Skripsi

PEMODELAN TOPIK PADA TWEET BAHASA INDONESIA MENGGUNAKAN BERTOPIC

---

Penilaian

---

The increasing use of information and communication technology in recent years has had a significant impact on the trend of communicating and expressing aspirations through social media, especially the Twitter platform. Every tweet on Twitter carries information about a particular topic that can be identified through the Topic Modeling method. Topic Modeling is a tool used to uncover hidden topics in a group of documents. This research aims to perform topic modeling on Indonesian tweets using BERTopic. The Topic Modeling process using BERTopic includes steps such as document embedding, dimension reduction with UMAP, document clustering using HDBSCAN, and representing topics using c-TF-IDF. The dataset used consists of 10,000 Indonesian tweets taken from the Twitter account @detikcom. From the 10,000 tweets, 119 main topics and 1 outlier topic were found. Topic Modeling Evaluation is done using coherence score cv, with the average coherence score cv of 0.685, the highest coherence score cv of 0.995, and the lowest coherence score cv of 0.119

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2307004697	T127188	T1271882023	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1271882023

Publisher

Indralaya : Jurusan Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2023

Collation

xiii, 54 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Aplikasi
Jurusan Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

FIRA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment