Claim Missing Document
Check
Articles

Found 12 Documents
Search

Analisis Perbandingan Sentimen Ulasan Lagu Populer pada Karya Taylor Swift, Rihana, dan Adele Menggunakan Metode Natural Language Processing dan Machine Learning Haniffah Sri Rinjani; Mambang Mambang; Septyan Eka Prastya; Johan Wahyudi; Finki Dona Marleny
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 7, No 3 (2024): Juni 2024
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v7i3.7562

Abstract

Abstrak - Secara umum musik merupakan salah satu media ungkapan kesenian, dan juga mencerminkan kebudayaan masyarakat pendukungnya. Di dalam musik terkandung nilai dan norma- norma yang menjadi bagian dari proses enkulturasi budaya, baik dalam bentuk formal maupun informal. Analisis sentimen juga dapat disebut proses menggunakan teknik dan metode komputasional untuk memahami dan mengevaluasi opini, sikap, atau emosi yang terkandung dalam teks atau data lainnya. Penelitian ini dilakukan secara virtual dengan seluruh data yang diperlukan diambil dari sumber-sumber yang tersedia di internet. Data yang diambil mencakup teks-teks ulasan, penilaian (rating), dan konteks terkait. Evaluasi model dilakukan menggunakan metrik akurasi, precision, dan recall untuk masing-masing artis. Hasil evaluasi menunjukkan bahwa model BERT memiliki performa sempurna (akurasi, precision, dan recall sebesar 1.0) untuk data Taylor Swift dan Adele. Namun, untuk data Rihanna, akurasi dan recall adalah 0.5, sementara precision tetap 1.0. Rata-rata keseluruhan menunjukkan bahwa model BERT sangat baik dalam menghindari kesalahan prediksi positif, tetapi kurang sempurna dalam mendeteksi semua kasus positif. Rata-rata akurasi, precision, dan recall adalah masing-masing 0.833, 1.0, dan 0.833. Model SVM juga dievaluasi menggunakan metrik yang sama. Hasil evaluasi menunjukkan bahwa model SVM memiliki performa yang kompetitif namun sedikit berbeda dibandingkan dengan BERT. Akurasi dan precision untuk Taylor Swift dan Adele juga tinggi, tetapi recall sedikit lebih rendah dibandingkan BERT. Untuk data Rihanna, performa SVM lebih baik dalam mendeteksi kasus positif dibandingkan dengan BERT, namun precision-nya sedikit lebih rendah. Rata-rata keseluruhan menunjukkan bahwa SVM memiliki akurasi dan recall yang lebih seimbang di seluruh dataset dibandingkan BERT.Kata kunci: Sentimen, Ulasan Lagu, NLP, Machine Learning, SVM Abstract - In general, music is one of the media for artistic expression, and also reflects the culture of the supporting community. Music contains values and norms that are part of the process of cultural enculturation, both in formal and informal forms. Sentiment analysis can also be called the process of using computational techniques and methods to understand and evaluate opinions, attitudes, or emotions contained in text or other data. This research was conducted virtually with all the necessary data taken from sources available on the internet. The data captured includes review texts, ratings, and related context. Model evaluation was performed using accuracy, precision, and recall metrics for each artist. The evaluation results show that the BERT model has excellent performance (accuracy, precision, and recall of 1.0) for Taylor Swift and Adele data. However, for Rihanna's data, accuracy and recall are 0.5, while precision remains 1.0. The overall average shows that the BERT model is very good at avoiding false positive predictions, but less than perfect at detecting all positive cases. The average accuracy, precision, and recall were 0.833, 1.0, and 0.833, respectively. SVM models are also evaluated using the same metrics. The evaluation results show that the SVM model has competitive performance but is slightly different compared to BERT. Accuracy and precision for Taylor Swift and Adele are also high, but recall is slightly lower than BERT. For Rihanna's data, SVM performs better in detecting positive cases compared to BERT, but its precision is slightly lower. The overall average shows that SVM has more balanced accuracy and recall across datasets than BERT.Keywords: Sentiment, Song Review, NLP, Machine Learning, SVM
EXPLANATORY DATA ANALISIS UNTUK MENGEVALUASI PENELUSURAN KATA KUNCI VIDEO PEMBELAJARAN DI YOUTUBE DENGAN PENDEKATAN MACHINE LEARNING Mambang Mambang; Ahmad Hidayat; Finki Dona Marleny; Johan Wahyudi
Jurnal Informatika Dan Tekonologi Komputer (JITEK) Vol. 2 No. 2 (2022): Juli : Jurnal Informatika dan Teknologi Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jitek.v2i2.287

Abstract

The purpose of this study was to find correlations related to the variable number of impressions, likes, subscribers, and comments on each learning video keyword search on YouTube. This research uses quantitative methods and experiments with secondary data sources. Exploratory Data Analysis in machine learning using several libraries in Python programming produces image visualizations that provide information related to the dataset that has been processed, such as boxplot graphs, histograms, line plots, and correlation graphs. Exploratory Data Analysis with machine learning that we have done finds results on boxplot graphs on five variables showing a whisker more elongated upwards which states positive data results. The difference in this histogram chart is in the duration variable. On the line plot graph, we find the keywords learning videos learning mathematics have the advantage of four variables and the keywords of accounting learning videos one variable. Exploratory Data Analysis using the correlation head map in the seaborn library shows that the like and comment variables strongly correlate with a value of 1. Duration variables have a low and negative correlation with other variables. The subscribers variable has a high correlation with the like variable 0.95. Thus, several indicators need to be considered in making learning videos, such as content or content of innovative and creative learning videos, so that the number of likes and comments becomes high. The length of time in learning videos does not affect the number of likes, subscribers, and comments.