Claim Missing Document
Check
Articles

Found 15 Documents
Search

Sarcasm Detection Engine for Twitter Sentiment Analysis using Textual and Emoji Feature Bagus Satria Wiguna; Cinthia Vairra Hudiyanti; Alqis Alqis Rausanfita; Agus Zainal Arifin
Jurnal Ilmu Komputer dan Informasi Vol 14, No 1 (2021): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Information
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v14i1.812

Abstract

Twitter is a social media platform that is used to express sentiments about events, topics, individuals, and groups. Sentiments in Tweets can be classified as positive or negative expressions. However, in sentiment, there is an expression that is actually the opposite of what is mean to be, and this is called sarcasm. The existence of sarcasm in a Tweet is difficult to detect automatically by a system even by humans. In this research, we propose a weighting scheme based on inconsistency between sentimen of tweet contain in Indonesian and the usage of emoji. With the weighting scheme for the detection of sarcasm, it can be used to find out a sentiment about a event, topic, individual, group, or product's review. The proposed method is by calculating the distance between the textual feature polarity score obtained from the Convolutional Neural Network and the emoji polarity score in a Tweet. This method is used to find the boundary value between Tweets that contain sarcasm or not. The experimental results of the model developed, obtained f1-score 87.5%, precision 90.5% and recall 84.8%. By using the textual features and emoji models, it can detect sarcasm in a Tweet.
Sistem Pendaftaran Online untuk PPDB SMA/SMK Negeri Provinsi Jawa Timur Diana Purwitasari; Alqis Rausanfita; Hadziq Fabroyir
Sewagati Vol 4 No 2 (2020)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (427.514 KB)

Abstract

Penerimaan Peserta Didik Baru (PPDB) merupakan langkah awal dalam bidang pendidikan yang menjadi agenda rutin tiap tahunnya dengan dua mekanisme yaitu luar jaringan (offline) dan dalam jaringan (online). Namun pada tahun 2020, Indonesia bahkan dunia sedang ditimpa pandemi Covid-19, yang menyebabkan pemerintah provinsi Jawa Timur tidak bisa melaksanakan PPDB dengan mekanisme luar jaringan (offline). Oleh karena itu, kegiatan pengabdian masyarakat ini membangun sebuah sistem pendaftaran PPDB berbasis web yang dapat memfasilitasi tiga jenis tahapan pendaftaran PPDB jenjang SMA / SMK Negeri Jawa Timur 2020. Sebelum melakukan pendaftaran pada salah satu jalur calon peserta didik harus melaksanakan tahap pengambilan pin. Pengabdian ini mengadopsi konsep objek oriented programming (oop) dengan menggunakan framework code igniter. Sistem pendaftaran online untuk PPDB jenjang SMA/SMK Negeri Jawa Timur telah diuji dengan menggunakan teknik blackbox sehingga dapat dipastikan sistem telah berjalan dengan baik. Sebelum pendaftaran PPDB berlangsung pada tanggal 8 juni 2020 sampai dengan 27 juni 2020, tim informatika ITS telah melakukan sosialisasi sistem, namun tetap saja ketika kegiatan ini berlangsung terdapat beberapa kendala yang dialami calon peserta didik dalam menggunakan sistem. Untuk itu, tim informatika ITS melakukan pendampingan untuk mengatasi kendala-kendala yang terjadi selama berlangsungnya pendaftaran PPDB.
Rancang Bangun Modul Pemeringkatan PPDB SMA/SMK Negeri Jawa Timur 2020 Siti Rochimah; Ridho Rahman Hariadi; Alqis Rausanfita
Sewagati Vol 4 No 3 (2020)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (225.802 KB)

