Article Per Year (5 Year)
p-Index From 2021 - 2026
3.493
P-Index
This Author published in this journals
All Journal JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING JURNAL MEDIA INFORMATIKA BUDIDARMA Jurnal Penelitian Pendidikan IPA (JPPIPA) Indonesian Journal of Artificial Intelligence and Data Mining Building of Informatics, Technology and Science Charity : Jurnal Pengabdian Masyarakat eProceedings of Engineering
Donni Richasdy
Telkom University
Agriculture, Biological Sciences & Forestry Arts Humanities Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Physics Social Sciences

Published : 29 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 29 Documents
Search

 1   2   3 
Sentiment Analysis of Telkom University as the Best BPU in Indonesia Using the Random Forest Method Irfan Budi Prakoso; Donni Richasdy; Mahendra Dwifebri Purbolaksono
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 6, No 4 (2022): Oktober 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v6i4.4567

Abstract

In this day and age, social media has become a necessity for every human being. By using social media networks, users can easily exchange information, especially on linkedin social media. Linkedin is a social media network that can search for information openly, mainly used for professional networking. It will be easier and more practical to connect with professionals worldwide. Like identity, LinkedIn is often used as a medium to introduce yourself or your business to potential colleagues or companies for various purposes. Social media networks are often used to deliver information in various institutions at State Universities (PTN) and Private Universities (PTS). For example, it conveys information about state and private universities' achievements (PTS) achievements. Telkom University uses Linkedin to convey the achievements that have been achieved. This triggers the public to see posts that are positive, negative, or neutral. This study aims to conduct a sentiment analysis about Telkom University which has become the best private university in Indonesia, based on opinions submitted on LinkedIn social media. The process carried out in this study is to process all opinion data about Telkom University, which is the best private university in Indonesia, from Linkedin and then classification using the Random Forest method based on the categories of positive, neutral, and negative sentiments. Sentiment analysis results that have been obtained using the Random Forest classification method are 92.85% accuracy, 83.33% precision, 91.67% recall, and 84.13% F1-score%.
Chatbot-Based Movie Recommender System Using POS Tagging Muhammad Alwi Nugraha; Z K A Baizal; Donni Richasdy
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.1908

Abstract

The movie recommender system is a technology designed to make it easier for users to provide recommendations quickly and among the many pieces of information. Because the number of movies is huge, it causes a person to be confused in determining the choice of the movie to watch. Many movie recommending systems have been developed, but users cannot interact intensively. Based on these problems, we developed a chatbot-based conversational recommender system, which can interact intensively with the system. The developed chatbot uses normal language handling to permit the framework to comprehend what the user enters as natural language. POS Tagging is used to find tags in the form of movie titles with patterns in the POS Tagging model. However, the algorithm of those used on POS Tagging does not pay attention to the sentence entity, so the predicted title must correspond to the provisions of POS Tagging. Multinomial Naive Bayes looks for similarities of user input to datasets on intents. The dataset with the highest probability value or almost equal to the sentence entered by the user can be used as a response to user input. The test results of the chatbot application showed that the match rate between response and user input was 89.1%. Thus, the developed chatbot can be used well to provide practical and interactive movie recommendations.
Question Answering System Using Semantic Reasoning on Ontology for The History of The Sumedang Larang Kingdom Silvia Atika Anggrayni; Z K A Baizal; Donni Richasdy
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.1910

Abstract

Studying history can train us to understand the sequence of events and increase a sense of nationalism in the younger generation. However, today's young generation views studying history as boring and unimportant. Studying history is considered boring because it has the stereotype of having to learn by reading long writings in books. Therefore, in this study, a Question Answering System (QAS) was built using an ontology to get historical information and get to know the culture. With QAS, users don't have to read long sentences and spend a lot of time searching for historical information, users can also ask questions in natural language without having to pay attention to sentence structure. The ontology was chosen to be able to build a knowledge base on the historical domain and SPARQL was used to find answers in the ontology. The construction of this system is expected not only to help introduce the history of the Sumedang Larang Kingdom but also to be able to introduce the attraction of cultural tourism in Indonesia, especially the Sumedang Larang Kingdom. The results of the evaluation with the system accuracy test showed a result of 87%.
The Organization Entity Extraction Telkom University Affiliated using Recurrent Neural Network (RNN) Muhammad Daffa Regenta Sutrisno; Donni Richasdy; Aditya Firman Ihsan
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.1956

