CD Skripsi

Topic Modelling Skripsi Prodi Sistem Informasi Fmipa Universitas Riau Menggunakan Algoritma Latent Dirichlet Allocation (LDA)

---

Information systems can be defined as a combination of various integrated information technology elements that work harmoniously to collect, process, store, and distribute information. The information produced by these systems supports communication, decision-making, and coordination within an organization or group. This research aims to understand the implementation process of topic modeling using Latent Dirichlet Allocation (LDA) on thesis titles from the Information Systems Study Program at the Faculty of Mathematics and Natural Sciences, University of Riau. The methodology includes data collection, preprocessing, word weighting, model building, model evaluation, and result analysis. The preprocessing phase consists of five stages: text cleaning, tokenization, normalization, stopword removal, and stemming. The LDA model is then applied to identify frequently occurring topics in the thesis data. The research results show that the application of topic modeling using the LDA algorithm was successful, achieving a coherence score of 0.0364 at 150 iterations with 4 topics: Topic 1 contained 61 entries related to information management, Topic 2 contained
45 entries on business intelligence, Topic 3 contained 105 entries on data engineering, and Topic 4 contained 7 entries on information retrieval, totaling 218 entries. The most frequent topic was Topic 3, which focused on data engineering.

Keywords : Text Analysis, Thesis Titles , Latent Dirichlet Allocation (LDA), Information Systems Study Program, Topic modeling

---

Ketersediaan

Informasi Detail

Judul Seri

-

No. Panggil

2003125716

Penerbit

Pekanbaru : Universitas Riau FMIPA Sistem Informasi., 2024

Deskripsi Fisik

-

Bahasa

Indonesia

ISBN/ISSN

-

Klasifikasi

2003125716

Tipe Isi

-

Tipe Media

-

Tipe Pembawa

-

Edisi

-

Subjek

SISTEM INFORMASI

Info Detail Spesifik

-

Pernyataan Tanggungjawab

Mutia

Versi lain/terkait

Lampiran Berkas

Komentar

---

Anda harus masuk sebelum memberikan komentar