Abstract

Salah satu elemen yang penting dalam mencapai kesuksesan pelaksanaan Penerimaan Peserta Didik Baru yaitu sistem yang digunakan untuk menyeleksi calon peserta baru. Untuk mencapai tujuan serta visi misi Dinas Pendidikan Provinsi Jawa Timur, Dinas Pendidikan Provinsi Jawa Timur membangun sistem pemeringkatan Penerimaan Peserta Didik Baru yang digunakan sebagai alat dalam melakukan seleksi awal kegiatan di bidang Pendidikan tingkat SMA dan SMK Negeri di Jawa Timur yang diadakan tiap setahun sekali. Proses pemeringkatan PPDB SMA/SMK Negeri Jawa Timur dilakukan tiap tahunnya mengikuti kebijakan pada petunjuk teknis yang dibuat oleh Dinas Pendidikan Jawa Timur. Selama berlangsungnya proses PPDB, pengembang menyediakan layanan pendampingan bagi calon peserta didik. Hal tersebut mengakibatkan adanya kemungkinan dilakukannya perubahan pada sistem yang telah dibangun pengembang secara tiba-tiba. Oleh karena itu, dibangunlah sistem pemeringkatan PPDB SMA/SMK Negeri Jawa Timur menggunakan metode Agile. Sistem pemeringkatan PPDB SMA/SMK Negeri Jawa Timur telah diuji dengan menggunakan teknik blackbox sehingga dapat dipastikan sistem telah berjalan dengan baik. Selama proses pemeringkatan terdapat beberapa kendala terkait ketidakpahaman calon peserta didik terhadap sistem perankingkan sehingga pengembang melakukan perbaikan sistem menyesuaikan kebutuhan calon peserta didik.
Analisis Sentimen Twitter Menggunakan Ensemble Feature dan Metode Extreme Learning Machine (ELM) (Studi Kasus: Samsung Indonesia) Alqis Rausanfita; Putra Pandu Adikara; Sigit Adinugroho
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 2 No 12 (2018): Desember 2018
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (428.668 KB)

Abstract

Business activity is very crucial and has a real impact on organizational growth and ROI (Return Of Investment) is to understand and respond appropriately sentiment from customers by conducting a sentiment analysis. The sentiment analysis can be a guide to evaluate a company's product, service, reputation, brand reputation, and the company can be a market leader supported by a very emotional customer condition so that disappointing products / services will lose the customer's commitment even customers will find it difficult to recover customer experience if a company does not care about customer sentiment. Based on the explanation, this research is done using ensemble feature and Extreme Learning Machine for Twitter sentiment analysis. The data used in this research is 72 tweets with the ratio of the amount of training and testing data 70:30 where the amount of data per class is balanced. Prior to the classification of data is done preprocessing, weighting ensemble feature, and weighting the word. The result of this research is get the best hidden neuron number as much as 5000, best activation function is sigmoid bipolar, and ensemble feature influence to accuracy result. Twitter sentiment analysis using ensemble feature and Extreme Learning Machine method in Samsung Indonesia case study did not get high accuracy. Accuracy in getting only amounted to 42.857 percent. The low accuracy caused by sparse data matrix resulting in overfitting which then resulted in low classification results.
Social Media Analysis Training for Digital Talent Development in Indonesia Rochmah, Wachda Yuniar; Oktavia, Vessa Rizky; Rausanfita, Alqis; Hakim, Maulana Naufal; Deudoena, Dara Ilma; Sayoga, Dhiki Sidik
Abdi Masyarakat Vol 5, No 2 (2023): Abdi Masyarakat
Publisher : Lembaga Penelitian dan Pendidikan (LPP) Mandala

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58258/abdi.v5i2.6219

Abstract

The development of digital technology has allowed people to share opinions on social media, send emails, make purchases online, to make phone calls every day. As a result, the amount of data continues to grow rapidly day by day. Most of the data available today is public and accessible to anyone, such as social media data, blogs, news, discussion forums, public government data, and others. With the immense value of this abundant source of social media data, there is an opportunity to extract knowledge or insights from this unstructured social media data, especially to understand opinions, current trends, or influential actors on information spread on the internet. As part of Telkom Surabaya's IT Community Service team that supports student development in SMA/SMK/MA, we propose solutions to the main problems faced today, namely in the field of data analysis. The solutions we offer are also in line with the government's program to increase Digital Talent in Indonesia. In the midst of increasing demand for Digital Talent, there is still a gap between the need for digital talent and job opportunities in Indonesia. The program we will create is Social Media Analysis Training, which will provide an understanding of the benefits of open social media data in general, how to take insights from social media data, and solve problems in various fields.  
Implementasi Digitalisasi Pembuatan Rapor untuk TPQ Al-Mubaarok Surabaya dalam Mendukung Evaluasi Santri Vessa Rizky Oktavia; Rausanfita, Alqis; Safitri, Pima Hani; Satria Bahari Johan, Ahmad Wali
PaKMas: Jurnal Pengabdian Kepada Masyarakat Vol 5 No 1 (2025): Mei 2025
Publisher : Yayasan Pendidikan Penelitian Pengabdian Algero

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54259/pakmas.v5i1.4102

Abstract

Taman Pendidikan Al-Quran (TPQ) is a non-formal educational institution. Often, TPQ prioritizes the quality of educational materials so that it slightly ignores the administrative aspects. A TPQ ​​usually contains asatidz (ustadz and ustadzah) who have expertise in the field of religion, but do not have staff who are experts in administrative matters. Not a few TPQs still use manual recording such as using paper to make report cards. As a result, there are still often errors in recording grades on report cards and asatidz who find it difficult to manage report cards. The problems faced by asatidz become more complicated when the number of students increases. Digitalization is a solution that can solve the problems faced by TPQ. With the digitalization of report cards, asatidz will easily manage student grades and print report cards massively in a short time. Application creation is carried out by analyzing needs, designing interfaces, implementing, and training. This activity was carried out by a community service team from Telkom University and partners of TPQ Al-Mubaarok Surabaya. The result is an application that has reliability in managing student grade data. This application can be accessed from anywhere by TPQ, making it easier for TPQ to manage student report cards. Positive impacts felt include reducing errors when entering data and ease in storing digital data.
SISTEM PENGELOLAAN DATA BERBASIS WEB DAN PELATIHAN BAGI PENGURUS TPQ AL-MUBAAROK SURABAYA rausanfita, alqis; Vessa Rizky Oktavia; Ahmad Wali Satria Bahari Johan; Moch. Andi Divangga Pratama; Fendi Virgiansyah; Muhammad Hanafi Choirulloh
Aptekmas Jurnal Pengabdian pada Masyarakat Vol 7 No 3 (2024): APTEKMAS Volume 7 Nomor 2 2024
Publisher : Politeknik Negeri Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36257/apts.v7i2.8561

Abstract

TPQ Al-Mubaarok, an institution for Quranic learning located in Surabaya, is currently facing challenges in managing student data. Presently, information regarding the students is manually recorded in logbooks, posing a hindrance for the administrators of TPQ Al-Mubaarok to efficiently manage and analyze data. In order to address this issue, we aim to develop a web-based system that facilitates the digital recapitulation process of data. This endeavor begins with conducting field surveys to understand user needs. Subsequently, we proceed to the system design phase and interface design to cater to these needs. System implementation follows the design phase, where we integrate all planned features into a functional system. Next, we conduct system trials involving the authors and the main users of the system, the ustadz/ustadzah. These trials are conducted to ensure that the system operates smoothly and meets user requirements. Finally, we evaluate user satisfaction with the system, particularly from the perspective of the ustadz/ustadzah. The implementation of this system is expected to provide significant benefits, including expediting the registration process for new students, facilitating access to information regarding donations, and providing facilities for managing and summarizing student data more efficiently
Analisis sentiment komentar Instagram bakal calon presiden menggunakan metode Support Vector Machine Alqis Rausanfita; Ramadan, Arip; Dzulfikar Fauzi, Muhammad; Mafidah, Qori Emalia Putri; Ramona, Emilia; Mahardika Putra, Yudha
Tech-E Vol. 7 No. 1 (2023): TECH-E (Technology Electronic)
Publisher : Fakultas Sains dan Teknologi-Universitas Buddhi Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31253/te.v7i1.2289

Abstract

The rising number of Instagram user affecting higher number of comments appear on post especially Instagram accounts of Indonesia's 2024 presidential candidates that made it difficult to understand the public sentiment towards presidential candidate. Therefore, this research aims to classify Indonesian sentiment on Instagram comments of 2024 Indonesian presidential candidates using the Support Vector Machine method. The classified sentiment is divided into three classes, namely positive, negative, and neutral. The results shows that Sentiment Analysis of Comments on Instagram Posts of Indonesia's 2024 Presidential Candidates Using The Support Vector Machine Method has a good accuracy value of 89.41%. This results also obtain recall and precision values of 89% and 87% respectively.
Normalisasi Komentar Media Sosial Pasangan Calon Gubernur 2024 Dengan Statistical Machine Translation Akbar Bayu Adityo , Kahil; Rausanfita, Alqis; Muhajir, Daud
eProceedings of Engineering Vol. 12 No. 5 (2025): Oktober 2025
Publisher : eProceedings of Engineering

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

Abstract

Abstrak — Tingginya aktivitas masyarakat dalam membahas pemilihan Gubernur melalui media sosial menghasilkan data komentar dalam jumlah besar, namun komentar tersebut sering menggunakan bahasa informal, bahasa sehari-hari, singkatan, serta bercampur dengan bahasa daerah dan dialek lokal yang sulit dipahami. Hal ini menghambat pemrosesan data komentar untuk keperluan analisis atau tujuan lainnya. Proses normalisasi manual membutuhkan waktu dan sumber daya yang sangat banyak, terutama jika data yang diolah berjumlah besar. Normalisasi secara manual juga rentan terhadap inkonsistensi dan kesalahan manusia. Jumlah data komentar di media sosial yang terus meningkat membuat normalisasi manual semakin tidak mungkin dan tidak efisien untuk dilakukan, sehingga diperlukan solusi otomatisasi. Sistem normalisasi teks otomatis dikembangkan menggunakan pendekatan Phrase-Based Statistical Machine Translation dengan memanfaatkan Moses. Dataset korpus paralel dibangun dari 31.889 pasangan kalimat informal-formal, sedangkan korpus monolingual terdiri dari 1.613.381 kalimat yang diambil dari Wikipedia. Model dievaluasi menggunakan metrik BLEU untuk mengukur kualitas hasil normalisasi. Model terbaik mencapai skor BLEU 82,16 pada data test dan 81,04 pada data validasi, berhasil mengenali berbagai pola bahasa informal seperti singkatan tidak baku, kata berulang dengan angka, dan bahasa gaul. Namun, sistem memiliki keterbatasan terhadap kemampuan penanganan Out-Of-Vocabulary. Kata kunci— normalisasi teks, PBSMT, Moses, media sosial, gubernur
IMBALANCED DATA HANDLING FOR OPTIMIZING RANDOM FOREST IN SENTIMENT ANALYSIS OF EAST JAVA GUBERNATORIAL ELECTION Rahma Putri Widyaiswari; Anisa Dzulkarnain; Alqis Rausanfita
Jurnal Sistem Informasi dan Informatika (Simika) Vol. 9 No. 1 (2026): Jurnal Sistem Informasi dan Informatika (Simika)
Publisher : Program Studi Sistem Informasi, Universitas Banten Jaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47080/simika.v9i1.4131

Abstract

Social media has become a strategic platform in conveying public opinion, especially at the moment of the Regional Head Election (Pilkada). The large amount of opinion data produced opens up opportunities for the application of sentiment analysis to map public perception. One of the main challenges in the classification of sentiment is the imbalance of distribution between classes, which can degrade the accuracy of the model, especially in recognizing minority classes. This study aims to analyze the impact of the application of data balancing techniques on the performance of the 2024 East Java Regional Election sentiment classification model using the Random Forest algorithm. The series of processes in the study include data preprocessing, manual sentiment labeling, text preprocessing, word weighting with TF-IDF, and model training on three data ratios, namely 90:10, 80:20, and 70:30. Each ratio was tested in three scenarios, namely no balancing (baseline), undersampling using the Tomek Links method, and oversampling using Borderline-SMOTE. Of all scenarios, Borderline-SMOTE gave the highest accuracy of 82.40% at an 80:20 ratio, an increase of 2.19% compared to the unbalanced condition at the same ratio. These results show that data balancing is able to improve the performance of the model in classifying sentiment more proportionally.