Analyzing Pangasinan State University Student’s Faculty Teaching

Performance Rating using Text Mining Technique

BOBBY F. ROARING, FREDERICK F. PATACSIL, JENNIFER M. PARRONE

College of Computing, Pangasinan State University

San Vicente, Urdaneta City

PHILIPPINES

used by the students to describe the performance of the faculty members. The results revealed that if a faculty

members was evaluated and rated 4 and 5 the descriptions are positive observations / comments from the

student respondents. The results reveal not only the quantitative values of faculty evaluation it also exposed the

qualitative description of the students in the performance of their faculty members. This study brings out

significant aspects of the teaching performance of the faculty members of Pangasinan State University. The

results can be used for coaching and mentoring by university and campus heads to their faculty members in

terms of their weaknesses. Moreover, the results can be utilized by Pangasinan State University to evaluate the

teaching performance of their faculty members based on the comments or opinions of the students.

Key-Words: - Faculty Performance Rating, Text Analytics, Teaching Performance, Faculty Evaluation, Word

Performance evaluation in higher education systems

is a significant aspect to improve the quality of

teaching – learning process and achieve excellence.

For most educational institutions, assessing faculty

teaching performance is a prerequisite to ensure an

effective student learning. However, institutions

continue to struggle with determining how effective

these assessments are and how they are evaluated.

Moreover, performance evaluation measurement

and standards remain to be a constraint in assessing

quantitative assessment with a define rating or

quantitative assessment which describe the

experience of the learning from the faculty under

evaluation.

University employs two forms of assessment to

evaluate faculty performance for different purposes

and is being conducted every end of a semester. It is

target areas that need work. Moreover, faculty

members utilize the results to reflect on their

teaching and curriculum and take measures to

enhance their instructional techniques and course

materials in order to provide future students with a

the result. Most HEIs resorted to digitalization of

educational services and processes which pave way

to datafication which is significant particularly in

understanding and enabling development within the

wide framework of education.

come up short of a deeper investigation of

qualitative evaluation. Most often times, the

institution only relies on the quantitative rating for

evaluation purposes, discarding the qualitative

rating, it provides a wider perspective for the

teachers in prioritizing and focusing the necessary

modifications of the course. The challenge for the

university is how to assist its faculty members in

better processing such enormous quantities of

feedback and identifying course delivery

shortcomings. As a higher education institution,

capturing and evaluating qualitative feedback data

can give important understandings of teaching

techniques and curriculum [2].

classify important and relevant information. In an

educational setting, these techniques are used to

analyze students’ behavior, performance evaluation

of teachers and the learning system, and curricula

[3]. The faculty evaluation process includes

personal and academic data for conducting

semestral performance evaluations. However, the

assessment process must be unbiased to ensure the

expected learning outcomes [4]. Hence, using DM

methods to extract hidden yet relevant knowledge

In a Philippine higher education context, faculty

The technique provide innovative solution within

faculty evaluation should be to improve the quality

of their teaching.

difficult task. Unfortunately, they are an imprecise

metric, since biases in aspects like student academic

evaluations based on classroom performance. Many

higher education institutions face many challenges

related to this, and much research has been done to

address the questions and ambiguities related to

teacher evaluation to help teachers adapt to the

result of the evaluation [13]. Despite its wide use,

several literature debate its validity and reliability

with regards to the degree in which it correctly

evaluates the teaching effectiveness or exhibits an

inclusive rating of the course or instructor [14], [15],

feedback or qualitative information, which rarely

receives much academic and developmental

attention [16].

numeric rating and textual feedback. They added a

new value to the overall faculty performance and

put a premium on student textual feedback as part of

the faculty evaluation process.

provided by the university to decipher themes such

as: The Disparity of Teaching Assignment to

Professors’ Field of Expertise, Professors’

Expression of Willingness to Help Students in

School-Related Matters, Desirable Traits Portrayed

by a Professional Teacher, Professor’s Commitment

and Dedication to Classroom Instruction, and

Enhancement of Teaching Practices to Improve

Quality of Academic Services [30].

Most of the comments gathered from the

Association rule mining finds important

discovers frequent/occurring itemsets satisfying

minimum support, and then from which generates

strong association rules satisfying minimum

confidence.

3.4 FP Growth (Frequent Pattern Growth)

FP growth is creating the frequent datasets without

FP-Tree algorithm which encodes the data set into a

tree and then extracts the frequent itemsets from this

tree. Frequent itemsets are groups of items that often

appear together in the data.

item. This fragmented part is called “pattern

fragment”. The datasets of these fragmented

patterns, then analysed. Thus, with this method, the

search for frequent datasets is reduced compared.

Fig. 2: Association rules derived from comments

dataset with faculty evaluation rating of 1

Figure 2 reveals 108 combinational rules derived

from the dataset. The word “teach” is connected

with “accept”, “wrong”, “dont”, “make”, class”,

“know”, “voice” and “loud”. The following

combinational rules suggest that the main task of

Table 2. Dominant words to describe the faculty

performance with an evaluation rating of 2

Table 2 show words/word patterns that describe a

teacher’s performance with an evaluation score of

2. Students report a faculty with a evaluation rating

of 2 as “give discuss”. “explain topic”, and “discuss

dataset, “topics” + “discuss” (0.039) or 3,900 times

In terms of changes of togetherness /

The results revealed that if a faculty members

Table 3. Dominant words to describe the faculty

performance with an evaluation rating of 3

that describe a teacher’s performance with a

evaluation score of 3. Students report a faculty with

a evaluation rating of 3 as “teach good” and

“explain topic”. The descriptions coming from the

students when a faculty is evaluated and obtained

rating as 3 were on the positive words/word

(0.045) or 4500 times that the words combined

appear in the dataset.

Fig. 4: Association rules derived from comments

dataset with a faculty evaluation rating of 3

chance of utilizing both of these words to describe

the performance of a faculty member. The words

The results revealed that if a faculty member was

evaluation score of 4. Students report a faculty with

a evaluation rating of 4 as “teach good”, “explain

topic”, “discuss topic”, “teach students”and

“understand topic”. The descriptions coming from

the students when a faculty is evaluated rating as 4

words appear in the dataset, “topics” + “explain”

(0.049) or 4900 times that the combination word

appears in the dataset, “discuss”+ “topics” 0.028 or

2800 times that the combination of word appear in

the dataset or 2800 and “understand” + “topic”

0.023 or 2300 time that the combination of word

appear in the dataset.

chance of utilizing both of these words to describe

the performance of a faculty member. The words

respectively.

were evaluated and rated as 4 sometimes they are

“good to explain and discuss topics, and students

understand the topics”. This descriptions are

respondents.

Table 5. Dominant words to describe the faculty

performance with an evaluation rating of 5

The results revealed that if a faculty members

be apply is so-called “quantitizing” of qualitative

data or is just relating qualitative to quantitative

methods. Linking quantitative results with a

qualitative analysis of open comments would

provide a more comprehensive understanding of

teaching performance strength and its weakness.

teaching performance of the faculty members of

Pangasinan State University. The results can be used

their weaknesses. Moreover, the results can be

utilized by Pangasinan State University to evaluate

the teaching performance of their faculty members

based on the comments or opinions of the students.

References: