Meganingrum Arista Jiwanggi
Fakultas Ilmu Komputer, Universitas Indonesia, Kampus UI Depok

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

PERBANDINGAN ALGORITMA KLASIFIKASI DALAM PENDETEKSIAN PENYAKIT KANKER Hidayanto, Achmad Nizar; Hapsari, Ika Chandra; Jiwanggi, Meganingrum Arista; Fitria, Diane
Proceedings of KNASTIK 2010
Publisher : Duta Wacana Christian University

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Kanker merupakan salah satu penyakit pembunuh teratas. Menurut  data dari WHO tahun 2008, kanker menyebabkan 12,6% kematian di dunia setelah penyakit jantung dan infeksi. Salah satu kesulitan dalam pendeteksian penyakit kanker adalah perlunya pasien untuk melakukan berbagai macam uji lab sebelum mereka divonis terkena penyakit kanker atau tidak. Penelitian ini bertujuan untuk melakukan deteksi penyakit kanker berdasarkan hasil uji lab yang sudah dilakukan oleh pasien. Terdapat empat hasil uji lab yang dipergunakan sebagai variabel untuk melakukan klasifikasi. Untuk melakukan deteksi penyakit kanker ini, digunakan beberapa algoritma klasifikasi yang sudah disediakan oleh SPSS Clementine 11.1 atau Weka 3.6.0, yaitu  Neural Network, C5.0, Logistic, Classification via Regression, dan LogitBoost. Algoritma Neural Network  sendiri  terdiri dari 6 metode, yaitu Dynamic ,Prune, Exhaustive Prune, Quick, RBFN dan Multiple. Percobaan dilakukan sebanyak sepuluh kali untuk masing-masing algoritma atau metode. Pada tiap percobaan, terdapat dua kali treatment terhadap data yang diolah.  Hasil percobaan menunjukkan bahwa  algoritma Neural Network dengan metode Prune menghasilkan hasil yang terbaik dalam mendeteksi penyakit kanker.
Analyzing public perception toward COVID-19 vaccines in Indonesia Rizqiyah, Putri; Yulianti, Evi; Jiwanggi, Meganingrum Arista
International Journal of Public Health Science (IJPHS) Vol 13, No 1: March 2024
Publisher : Intelektual Pustaka Media Utama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijphs.v13i1.23134

Abstract

The research is prompted by the dearth of studies addressing public perceptions of various COVID-19 vaccines in Indonesia using extensive datasets spanning and a wide timeframe. This study examined public perception toward COVID-19 vaccines in Indonesia using a dataset of tweets. We further detect whether there are any changes in sentiment toward each type of vaccine. The five most commonly used vaccines in Indonesia (AstraZeneca, Moderna, Pfizer, Sinopharm, and Sinovac) were analyzed for sentiment using a lexicon-based method: Valence Aware Dictionary and Sentiment Reasoner (VADER), with changes in sentiment detected using Pruned Exact Linear Time (PELT). The 280,826 tweets collected between 2021 and 2022, 39% were positive, 18% were negative, and 43% were neutral. While Indonesian citizens generally responded positively and neutrally to each vaccine, with Sinopharm and Pfizer receiving the highest sentiment scores and AstraZeneca receiving the lowest, some change points in sentiment were associated with real-world events. Jakarta had the highest number of tweets (22%), while Maluku had the highest sentiment score (0.498). A significant positive correlation was also found between the total number of tweets and two variables: new cases of COVID-19 (r=0.9, p=0.001) and total new deaths caused by COVID-19 (r=0.8, p=0.008). Overall, the discussion of COVID-19 vaccines is still ongoing, and Indonesian citizens tend to respond neutrally and positively regardless of location or time.
Adjusted TextRank for keyword extraction in petrochemical project correspondence documents Atmoko, Indri; Yulianti, Evi; Jiwanggi, Meganingrum Arista
Indonesian Journal of Electrical Engineering and Computer Science Vol 35, No 2: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v35.i2.pp1171-1180

Abstract

A large petrochemical construction project is typically executed by multiple parties, all bound by contract agreement. During the execution phase, issues and problems may arise because the work details are not clearly specified in the contractual agreement. These issues are formally communicated and documented through written correspondence letters. By identifying important keywords within these formal letters, a comprehensive narrative of the project, including its associated issues, can be identified and analyzed. In this research, we introduce an adjusted TextRank algorithm that integrates external features from the Indonesian FastText language model and term frequency-inverse document frequency (TF-IDF) scores to identify important keywords within a dataset of correspondence letters of petrochemical projects. This enhancement involves refining phrase detection, semantic relationship estimation between words, and part-of-speech (POS) identification for words or phrases. Our results show that the proposed adjustments result in improved evaluation scores compared to the baseline standard TextRank and standard TF-IDF, respectively by 24.1% and 25% in terms of F-1 scores.