Skripsi

PERBANDINGAN TF-IDF DAN WORD2VEC UNTUK ANALISIS SENTIMEN MENGGUNAKAN SUPPORT VECTOR MACHINE.

---

Sentiment analysis is a branch of Natural Language Processing (NLP) used to determine public opinions on specific topics as positive, negative, or neutral. This study aims to compare the performance of two feature extraction methods across three scenarios: TF-IDF, Word2Vec-CBOW, and Word2Vec-skipgram. The dataset utilized consists of comments from the Instagram platform @magangmerdeka regarding MSIB 7. The model was developed using the Support Vector Machine (SVM) algorithm with a linear kernel, and the data was split into training, validation, and test sets in an 80:10:10 ratio. Evaluation was conducted using a confusion matrix and evaluation metrics. The results show that the TF-IDF feature extraction method achieved the highest accuracy of 80.63%, compared to the Word2Vec methods, CBOW and skipgram, which achieved 69.38% and 71.88%.

---

Availability

Detail Information

Series Title

-

Call Number

T1627812024

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xvi, 66 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.507

Content Type

Text

Media Type

unmediated

Carrier Type

other (computer)

Edition

-

Subject(s)

Game Komputer
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MURZ

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment