IRJET - Analysis of Student Feedback on Faculty Teaching using Sentiment Analysis and NLP Techniques

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 07 Issue: 04 | Apr 2020 www.irjet.net p-ISSN: 2395-0072
© 2020, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 1359
Analysis of Student Feedback on Faculty Teaching Using Sentiment
Analysis and NLP Techniques
M. Ravi Varma1, R. Venkatesh2, S.V. Pavan3, P. Sai Teja4
Students [1][2][3][4], Dept. of Computer Science Engineering, ANITS, Andhra Pradesh, India
---------------------------------------------------------------------***----------------------------------------------------------------------
Abstract - In education system, student’s feedback is very
important to live the teaching traditional. Students feedback
area unit usually analyzed victimization lexicon primarily
based approach to spot the scholars positiveor negativeangle.
The foremost objective of this analysis is to analysis the
student’s feedback and acquire the opinion. In most of the
prevailing teaching analysis system, the qualifier words and
blind negation words aren't thought of. The extent of opinion
result isn’t displayed-whether positive or negative opinion. To
traumatize this downside, we've got a bent to propose to
analysis thescholarstextfeedbackautomatically victimization
lexicon-based approach to predict the extent of teaching
performance. To extend the accuracy of the sentiment price,
the comments undergone polarity identification, negation
tagging, and intensity multiplication, taking into thought the
terms close a given word.
Key Words: Sentiment analysis,lexiconbased,dictionary
based, corpus based, qualitative information,
quantitative information.
I. INTRODUCTION
Sentiment analysis is additionally a way for tracing the
ambiance of the people concerning any specific topic by
reviews. Generally, opinion is additionally the results of
people’s personal feelings, beliefs, opinions, sentiments and
desires etc. This analysis work concentrates on student’s
comments and Analysing student’s comments pattern
sentiment analysis approaches and will classify the scholars
positive or negative feeling. Student’s feedback canhighlight
varied issues that students might have with a lecture.
Typically, students don't understand what the lecturer is
creating a shot to elucidate, therefore byprovidingfeedback,
student’s candidate this to thelecturer. TheInputwe'vegota
bent to require is qualitative info insteadof quantitativeinfo.
The method of qualitative info analysis is awfully necessary
and it'll enhance the teacher analysis effectiveness.
The taking of feedback plays a awfully vital role within the
lifetime of students additionally because the academics.The
scholars offer the feedback therefore to convey what's the
distinction between the particular teaching that is presently
going down in schools and what variety of teachingstudents
very want for. These feedbacks show the school theiroverall
performance in their specific subjects. They’ll improve their
teaching consequently then school analysis is that the
method of gathering and process knowledge to live the
effectiveness of teaching. There square measure totally
different areas to be thought of for evaluating a college like
teaching, advising and analysis and critical activities. The
foremost necessary advantage of this analysis is that the
feedback the forms offer on to instructors, so they'll refine
the courses and teaching practices to produce students with
higher learning experiences.
This analysis shows the utilization of sentiment analysis to
gauge the student’s narrative commentwithintheanalysis of
their various school. Theremainderofthepaperisorganized
as follows: Section 2 presents a review of literature;planned
methodology is conferred in Section 3; Section 4 describes
the development of sentimentwordinformationforteaching
analysis. Section 5 presents the design of our planned
system. Section 6 presents the case study and results of the
teaching evaluation;andtherefore,thefinal chapterpresents
the conclusion.
II. RELATED WORKS
The following are the variety of the work’s on Student
feedback using sentiment Analysis.
• Tanvi Hardeniya and Dilipkumar A.Borikar[8]in2016self-
addressed the Dictionary- Based strategy to Sentiment
analysis. They reviewed on sentiment analysis is completed
and so the challenges and problems concerned inside the
method are mentioned. The approaches to sentiment
analysis mistreatment dictionaries like SenticNet,SentiFul,
SentiWordNet, and WordNet are studied. Lexicon-based
approaches are economical over a website of study. Though
a generalized lexicon like WordNet might even be used, the
accuracy of the classifier gets affected due to problems like
negation, synonyms, sarcasm,etc.Thishasprovidedimpetus
to substantial growth of online buying creating opinion
analysis a very important issue for business development.
• Another Approach was developed by Bhagyashree Gore
supported Lexicon based mostly Sentiment Analysis of
Parent Feedback to gauge their Satisfaction Level [10] in
2018.They used lexicon based mostly approach and
computing of polarity values. Throughoutthisapproachthey
produce a lexicon of words with opinion score assigned to
that.
• R Mehana from Dr.Mahalingam school of Engineering and
Technology Pollachi, Tamlinadu,India[6]developedStudent
feedback mining system adopting sentiment analysis in
2017.They projected a system to mine the feedback given by
the students and acquire information from that and gift that
info in qualitative method. They have known the frequency
of each word and extract the topic that has the perfect

