Septiyawan Rosetya Wardhana
Institut Teknologi Adhi Tama Surabaya

Published : 7 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika

ANALISA SENTIMEN REVIEW PRODUK HANDPHONE PADA SITUS AMAZON MENGGUNAKAN PENDEKATAN LEXICON BERDASARKAN SENTIWORDNET Anugerah Tri Siswanto; Rani Rotul Muhima; Septiyawan Rosetya Wardhana
KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Vol 3, No 1 (2022)
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.kernel.2022.v3i1.1928

Abstract

Sentiment analysis is part of opinion mining, is the process of understanding, extracting and processing textual data automatically to obtain information. It is done to find out the attitude of a speaker or writer later to be classified into positive or negative sentiment groups. In this study, the determination of the word value in the document is determined using Lexicon Sentiwordnet as a benchmark for word value, the review document will go through several pre-processing stages including Delete URLs, Remove Punctuation, Casefolding, Delete Stopwords, POS Tagging, Sentence tokens, and tokens. word so that the review document data are structured. Furthermore, the Sentiwordnet Interpretation calculation is carried out to determine the value of a term or word in the document to determine whether the word is a positive or negative word based on its category in the POS Tagging process. Then do the calculation of the term score summation, calculate the value of the sentence, calculate the text score, and the results of the rating system that will generate a rating to determine the quality of a mobile phone product based on user reviews.
Analisis Sentimen Terhadap Video Ulasan Produk Menggunakan Metode Support Vector Machine Dengan Sequential Minimal Optimization Mohammad Aji Subarkah; Wenny Mistarika Rahmawati; Septiyawan Rosetya Wardhana; Rinci Kembang Hapsari
KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Vol 3, No 2 (2022)
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.kernel.2022.v3i2.4039

Abstract

The popularity of video as a medium for reviewing a product today has created interest and dependence on other users to look for video recommendations before buying the desired effect. Youtube social media is one of the media that has product reviews in the form of videos. The use of sentiment analysis can predict the tendency of someone's video review to have a positive or negative opinion which can be done by processing the video review into text form first using speech recognition. In this study, thoughts that have been in the form of text will be followed by the process of tokenizing, weighting and classification by applying the Support Vector Machine (SVM) algorithm model using Sequential Minimal Optimization (SMO) optimization. Based on the results of this study, it shows that the accuracy, recall, precision and f-measure values will increase with the increasing number of terms tested, while the C value variable in the enhanced SMO cannot be retrieved because the resulting accuracy value fluctuates. The test results with term 300 and C 1.5 get the highest value: accuracy 89.91%, recall 89.12%, precision 94.97% and f-measure 91.05.
Penentuan Relevansi Artikel Ilmiah dengan Metode Word2Vec Kaisul Fuqara Dewanda; Weny Mistarika Rahmawati; Septiyawan Rosetya Wardhana; Gusti Eka Yuliastuti
KERNEL: Jurnal Riset Inovasi Bidang Informatika dan Pendidikan Informatika Vol 3, No 2 (2022)
Publisher : Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.kernel.2022.v3i2.4038

Abstract

ArXiv merupakan tempat menyimpan pracetak elektronik termasuk artikel ilmiah dan dapat diakses oleh semua pengguna internet secara online. Seiring berjalannya waktu, dokumen artikel ilmiah makin bertambah banyak. Hal tersebut dapat menurunkan tingkat efektifitas pengelompokkan artikel ilmiah berdasarkan bidang keminatan pengguna. Suatu sistem rekomendasi diperlukan untuk penentuan relevansi artikel ilmiah dapat memberi pengguna rekomendasi artikel ilmiah yang sesuai bidang keminatan pengguna, sehingga pengguna akan lebih mudah dalam mengakses artikel ilmiah pada sistem tersebut. Penulis akan melakukan word embedding dengan menerapkan metode Word2Vec. Word2Vec merupakan metode pembelajaran mesin untuk mendapatkan sebuah vektor berkualitas tinggi. Berdasarkan hasil pengujian didapatkan kesimpulan bahwa metode Word2Vec dapat digunakan untuk menghasilkan rekomendasi artikel ilmiah sesuai bidang keminatan pengguna dan menghasilkan nilai parameter terbaik n=150, epoch=100, window size=3 dan learning rate=0.01.