Abstract

In the news portal text, there is a lot of important information such as the name of the person, the name of the organization, or the name of the place. To obtain information in text documents manually, humans must read the contents of the entire news text. To overcome this issue, information extraction, commonly called Named Entity Recognition (NER) was used. The extraction of information expressly for the NER field is used to make it easier to process word or sentence data. It helps search engines and also helps to classify places, times, and organizations. There is a limited number of NER in Indonesian texts using only the Recurrent Neural Network (RNN) method. Similar previous studies only employed other versions of RNN such as LSTM (Long Short Term Memory), BiLSTM (Bidirectional Long Short Term Memory), and CNN (Convolutional Neural Network). NER is one of the answers to the problems that exist in a large number of news portal texts to obtain information effectively and efficiently. The results of this study indicate that the NER system using the RNN method in Indonesian news texts has an F1 -Score of 80%
POS Tagger Improvisation with the Addition of Foreign Word Labels on Telkom University News Winkie Setyono; Donni Richasdy; Mahendra Dwifebri Purbolaksono
Building of Informatics, Technology and Science (BITS) Vol 4 No 2 (2022): September 2022
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i2.1983

Abstract

News is a medium of daily information usually obtained by the public. The news consists of a lot of information in it and is composed of sentence structures. Each language is unique with its own sentence structure, like Indonesian and other foreign languages. But nowadays, many media mix Indonesian with foreign languages, making the sentence structure different from Bahasa Indonesia. To classify these words, Part Of Speech Tagging needed to determine the class of words composed of sentences by learning from the Corpus of each language. With the new sentence structure, POS Tagger requires a larger Corpus to learn. The language structure can determine the results of tagging from the POS Tagger. If there are words that are not in the Corpus, it can reduce the accuracy of the POS Tagger. We conducted to enhance the research results by adding data with a different sentence structure from the Indonesian Language Corpus using sentences from online media. Added about 242 sentences with 7,043 tokens on Corpus focused on Foreign Word tags, which total 3819 tags. After doing some testing and scenarios, the results of the accuracy of POS Tagger show an accuracy of 94.7% using the Hidden Markov Model method with the F1-Score tag FW 78%.
Part-of-Speech Tagging Implementation on Telkom University News using Bidirectional LSTM Method Rheza Ramadhan Putra; Donni Richasdy; Aditya Firman Ihsan
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i1.5506

Abstract

News is a tool used to disseminate information through various media, one of which is the internet. Various kinds of news articles have words that are not recognized in the dictionary such as slang words and have foreign words that do not exist in the corpus. How can a POS tagging model built on the corpus be able to handle word class labeling in Indonesian news. The research was conducted to check the results of POS tagging on a collection of news about Telkom University which was selected manually. By using the bidirectional LSTM model, three test scenarios were attempted to improve the performance of the built model, the test scenarios were applying the best padding for the corpus, comparing the performance results of the modified corpus model with the original corpus model, and determining the dimensions of the Word2vec vector. Then the selected model from each corpus is implemented on the news that has been labeled manually. One of the best scenario tests is obtained by modifying the corpus by removing double words in the word class "X" and changing some of the word classes "X" which are more likely to be foreign words so that they are changed to the word class "FW". The best performance results in the implementation of news about Telkom University using the bidirectional LSTM model which was built based on the modified corpus get accuracy values of 92.74%, precision of 92.85%, recall of 92.74%, and F1-score 92.48%.
Tagging Efficiency Analysis of Part of Speech Taggers on Indonesian News Djatnika Widia Nugraha; Donni Richasdy; Aditya Firman Ihsan
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 1 (2023): Januari 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i1.5384

Abstract

Part of speech tagging (POS tagging) is a part of Natural Process Language (NLP). POS tagging is the process of automatic labeling of a word in a sentence according to the word class. There are various tagger methods in POS tagging, each tagger method has its own characteristics in its application. The research method used is Conditional Random Fields and Hidden Markov Model. The training of the two method models uses the Indonesian language corpus and Indonesian news texts as test data to determine which method is the most efficient based on the results of the accuracy and training time of each model. The method that has the best value is the CRF method with an accuracy value of 97.68 on the evaluation of the corpus test data and 90.02% for the sample Indonesian news dataset with a training time of 146.90 seconds, then there is the HMM method which has the highest accuracy value with a value of 94.25 % and shorter training time relatively shorter at 32.45 seconds and for the sample sentences containing 116 tokens, CRF method produces 90.05% accuracy which is higher than the HMM method which produces 79.31% accuracy.
Pembuatan Tool Anotasi Kata Ganti Bahasa Arab Menggunakan Coreference Resolution Rendy Andrian Saputra; Moch Arif Bijaksana; Donni Richasdy
eProceedings of Engineering Vol 7, No 2 (2020): Agustus 2020
Publisher : eProceedings of Engineering

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

Abstract

Al-Quran merupakan kitab suci orang muslim yang didalamnya banyak sekali ilmu pengetahuan. Seperti yang kita ketahui bahwa Al-Quran diturunkan dengan bahasa arab, sedangkan kita menggunakan bahasa Indonesia. Inilah salah satu penyebab yang membuat kebanyakan orang menjadi sulit memahami isi kandungan dalam Al-Quran. Mengetahui kesetaraan kata dari sebuah kata ganti sangat penting untuk memahami Al-Quran. Untuk mengetahui kesetaraan kata dari sebuah kata, diperlukannya Coreference Resolution. Coreference Resolution merupakan subtugas dari Natural Language Processing (NLP) yang bertugas untuk mengidentifikasi kesetaraan antar entitas, dengan menggunakan metode Naive Bayes sebagai metode klasifikasi yang telah terdapat di dalam tool anotasi. Tool anotasi diperuntukan untuk pengguna yang ahli dalam menafsirkan makna yang terkandung di dalam Al-Quran. Dimaksudkan agar hasil pemberikan rujukan disetiap kata memiliki data yang valid. serta dengan menggunakan tool anotasi pengguna dapat memberikan kesetaraan kata dari suatu kata ganti yang dapat mengacu pada suatu objek dikalimat sebelumnya. Berdasarkan hasil pengujian telah didapatkan nilai akurasi sebesar 80%.
Implementasi Metode Tf-idf Dan K-nearest Neighbor Untuk Seleksi Pelamar Kerja Jofardho Adlinnas; Kemas Muslim Lhaksmana; Donni Richasdy
eProceedings of Engineering Vol 7, No 3 (2020): Desember 2020
Publisher : eProceedings of Engineering

