracy
overall performance with relevance several evaluation
standards designed for the various techniques.
measures. Accurateness is outlined because of the
quantitative relation of entire classifications that place unit
Keywords— Opinion mining, Sentiment analysis, Supervised specifically to the entire style of knowledge set. Accuracy is
learning, Natural Language Processing, that the quantitative relation of true positives toward the
whole type of positives that vicinity unit foretold while
I. INTRODUCTION keeping in mind is that the quantitative relation of actual
positives by means of the complete positives inside the
The total of information that whichever organization within dataset.
the humankind managing is huge. This “Big Data” is often
characterizing by three V’s i.e. volume, velocity, and II. LITERATURE SURVEY
selection. It is usually a lot of concerning of these three The paper spotlight on victimization Opinion Mining
dimensions coming back along than considering any of them method for classifying the student's comments acquired
on an individual basis. The existence of enormous amount during module evaluation survey. The mined and
of ordered records much like grades, conscription preprocessed datasets have been based to numerous
information, and development quotes likewise as supervised evaluations taking out rule like aid Vector Naïve
unstructured in order like scholar opinions articulated via Bayes (NB), Nearest Neighbor (KNN) and Neural Networks
surveys, it will become time and useful source (NN) enforced [1].
overwhelming to précis the facts by hand to gain It is visible currently that there is a rise of expertise
information lead conclusions and alternatives. availableness, the alleged statistics deluge, controlled by
accomplice inflated amount of electronic motion
Studying analytics can be discipline of information analytics accomplished, and additionally the revolutionary pervasive
to procedures, analyzes, reviews and predicts facts regarding attain of IT altogether gadgets. the number one of those
learners for the aim of optimizing coaching and studying. developments is that the supposed open statistics
On the opposite side, it is essential to recognize the outline association, distinguished by the manner that the complete
generated by means of the information like scholar feedback method throughout European and also the united states,
to correctly develop the overall routine of the established governments area unit more and more e-book their
order and to form plans to reinforce institutions’ coaching information repositories for humans to admittance and use it
and mastering understanding. From among the numerous any other pattern issues the inconceivable amount of
systems for aggregation pupil comments, surveys contain a knowledge is formed handy by electorate through
vital position and most of the establishments commence participatory sensing": commonplace play a practical
surveys in several paperwork.

978-1-7281-5197-7/20/$31.00 ©2020 IEEE 1161

Authorized licensed use limited to: James Cook University of Northern Queensland. Downloaded on June 02,2020 at 10:39:15 UTC from IEEE Xplore. Restrictions apply.
2020 6th International Conference on Advanced Computing & Communication Systems (ICACCS)

position in booklet commentary and grumbling online, and A collection of associated information including disconnect
increasingly more make use of novelty to report further in data fundamentals stored, retrieved, or else organized and
sequence.[2] indulgence as a unit, i.e., folder. For our project, we are
using a comma-separated value data structure. Datasets are
The paper projected a web feedback system that is of two types’ linear dataset and non-linear dataset. The
concerning automating the method of recording student’s linear dataset is the one which is having equal properties
feedback. The projected system collects the feedback whereas the non-linear dataset is the one which is having
submitted by students and so classifies them as positive non-equal properties. Machine learning works well for
feedbacks or negative feedbacks victimization SVM linear datasets. The datasets contain reviews made by
classifier. Then, it generates a performance outline of a students. This dataset contains 30,000 reviews with their
coach for the themes he or she schooled there in academic student_id, student_ name, review, and their emotion. The
term employing a delimited account rule. In my view, the review contains textual input about the college.
projected system may be helpful for the educational Pre-processing is the progression of concentrated effort the
establishments and may additionally facilitate academics to data from redundant elements. It enlarges the accurateness
know their teaching performance in an exceedingly of the results by dropping errors in the data. Not by means
summarized manner. This projected a web feedback system of pre-processing, such as enchantment corrections, may
which might record the student’s feedback and analyze the lead the system to disregard important words. Pre-
teacher's performance supported opinion mining processing and concentrated effort of data are one of the
victimization SVM classifier and so summarizes the teacher most important tasks that must be one before dataset be able
performance supported delimited outline rule i.e. count to be used for machine learning. The real-world statistics is
frequency of positive and negative reviews.[3] strident, incomplete and incompatible. So, it is necessary to
be cleaned. There are many general pre-processing
The work aims to dig deeper into the feedback information techniques, of which the majority common is: tokenization,
of an establishment. Presently the feedback information is convert text to lower or upper case, eliminate punctuation,
employed to report solely the performance of the teacher. take away numbers, take out repeated letters, get rid of stop
The paper proposes ways to research the feedback words, stemming and negation. The data that is obtained
information victimization data processing techniques for a after the pre-processing is done is given to the Machine
higher understanding of the college, course, and student. learning algorithm.
The format of feedback varies from establishment to Later the data is skilled through the machine learning
establishment, thus there cannot be a general technique algorithms. The built Machine learning models present the
which will appropriate all. The feedback information from confusion matrix and the accurateness of the models. The
the scholars is analyzed by victimization completely dealing out time for running this module is also
different data processing techniques. The feedback demonstrated. The output of the algorithm is that it results in
information is used for analyzing all the parameters thought a new column which shows the predicted emotion of the
of for feedback which might facilitate management in review.
creating policy choices in teaching-learning method. This
Paper surveys all data processing technique that is applied IV.EXPERIMENTAL RESULTS
for analyzing feedback information.[4] In this investigation work python is used to discover how
well the algorithm mechanism on the feedback given by the
students based on the accuracy metric.
III. METHODOLOGY The dataset that contains of the feedback from students is
The data is collected from the students in the form of the pre-processed by removing the stop words and stemming of
feedback of the college. The feedback consists of the textual words. Then the pre processed dataset is subjected to the
reviews. Then the data pre-processing is done on the data Naive Bayes algorithm
that is collected. Later the Opinion classification is
performed on the dataset and the results are
obtained.

Fig 4.1 Classification report of naïve bayes

The Fig 4.1 describes that the model has 50% accuracy for
the random values in the dataset.
It has calculated the precison, recall for the classes of that
randomly choosen feedbacks in the dataset.
978-1-7281-5197-7/20/$31.00 ©2020 IEEE 1162

Authorized licensed use limited to: James Cook University of Northern Queensland. Downloaded on June 02,2020 at 10:39:15 UTC from IEEE Xplore. Restrictions apply.
2020 6th International Conference on Advanced Computing & Communication Systems (ICACCS)

the feedback report effectively and evaluating school

performance in the type of a summarized read might be
helpful for the establishments.
The opinion mining is that the method of insights taking out
that be procured to look into assessments of students for any
examination. For the length of this, the conclusion mining at
the coed remarks created through reviews abuse managed
gadget becoming acquainted with calculations upheld
through Python. Several opinion mining systems are audited
and referred to. Our results proved that the engineered
Neural Networks algorithmic regular hit others as far as
accuracy.
In the future assessment, we resolve in broad absolute
conclusion mining of student feedback gathered from web-
based life and moreover to investigate however the coed
sentiment changes misuse various socioeconomics like age
Fig 4.2 Classification report of SVM sex, etc. We have a propensity to in addition look forward to
to improve the effecting of conclusion mining system. The
The Fig 4.2 represents that the accurateness of the affordable opinion mining method resolve be arranged and
representation is 60% by using the support vector machine consequences will be dissected as far as different
algorithm. The accuracy of the SVM representation is better parameters. We measure expecting to build up the arranged
than that of the naïve Bayes model. framework which would encourage organizations by
assessing our framework and would without a doubt benefit
the instructional exercise foundations. The arranged
framework might be stretched out to various zones like
amassing inputs for workshops and short-run courses.

REFERENCES

[1]. V. Dhanalakshmi ; Dhivya Bino “Opinion mining from student

feedback data using supervised learning algorithms”, 2016 3rd
MEC International Conference on Big Data and Smart City
(ICBDSC)
[2]. Sarpreet Kaur1 , Rasleen Deol,” Students Feedback for Mining
Their Opinions Using Supervised Learning Algorithm”
International Journal of Engineering Science and Computing,
June 2017
Fig 4.3 Classification report of ANN [3]. Vaibhav Jain,Evaluating and Summarizing Student’s Feedback
Using Opinion Mining , International Journal of Scientific
Research in Computer Science and Engineering
The Fig 4.3 represents that the accurateness of the [4]. Anushree Chitriv, Prof. A. Thomas Analysis of Student
representation is 88% by using the artificial neural networks Feedback by Using Data Mining Techniques , Helix 2018
algorithm. It is clearly shown that the ANN algorithm have [5]. Khan, Khairullah, “Mining opinion components from
outperformed all other machine learning algorithms. unstructured reviews: A review,” Journal of King Saud
University – Computer and Information Sciences , Vol. 26,
Algorithm Used Accuracy Obtained 2016.
[6]. Pang, B. and Lillian L. s.l, “Opinion mining and sentiment
analysis : Foundations and trends in information retrieval”, Vol.
Naïve Bayes 50 2, 2016.
[7]. Kumar Ravi, Vadlamani Ravi, “A survey on opinion mining and
Support Vector Machine 60.8 sentiment analysis: Tasks, approaches and applications”,
Published in Knowledge-Based Systems Vol. 89 , 14–46, 2017.
Artificial Neural Network 88.2 [8]. S.Vijayarani, “Preprocessing Techniques for Text Mining - An
Overview”, International Journal of Computer Science &
Communication Networks, Vol 5(1),7-16.
[9]. Trisha Patel, “Sentiment Analysis of Parents Feedback for
Educational Institutes”, International Journal of Innovative and
V.CONCLUSION AND FUTURE WORK Emerging Research in Engineering, Volume 2, Issue 3, 2017.
Sentence level sentiment mining become accustomed [10]. SunghwanMacKim and Rafael, “Sentiment Analysis in Student
Experiences of Learning”, Available at ResearchGate.com
removes the remarked normal alternatives and evaluation [11]. Vijayarani,Ilamathi, and Nithya“Preprocessing Techniques for
words from the contribution dataset. A Student Feedback Text Mining-An Overview”,International Journal of Computer
Mining System is work to inquire about points and their Science & Communication Networks,Vol 5
slants as of understudy produced criticism. This strategy [12]. Munkova, Dasa, Munk, Michal and Mozar, Martin, “Data Pre-
Processing Evaluation for Text Mining:Transaction/Sequence
will be useful to improve student knowledge and educator's Model”, Procedia Computer Science, Vol. 18, 2017.
process for conveyance. Automating the student’s feedback [13]. B. Seerat and F.Azam “Opinion Mining: Issues and Challenges
may give several advantages together with saving price, (A survey)” International Journal of Computer Applications
time and creating economical report generation, etc. the (0975 – 8887) Volume 49– No.9, July 2016.
utilization of opining mining will facilitate in summarizing
978-1-7281-5197-7/20/$31.00 ©2020 IEEE 1163

Authorized licensed use limited to: James Cook University of Northern Queensland. Downloaded on June 02,2020 at 10:39:15 UTC from IEEE Xplore. Restrictions apply.