frequency count. Similar comments in every topic are
clustered then the clustered words are classified into
positive or negative comments.
• S. MacKim and R. A. Calvo projected Sentiment analysis in
student experiences of learning [7] in 2016.they Classify the
text supported the presence of unambiguous have an effect
on words. In their approach, a bit set of opinion words is
collected manually as a seed. They have a sentiment lexicon
contains a listing of words aboard their individual polarity.
Many like corpora are developedandthattheycreatedfreely
out there.
• Other interesting approach of Sentiment Analysis was
presented in the work of M. A. Ullah [5] wherein they extract
sentiments with polarities of positive and negative for
specific subjects from a document, instead of classifying if
the document is positive or negative. In this paper, they
applied semantic analysis with a syntactic parser and
semantic lexicon which gave them a highprecisionof75% to
95% in finding the sentiments within web pages and news
articles.
III. METHODS IN SENTIMENT ANALYSIS
There are two main approaches for lexicon based in
Sentiment analysis:
A. Corpus based Approach
Using the corpus-based approach alone to identify all
opinion words, however, it is not as effective as a result of
the results of the lexicon-Based approach as a result of it's
arduous to rearrange an outsized corpus to cover all English
words. However, it's going to facilitate to hunt out domain
and context specific opinion words using an online website
corpus that is that the big advantage of this methodology.
The corpus-based approach is performed in arithmetic
approach or linguistics approach.
B. Dictionary based Approach
One amongst the simple techniques throughout this
approach is supported bootstrapping pattern slightly set of
seed opinion words and a web reference, e.g., WordNet. The
strategy is to initial collect slightly set of opinion words
manually with celebrated orientations then to grow this set
by making an attempt inside the WordNet for his or her
synonyms and antonyms. The modern found words unit of
activity supplementary to the seed list. ulterior iteration
starts. The repetitious technique stops once no additional
new words unit of activity found. Once the manoeuvre
completes, manual examination unit of activity usually
administered to urge obviate and/or correct errors.
During this approach, opinion words unit of activity divided
in an exceedingly combine of classes. Positiveopinion words
unit of activity accustomed categorical some necessary
things, and negative opinion words unit of activity
accustomed describesurplus things.themethodstartedwith
the pre-processing of the input texts were the comments for
the school, that were composed of 1 or several sentences
connected to a precise person, specifically a academic. For
this project, the comments were assumed to be correct in
terms of writing system and synchronic linguistics.
IV. SENTIMENT WORD DATABASECONSTRUCTION
Throughout this paper we have a tendency to learned
transient description regarding the strategies thatwehavea
tendency to adopted to extract the key words from the
student’s feedback document. They are:
1. Tokenization
Tokenization is that the act of ending a sequence of strings
into things like words, keywords, phrases, symbols and
totally different elements named as tokens. Tokens will be
individual words, phrases or perhaps whole sentences.
Within the strategy of tokenization, some characters like
punctuation marks square measure discarded.
2. Stop word removal
Stop words square measure words that square measure
filtered out before or once method of tongue info. These
words square measure removedtoextractonlythepregnant
information. The list of stop words may even be ' the, is, at,
which, on, who, where, how, hi, before, when’ etc.
Fig 4.1: Diagram of proposed System
We projected a system to mine the feedback given by the
scholars and procure data from that and gift that info in
qualitative approach. Feedback was collected for a course;
those feedback were pre-processed victimization text
process techniques. In preprocessing, the feedback files
square measure generated as a file. The file is tokenized into
sentences and also the keywords square measure listed
when removing the stop words. we've known the frequency
of every word and extract the subject that has the best
frequency count. Similar comments in every topic square
measure clustered then the clusteredwordssquaremeasure
classified into positive or negative comments. The classified
comments square measure generated as a chart for
straightforward visualization. This method of planned
system started with the pre-processing of the input texts
were the comments for the school, that were composed of 1
or several sentences connected to a precise person,
specifically a academic. For this project, the comments were
assumed to be correct in terms of writing system and
synchronic linguistics.

