ANALISIS SENTIMEN TERKAIT FENOMENA TECH WINTER MELALUI MEDIA SOSIAL X MENGGUNAKAN NATURAL LANGUAGE PROCESSING

NEGARA, YUSTIAR CATUR (2025) ANALISIS SENTIMEN TERKAIT FENOMENA TECH WINTER MELALUI MEDIA SOSIAL X MENGGUNAKAN NATURAL LANGUAGE PROCESSING. S1 thesis, Universitas Mercu Buana Jakarta.

[img]
Preview
Text (HAL COVER)
01 COVER.pdf

Download (510kB) | Preview
[img] Text (BAB I)
02 BAB 1.pdf
Restricted to Registered users only

Download (105kB)
[img] Text (BAB II)
03 BAB 2.pdf
Restricted to Registered users only

Download (257kB)
[img] Text (BAB III)
04 BAB 3.pdf
Restricted to Registered users only

Download (133kB)
[img] Text (BAB IV)
05 BAB 4.pdf
Restricted to Registered users only

Download (349kB)
[img] Text (BAB V)
06 BAB 5.pdf
Restricted to Registered users only

Download (28kB)
[img] Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf
Restricted to Registered users only

Download (97kB)
[img] Text (LAMPIRAN)
08 LAMPIRAN.pdf
Restricted to Registered users only

Download (809kB)

Abstract

The tech winter phenomenon is a situation where many technology-based startups face financial problems that can cause them to go bankrupt. This is characterized by a decrease in the number of jobs, a halt in recruitment, and a decrease in technology investment. In Indonesia, many large companies such as Tokopedia, Gojek, and Traveloka have been affected by this phenomenon. Social media X has grown into one of the main platforms where people can express their opinions about this phenomenon. Therefore, this study aims to conduct a sentiment analysis of the tech winter phenomenon using the K-Nearest Neighbor (KNN) algorithm and natural language processing (NLP) techniques. The data used consists of 2,101 text data that have gone through a preprocessing stage and are grouped into three categories: positive, neutral, and negative. The TF-IDF method displays text features, while GridSearchCV with five-step cross validation is used to find the best parameters. A data sharing scheme of 20% for testing and 80% for training is used to test the KNN model. The evaluation results show that the model works well with a value of 55.11%, an accuracy of 55.41%, a recall of 55.11%, and an f1- score of 53.68% at the best k value = 20. The distribution of sentiment also shows that public perception of tech winter tends to be positive or neutral, with negative sentiment being in a smaller proportion. These findings provide an overview of public response to the tech winter phenomenon and provide a basis for the development of more accurate classification methods on text data in the future. Kata kunci: Tech winter, sentiment analysis, social media X, NLP, TF-IDF, VADER, KNN. Fenomena musim dingin teknologi atau tech winter adalah situasi di mana banyak perusahaan rintisan berbasis teknologi menghadapi masalah keuangan yang dapat menyebabkan mereka gulung tikar. Ini ditandai dengan penurunan jumlah pekerjaan, penghentian rekrutmen, dan penurunan investasi teknologi. Di Indonesia, banyak perusahaan besar seperti Tokopedia, Gojek, dan Traveloka terkena dampak fenomena ini. Media sosial X telah berkembang menjadi salah satu platform utama di mana masyarakat dapat menyampaikan pendapat mereka tentang fenomena ini. Oleh karena itu, penelitian ini bertujuan untuk melakukan analisis sentimen terhadap fenomena musim dingin teknologi dengan menggunakan algoritma K-Nearest Neighbor (KNN) dan teknik pemrosesan bahasa natural (NLP). Data yang digunakan terdiri dari 2.101 data teks yang telah melalui tahap preprocessing dan dikategorikan ke dalam tiga kategori: positif, netral, dan negatif. Metode TF-IDF menampilkan fitur teks, sedangkan GridSearchCV dengan crossvalidation lima langkah digunakan untuk menemukan parameter terbaik. Skema pembagian data 20% untuk pengujian dan 80% untuk pelatihan digunakan untuk menguji model KNN. Hasil evaluasi menunjukkan bahwa model bekerja dengan baik dengan nilai akurasi 55,11%, presisi 55,41%, recall 55,11%, dan skor f1- 53,68% pada nilai k terbaik = 20. Distribusi sentimen juga menunjukkan bahwa persepsi publik terhadap tech winter cenderung positif atau netral, dengan sentimen negatif berada dalam proporsi lebih kecil. Temuan ini memberikan gambaran umum tentang respons masyarakat terhadap fenomena tech winter serta memberikan dasar untuk pengembangan metode klasifikasi yang lebih akurat pada data teks di masa mendatang. Kata kunci: Tech winter, analisis sentimen, media sosial X, NLP, TF-IDF, VADER, KNN.

Item Type: Thesis (S1)
Call Number CD: FIK/INFO. 25 142
NIM/NIDN Creators: 41521010049
Uncontrolled Keywords: Tech winter, analisis sentimen, media sosial X, NLP, TF-IDF, VADER, KNN.
Subjects: 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 004 Data Processing, Computer Science/Pemrosesan Data, Ilmu Komputer, Teknik Informatika
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.31 Machine Learning/Pembelajaran Mesin
000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.7 Multimedia Systems/Sistem-sistem Multimedia > 006.75 Social Multimedia/Multimedia Social > 006.754 Online Social Network/Situs Jejaring Sosial, Sosial Media
300 Social Science/Ilmu-ilmu Sosial > 330 Economics/Ilmu Ekonomi > 332 Financial Economics, Finance/Ekonomi Keuangan dan Finansial, Ekonomi Biaya dan Pembiayaan > 332.6 Investment/Investasi
600 Technology/Teknologi > 600. Technology/Teknologi
Divisions: Fakultas Ilmu Komputer > Informatika
Depositing User: khalimah
Date Deposited: 11 Aug 2025 04:18
Last Modified: 11 Aug 2025 04:18
URI: http://repository.mercubuana.ac.id/id/eprint/96750

Actions (login required)

View Item View Item