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

Abstract

Abstrak Indonesia merupakan salah satu negara dengan jumlah penduduk terbesar didunia dan mengalami peningkatan disetiap tahunnya, maka dari itu jumlah tenaga kerja juga terus meningkat pada setiap tahunnya dari berbagai jenis tingkatan pendidikan. Perekrutan pegawai merupakan salah satu proses penting menyaring pelamar yang berkualifikasi dan memenuhi standar organisasi/perusahaan. Proses perekrutan pelamar kerja yang dengan jumlah yang banyak menjadikan salah satu faktor bagi perusahaan membutuhkan waktu dan biaya lebih pada proses penyeleksian. Salah satu cara untuk memudahkannya proses seleksi, dengan memberi label/skor pada hasil wawancara pelamar oleh expert/ahli. Untuk menyelesaikan masalah tersebut digunakannya metode Term Frequency-Inverse Document Frequency (TF-IDF) sebagai extraksi fitur dan metode K-Nearest Neighbor (KNN) dengan cosine similarity untuk menghitung jarak tetangga terdekat, sebagai klasifikasi terhadap teks hasil wawancara pelamar. Hasil dari proses ini menunjukkan bahwa KNN merupakan pendekatan yang cukup efektif karena tingkat akurasi KNN mampu menghasilkan keakuratan ratarata mencapai 65.2%. Kata kunci: perekrutan pelamar kerja, klasifikasi teks, K Nearest-Neighbor, Cosine similarity Abstract Indonesia is one of the countries with the largest population in the world and has increased every year, therefore the number of workers also continues to increase every year from various types of education levels. Recruitment of employees is an important process of screening qualified applicants and meeting organizational / company standards. The recruitment process of job applicants with a large number makes one of the faktors for companies requiring more time and money in the selection process. One way to facilitate the selection process, by giving a label / score on the interview results of the applicant by the expert / expert. To solve this problem the term frequency-inverse document frequency (TFIDF) method is used as a feature extraction and the K-Nearest Neighbor (KNN) method K-Nearest Neighbor (KNN) method with cosine similarity to calculate the distance to the nearest neighbor, as a classification of the text of the interview applicants. The results of this process show that KNN is a quite effective approach because the accuracy of KNN is able to produce an average accuracy of 65.2%. Keywords: recruitment of job applicants, text classification, K Nearest-Neighbor, Cosine similarity
Recommendation System in the Form of an Ontology-Based Chatbot for Healthy Food Recommendations for Teenagers Nazar Azmi; Donni Richasdy; Hasmawati
Jurnal Penelitian Pendidikan IPA Vol 9 No 7 (2023): July
Publisher : Postgraduate, University of Mataram

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29303/jppipa.v9i7.4401

Abstract

Adolescents need adequate nutrition to support their growth and to avoid nutritional problems, such as malnutrition or obesity. Nutritional issues during adolescence can significantly influence health problems in adulthood. Although information about nutrition science is widely available on the internet, accurate interpretation requires specialized knowledge of nutrition science. Therefore, a system is needed to provide direct recommendations for healthy food to adolescents. In this study, a recommendation system in the form of a chatbot was developed to recommend healthy food that meets the nutritional needs of adolescents. The system was constructed using Ontology supplemented with Semantic Web Rule Language (SWRL), enabling the recommendation of food according to adolescents' health conditions. From the collected sample data, 150 food menus were recommended. Validation results by nutrition experts showed a precision value of 0.75, a recall of 1, and an F1-score of 0.857. These results indicate that the system is capable of providing appropriate food recommendations for adolescents.
Co-Authors Ade Romadhony Aditya Firman Ihsan Amala, Ihsan Ahsanu Arfive Gandhi Arie Ardiyanti Suryani Aroman, Andika Djatnika Widia Nugraha Elsa Rachel Dementieva Erbina Selvia Br Perangin-Angin Firmansyah, Nanda H Hasmawati Hasmawati Hasmawati Hutari Gani, Prati Irfan Budi Prakoso Jofardho Adlinnas Kemas Muslim Lhaksmana Mahendra Dwifebri Purbolaksono Meillano, Zico Fachreza Moch Arif Bijaksana Muhammad Alwi Nugraha Muhammad Daffa Regenta Sutrisno Muhammad Faris Abdussalam Nazar Azmi Pratama, Reyhan Ramanti Dharayani Rendhy Al-Farrel Rendy Andrian Saputra Rheza Ramadhan Putra Ridho Akbar Rimbawan, Awan Rinaldi Jasmi Saiful Akbar Salsabila Putri Adityani Sa’adah, Siti Sean Akbar Ryanto Silfi Nur Amalia Silvia Atika Anggrayni Sri Widowati Tandya Rizky Pratama Widi Astuti Wijaya, Kurniadi Ahmad Winkie Setyono ZK Abdurahman Baizal