3. Classification of information
Classification is that the strategy of organizing info into
categories for its best and economical use. A well-planned
info arrangement makes essential info straightforward to
hunt out and retrieve. This will be of specific importance for
risk management, legal discovery, and compliance.
Faculty matter Comments exploitation Lexicon based
Approach throughout this paper we've got a bent to learned
concerning varied lexicons that unit won’t to urge the
opinion of student analysis. The lexiconbased approach
depends on opinion (or sentiment) words, that unit words
that express positive or negative sentiments. Choosing the
sentiment lexicon to just accept is extraordinarily necessary.
The following section describes some common sentiment
lexicon.
Liu Lexicon: Liu lexicon consist to facet of around 6800
English words classified into positive and negative opinion
teams. Liuet al used the adjective word and opposite set sin
WordNet to predict linguistics orientation of adjectives.
Firstly, as mallist of seed adjective staged with either
positive or negative labels is seventeen manually created.
This seed adjective list is actually domain freelance. As an
example, great, fantastic, smart square measure positive
adjectives; and unhealthy, boring square measure negative
adjectives. The list is then enlarged exploitation Word web,
leading to an inventory of 4783 negative terms and 2006
positive terms as well as misspellings, morphological
variants, slang, and social-media mark-up that square
measure helpful for social network informationanalysis.But
Liu lexicon cannot cowl all of planet issues in terms of
sentiment analysis for education a domain.
Afinn Lexicon: Afinn lexicon was initially came across in
2009 for tweets downloaded foronlinesentimentanalysisin
connectedness the United Nation Climate Conference
(COP15). The previousversiontermedAFINN-96distributed
on the online has 1468 whole completely different words,
likewise as several phrases. The foremost recent version,
AFINN-111 contains 2477 distinctive words and fifteen
phrases. AFINN uses a rating vary from−5(very negative) to
+5 (very positive). For straightforward labeling the author
only scored for valence, leaving out, e.g., judgement
/objectivity, arousa land dominance. Thewordswerescored
manually by the author. The synonym finderinAfinnlexicon
initiated from a set of obscene words. Most of the positive
words were tagged with +2 and most of the negative words
with –2, strong obscene words with either four or –5.
Sentiment word information contains immense quantity of
words. It consists many intensive words, positive words,
negative words and conjointly neutral words.Thesentiment
score ranges from -1 to +1. Once the score is one then it may
be thought of as positive; whereas once score shows -1, it is
aforesaid to be negative word. Once the sentiment score
equals to zero (0), it's thought of as neutral class. Some
example words are shown in below Table 4.1.1.
Table 4.11: Sample words in sentiment word database.
Using the sentiment word database, the sentences are
processed as below:
1. Text extraction:
The comments, that consists of few sentences unit of
measuring go alternativeroutes intoclausesupportedclause
level mark. The clause level punctuation is any word from
regular expression ^[.,:;!?]$ .
2. Text cleaning:
This is to urge eliminate special characters and switch the
majuscule letters into minuscule ones. The is employed to
urge eliminate special characters and alter majuscule into
minuscule letters.
3. Stemming:
Stemming might even be a heuristic techniqueforcollapsing
distinct word forms by making an attempt to urge eliminate
affixes. Noun square measurein eithersingularordescriptor
exploitation either –es or –s suffix. Similarly, verb square
measure in either gift or verb kind exploitation –ing and –ed
severally. Adjectives square measure in comparative kind
exploitation -er suffix or superlative kind exploitation –est
suffix. very cheap kind is then used for wanting up the word
in lexicon.

