Skripsi

ANALISIS SENTIMEN ULASAN PENGGUNA DUOLINGO MENGGUNAKAN METODE VALENCE AWARE DICTIONARY AND SENTIMENT REASONER

---

Penilaian

---

Current technological developments have made it easier to learn languages through applications such as Duolingo. This study aims to understand users' perceptions of Duolingo using VADER (Valence Aware Dictionary and Sentiment Reasoner)-based sentiment analysis. User reviews from the Google Play Store were processed using Google Collaboratory, resulting in 1,831 data points that were grouped as neutral, negative, and positive. The analysis results show an overall accuracy of 98 percent. The model is effective in identifying neutral sentiment (precision 100 percent, recall 97 percent, F1-score 99 percent) and positive sentiment (precision 99 percent, recall 82 percent, F1-score 99 percent). However, the model is less effective in detecting negative emotions, with an F1-score of 74 percent, recall of 82 percent, and precision of 67 percent, indicating misclassification of some negative emotions. The word cloud shows positive words such as “good,” “helpful,” and “fun,” as well as negative words such as “technical problems” and “learning limitations.” Challenges in using VADER include its inability to handle complex language contexts and deep emotional nuances. To improve sentiment classification, this study recommends using VADER in conjunction with Deep-Translator. This combination can help identify negative sentiments more effectively and handle data in multiple languages more efficiently. The objective of this research is to understand user perspectives and improve sentiment analysis accuracy, thereby contributing to the development of better language learning applications. Keywords : Sentiment Analysis, Deep-Translator, Duolingo, Google Collaboratory, VADER

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003876	T177518	T1775182025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1775182025

Publisher

Indralaya : Prodi Sistem Informasi, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xvi, 97 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

005.360 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem informasi

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment