Page 140 - Conference Book The 3rd IConVET "Future of TVET Graduates: Developing Talent for Industry 4.0 and The New Normal"

The 3 International Conference
rd
on Vocational Education and Technology (IConVET)
th
Universitas Pendidikan Ganesha - Bali | 7 November, 2020
PERFORMANCE ANALYSIS OF SUPPORT VECTOR
MACHINES WITH POLYNOMIAL KERNEL FOR
SENTIMENT POLARITY IDENTIFICATION: A CASE
STUDY IN LECTURER PERFORMANCE
QUESTIONNAIRE

Gede Aditra Pradnyana , I Gede Mahendra Darmawiguna , Dewa Ketut
1
2
4
Satriawan Suditresna Jaya , Ade Sasmita
3
1,2,3,4 Department of Informatics, Universitas Pendidikan Ganesha, Bali -
Indonesia

E-mail: gede.aditra@undiksha.ac.id
Abstract. The lecturer performance evaluation process can be carried out
using an open questionnaire that is filled out by students at the end of the
semester. In this questionnaire, students can provide an assessment in the
form of comments, suggestions, and criticism of the lecturer's performance
which in turn can describe the level of student satisfaction with the lecture
process. Conducting assessments or analyzes one by one on the open
questionnaire entries manually will certainly have an impact on high costs,
such as time and energy. Sentiment polarity identification is a process in
sentiment analysis that classifies text into a sentence or document and then
determines whether the opinion expressed is positive, negative or neutral. In
this research, a sentiment polarity detection system will be developed in a
lecturer evaluation questionnaire using the Support Vector Machine (SVM)
method with a polynomial kernel. The test results show that the performance
of the SVM method with the Polynomial kernel is strongly influenced by the
value of the learning rate parameter, the maximum iteration, and the degree,
with the optimal parameter values, respectively, 0.001, 200, and 0.3. The use
obtained an accuracy value of 84.88%.
of optimal parameter values in the process of identifying sentiment polarity

| IConVET 2020 | 140

https://conference.undiksha.ac.id/iconvet/ | 140 |