ANALYSIS OF PERSONALITY ASPECT CLASSIFICATION FROM THE RECRUITMENT INTERVIEW TEST WITH LDA TOPIC MODELING

Mulyono, Evander Reinhart (2020) ANALYSIS OF PERSONALITY ASPECT CLASSIFICATION FROM THE RECRUITMENT INTERVIEW TEST WITH LDA TOPIC MODELING. Other thesis, UNIKA SOEGIJAPRANATA SEMARANG.

[img] Text (COVER)
16.K1.0007 EVANDER REINHART MULYONO_COVER_a.pdf

Download (927kB)
[img] Text (BAB I)
16.K1.0007 EVANDER REINHART MULYONO_BAB I_a.pdf

Download (365kB)
[img] Text (BAB II)
16.K1.0007 EVANDER REINHART MULYONO_BAB II_a.pdf
Restricted to Registered users only

Download (364kB)
[img] Text (BAB III)
16.K1.0007 EVANDER REINHART MULYONO_BAB III_a.pdf

Download (359kB)
[img] Text (BAB IV)
16.K1.0007 EVANDER REINHART MULYONO_BAB IV_a.pdf

Download (1MB)
[img] Text (BAB V)
16.K1.0007 EVANDER REINHART MULYONO_BAB V_a.pdf

Download (623kB)
[img] Text (BAB VI)
16.K1.0007 EVANDER REINHART MULYONO_BAB VI_a.pdf

Download (356kB)
[img] Text (DAFTAR PUSTAKA)
16.K1.0007 EVANDER REINHART MULYONO_DAPUS_a.pdf

Download (365kB)
[img] Text (LAMPIRAN)
16.K1.0007 EVANDER REINHART MULYONO_LAMPIRAN_a.pdf

Download (455kB)

Abstract

The development of data processing and data storage techniques in this modern era has been growing rapidly. The size of data collected nowadays are very large and from these large scaled data we can get useful information. This information can be used for several things especially can be used for determining aspects of a person’s personality from a recruitment interview. From the results, we can store those data and study it and we can get the patterns then those patterns will help classifying person’s personality aspect from the Motivation, Work Enthusiasm, and Self-awareness. To help classifying, LDA algorithm is used. But not the original version of LDA but the supervised variant of the LDA (L-LDA). There are two approaches that will be used and compared. The first one views that a text consists of common words and the second one views that a document does not consist of common words. From these approaches, will be compared and analyze which approach is more effective and better. The result summaries that the second approach is more effective because the first approach depends on the training data used. If the dataset has varied words, it will be difficult to detect words that are common.

Item Type: Thesis (Other)
Subjects: 000 Computer Science, Information and General Works > 004 Data processing & computer science
Divisions: Faculty of Computer Science > Department of Informatics Engineering
Depositing User: Ms Agustin Hesti Pertiwi
Date Deposited: 23 Jun 2020 04:17
Last Modified: 23 Sep 2020 02:09
URI: http://repository.unika.ac.id/id/eprint/21434

Actions (login required)

View Item View Item