4. Negation Marking:
Negators unit of measuring words and phrases that switch
sentiment orientation of different words at intervals
constant sentence. The negation marking technique of
defender Potts is applied. This methodologyappendsa _NEG
suffix to each word standing betweena negatoranda clause-
level mark.
For example, given the text “It isn't delicious: it's TOO
spicy!!!”. The content once applying the pre- process
technique is “it isn't delicious _NEG it's too spicy”.
5. Parts of speech:
POS Tagger is employed to assign a part of speech to every
word at intervals the text (and completely different tokens),
like noun, verb, adjective, etc.
V. SYSTEM ARCHITECTURE
In this paper, we have a tendency to followed the below
design System to research topics and their sentiments from
the coed generated feedback. We have a tendency to
tokenized the feedbacks into sentences. Topics were
extracted from the feedback document. The subsequent
design shows however the comments are extracted and got
scored.
Fig. 5.1: The Architecture model of sentiment analysis
The first a part of the pre-processing module is that the
sentence splitter. It’s the method wherever the comment
was broken down into smaller components, specifically in
sentence level below the method. Afterwards, these
sentences dampened from the sentence splitter were
additional dampened into words
Then the words are labelled in their individual a part of
speech. Within the opinion word identification. The words
that unit used for opinion analysing unit categorizes into
following:
Negation words:
The negation words unit the words that reverse the polarity
of sentiment, high-power sensible(+2)intonotsensible(-2).
(e.g. no, not, neither, nor, nothing, never, none) unit very
important in characteristic the emotions, as their presence
can reverse the polarity of the sentence.
Blind negation words:
Words like would love, needed, require,neededetc.,arevery
important in characteristic the emotions. as Associate in
Nursing example:
‘Her teaching method needed to be better’, ‘better’ depicts a
positive sentiment but the inclusion of the blind negation
word ‘needed’ suggests that this Sentence is depicting
negative sentiment. Within the projected approach
whenever a blind negation word happens in a {very} very
sentence its polarity is instantly labelled as negative and
allotted the opinion score to (-2).
Adjective, adverb, verb, noun words:
Most of the opinion words unit adjective.asanexample:‘She
is knowledgeable. Her discussions unit fascinating. I
understand her teaching’. throughout this sentence
‘knowledgeable’ and ‘interesting’ unit positive adjective
opinion words, ‘understand’ can be a positive verb opinion.
Intensifier words:
They're classified into two major categories, depending on
their polarity. Amplifiers (e.g., very) increase the linguistics
intensity of an in-depth lexical item, whereas down toners
(e.g., slightly) decrease it. For example, “Her clarification is
de facto very good”. Throughout this sentence ‘really and
very’ unit intensifiers that increase the positive sentiment
polarity.
Next, the polarity of the words in every sentence were
summed up, and divided by the overall range of subjective
words. Then, it had been classified as powerfully Positive,
Positive, Negative or powerfully Negative. Then, the
polarities of all the sentences were averaged. When the
averaging, the ultimate output was classified supported 3
classifications: Positive, Neutral or Negative.
During this paper, we have a tendency to use Text Blob that
could be a python library and offers an easy API to access its
strategies and perform basic information processing tasks.
Since, it's engineered on the shoulders of NLTK and Pattern,
thus creating it easy by providing Associate in Nursing
intuitive interface to NLTK. Here, the sentiment property
returns a named section of the shape Sentiment (polarity,
subjectivity) it very depends onwhattypeoftextanalysis we
wish to perform and what information feels like.TextBlob is
less complicated to use if we're simply obtaining started

with information processing primarilybecauseof2 reasons-
it's an honest interface and a superb documentation.
In this way, the opinion result will be showed.
VI. CASE STUDY AND RESULTS
In this system, there are basically three different modules
which are as following:
ØAdmin Module
ØStudent Module
ØFaculty Module
Firstly, there’s admin module which has admin login portal.
The username and password of admin is initially fixed. After
login, Admin views the students as well as faculty accounts
and can modify their details. The whole data is stored in the
database. The admin also adds the students and faculty
details in the database. The admin also can delete the
student’s as well as the faculty data. The admin can view all
the feedbacks results present in the database.Theidentityof
the student who gave the feedback is given by the admin.
Then there’s student module that has student login portal.
Every and each valid student has their distinctive username
and password that is given by admin. The username and
password once entered are checked with data in database.
When login, the coed will read the subject’s feedback that
he/she needs to submit. Theninthefeedback form,thename
of the faculty automatically comes who teaches that
particular subject. Within the feedback from, there are
multiple fields that student should show his opinion. The
fields are Vocabulary and visual communication, Audibility,
clarification, Subject Command etc., when the submission of
feedback the answers of all the queries areanalyzedandalso
the result's hold on in information.
ESM VBL DCI ISC
Everythi
ng is
good
Voice
is so
fast
Friendly
interaction
Intime
syllabus
was
completed
Good Bad Bad Good
I am not
satisfied
with the
explanati
on
good Doubts are
clarified
even
outside
the
classroom
All topics
covered in
time
Good Very
good
Very good Very good
Good Good Good Good
Good Good Good Good
Table 6.1.1: Student Feedback table
Where
ESM: - Explanation and subject Command VBL: -Voice
and visual communication DCI: -Doubt clearance and
Interaction
If the coed has already given the feedback of that specific
teacher, then he/she can’t provide the feedback once more.
Then eventually there’sfacultymodulethathasteacherlogin
portal. Every and each school has their distinctiveusername
and password that is given by the admin. The username and
password once entered are checked with data in database.
The faculty will read their overall performance in keeping
with the student’s feedback. And student’s identity isn't
unconcealed to the faculty.
There will be a graphical illustration of student'sfeedback in
order that faculty will clearly perceive his/her strengths.
Next, the polarity of the words in each sentence were
calculated. The polarity scores are assigned as given below:
If there's only 1 opinion wordinanexceedinglysentence, the
corresponding positive scores or negative scores area unit
allotted mistreatment Ws=Os
If one modifier word and one opinion word area unit found
along,
Ws=(100%+Sinf) * Os
If 2 modifier words and one opinion word area unit found in
an exceedinglysentenceWs=(100%+Sinf)*(100%+Sinf)*
Os
If a negation word ahead of the opinion word is found in an
exceedingly sentence Ws=Ws*(-1).
Where
‘Ws’ is that the linguistics orientation score of mixing words.
‘Sinf’ is that the qualifier worth of word supported 100
percent.
‘Os’ is that the score of opinion word from sentiment word
info.
Student Feedback Table:
Let us consider there are 6 students. They have to give
feedback to one of their faculty.
Following table represents the feedback form for one
faculty(say):
Subject: OST lab
Faculty: S.Joshua Johnson Class&Section:3&C Academic
year:2018-2019
ISC: Intime Syllabus Coverage

Graphical Representation of student feedback on
faculty teaching:
Fig. 6.1: Feedback result of Faculty in Graphical Notation
VII. CONCLUSION AND FUTURE SCOPE
This project is designed in order to reduce burden of
maintaining bulk of records of all student’s feedback details.
This system uses preprocessing, topic extraction, clustering,
classification to represent the student views in a graphical
way. This system will be useful to improve the students
learning and instructor’s methods of delivery. The Opinion
Mining and in language process community, Sentiment
Analysis become a most fascinating analysis space. A lot of
innovative and effective techniques required to be fancied
that ought to overcome these challenges faced by Sentiment
Analysis.
REFERENCES
[1] A. El-Halees, “Mining opinions in user- generated
contents to improve course evaluation,” Software
Engineering and Computer Systems, pp. 107-115, 2011.
[2] Student Feedback Mining System Using Sentiment
Analysis Prabu Palanisamy, Vineet Yadav
and Harsha Elchuri “Simple and Practical lexiconbased
approach to Sentiment Analysis”, pp.october- 2017.
[3] K.P.Mohanan, the place of student feedback in teaching
evaluation
http://www.cdtl.nus.edu.sg/publications/studfeedback
/StudFeedback_Teach Quality. pdf.
[4] Khin Zezawar Aung,"Analysing Sentiment in Student-
Teacher Textual Comments Using LexiconBasedApproach".
pp. 29-06,2017.
[5] M. A. Ullah,” Sentiment analysis of students feedback: a
study towards optimal tools”, International Workshop on
Computational Intelligence (IWCI), pp. 17-10, 2016.
[6] R Mehana,"Student feedback mining system adopting
sentiment analysis",
https://ijcat.com/archives/volume6/issue1/ij
catr06011009.pdf.
[7] S. MacKim and R. A. Calvo, “Sentiment analysis instudent
experiences of learning,” in Proceedings of the 3rd
International Conference on Educational Data Mining (EDM
'10), pp. 111– 120, Pittsburgh, Pa, USA, June 2010.
[8] Tanvi Hardeniya, Dilipkumar A.Borikar “ Dictionary-
Based approach to Sentiment analysis”,pp.may,2016.
[9] Z Nasim, Q Rajput, S Haider. “Sentiment Analysis of
Student Feedback Using Machine Learning and Lexicon
Based Approaches” , pp.1-6, 2017.
[10] Bhagyashree Gore “Sentiment Analysis of Parent
Feedback” to gauge their Satisfaction Level,pp.march,2018.

IRJET - Analysis of Student Feedback on Faculty Teaching using Sentiment Analysis and NLP Techniques

More Related Content

What's hot (18)

Similar to IRJET - Analysis of Student Feedback on Faculty Teaching using Sentiment Analysis and NLP Techniques (20)

More from IRJET Journal (20)

Recently uploaded (20)

IRJET - Analysis of Student Feedback on Faculty Teaching using Sentiment Analysis and NLP Techniques