Claim Missing Document
Check
Articles

Pembentukan Daftar Stopword menggunakan Zipf Law dan Pembobotan Augmented TF - Probability IDF pada Klasifikasi Dokumen Ulasan Produk Destin Eva Dila Purnama Sari; Yuita Arum Sari; Muhammad Tanzil Furqon
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 1 (2020): Januari 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (367.117 KB)

Abstract

Stopword is an insignificant word contained in a sentence. Stopword was used to help the text preprocessing stage, especially in the stopword removal stage. Digital library was often used at this stage to get a stopword list. However, not all stopword lists in the digital library were words that were not important in the data. The main focus in this research was to find out forming stopword list and word weighting on the document classification of product review using the Zipf Law method. The method used for word weighting was Augmented Term Frequency - Probability Inverse Document Frequency. The document classification process aimed to find out the effect of forming stopword list and word weighting. Document classification using the Support Vector Machine algorithm and Polynomial Kernel. The output of the research was the result of classification accuracy. Based on the result of classification accuracy, there was an effect of forming a stopword list and weighting of words on the classification result. The best accuracy result of the document classification was found at a percentage of 15% for forming stopword list taken from term that has low constant result. The resulting accuracy consisted of a precision value of 0.73, a recall value of 0.7 and a f-measure value of 0.63.
Analisis Sentimen Terhadap Rating dan Ulasan Film dengan menggunakan Metode Klasifikasi Naive Bayes dengan Fitur Lexicon-Based Nadhif Sanggara Fathullah; Yuita Arum Sari; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 2 (2020): Februari 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (495.966 KB)

Abstract

Film is a work of art which liked a lot by movie fans today. The types of films are very diverse and each type of film has its own fans. Every fan has their own assessment of the film they like. Rating becomes an assessment of a film with a certain scale. In addition, the review becomes a translation of fan ratings of the film. The assessment aspects contained in the review include the delivery of stories, shooting techniques, actors, visual effects, etc. In the review itself there are criticisms or comments that contain sentiment towards the film. Sentiment analysis can help film fans determine whether a film has positive or negative sentiments. In order to get the sentiment analysis result, the Naive Bayes Classification Method is used with Lexicon-Based features selection. In the classification process, the appearance of sentiment words are calculated as well as the rating features to determine the sentiment class. Based on the test results, the value of accuracy, precision, and recall has a result of 0.9, 0.9, and 0.9 respectively by selecting the feature in the form of deletion of stopword while the value of accuracy, precision, and recall has a result of 1, 1, and 1 respectively by selecting features in the form of Lexicon-Based.
Analisis Sentimen Terhadap Ulasan Pengguna MRT Jakarta Menggunakan Information Gain dan Modified K-Nearest Neighbor Adella Ayu Paramitha; Indriati Indriati; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 4 (2020): April 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (562.833 KB)

Abstract

Mass Rapid Transit (MRT) is one of rail based public transportation that operates in DKI Jakarta. This transportation is expected to be able to reduce traffic congestion because of private car and motorcycle usage. Improvement on service quality is one of the way to attract people to use public transportation. Service quality improvement can be done by extracting positive and negative feedbacks from users using sentiment analysis. Methods used in this research are Modified K-Nearest Neighbor (MKNN) for classification and Information Gain for feature selection. Comment data will be carried out in the stages of pre-processing, vectorize, feature selection, term weighting using TF-IDF, and classification process. Based on evaluation result, we obtained accuracy value of 0,86769 and f-measure value of 0,86265 with k=3 and threshold-25% as parameter.
Klasifikasi Pertanyaan untuk Question Answering System Bahasa Indonesia menggunakan Support Vector Machine berdasarkan Taksonomi Li & Roth Muhammad Faiz Al-Hadiid; Putra Pandu Adikara; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 13 (2020): Publikasi Khusus Tahun 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Untuk dipublikasikan di 2020 5th International Conference on Sustainable Information Engineering and Technology (SIET 2020)
Klasifikasi Kategori Buku Ilmu Agama Islam Menggunakan Metode Naive Bayes Dan Seleksi Fitur Information Gain Panji Gemilang; Yuita Arum Sari; Suprapto Suprapto
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 6 (2020): Juni 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Books that have important role for making the next generation of nation intelligent, creative, and critical. Special reading books on Islamic religion have various categories, for example categories of creed, morals, sirah, and so forth. Books about Islam and various categories that exist makes it difficult for people to find the desired book according to the category of books that you want to read. Thus this study seeks to classify Islamic religious book categories into 7 categories using the Naive Bayes Multinomial and feature selection Information Gain. The classification process starts from the preprocessing text, features selection by the Information Gain method, and classification using the method Multinomial Naive Bayes. Testing is acuration, precision, and recall with 2 scenarios, namely through the process of stemming and not through the process stemming also analysis the influence of threshold Information Gain. Displaying scenarios through stemming with a 50% feature selection has the best accuracy, precision, and recall results of 69%, 74%, and 69% by order. Based on testing algorithms can classify the categories of Islamic religious science books using the Naive Bayes Multinomial method and feature selection Information Gain
Analisis Sentimen pada Opini Konsumen menggunakan Metode Naive Bayes dengan Seleksi Fitur Pearson Correlation Coefficient Safira Dyah Karina; Yuita Arum Sari; Sutrisno Sutrisno
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 13 (2020): Publikasi Khusus Tahun 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Untuk dipublikasikan di 2020 5th International Conference on Sustainable Information Engineering and Technology (SIET 2020)
Implementasi Fuzzy Analytical Hierarchy Process Untuk Menentukan Berita Utama (Headline News) di Kavling 10 Akbar Imani Yudhaputra; Edy Santoso; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 4 No 7 (2020): Juli 2020
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

News is very important for people's lives, through public news can add insight, get new or current information, express opinions or opinions in public etc. news can be published through a bulletin, in the bulletin there is a headline which is the best news from a collection of news that is there to be used as a headline for the purpose of attracting interest and increasing the curiosity of readers on the next page, so that the selection of headlines is very important. There are problems experienced by the Kavling 10 Editor for or in determining the headlines. There are two options prepared namely searching for the highest news value and preparing a special coverage theme. The two options still have a problem, which is the confusion of choosing the main news in a bulletin called Juros PKK Maba. The criteria used to look for the highest news value are 12, while the special coverage theme criteria are 6. With the Fuzzy Analytical Hierarchy Process (FAHP) method, the problem can be overcome. The FAHP procedure systematically or sequentially starts from determining the weight of the criteria, testing the consistency, determining the alternative weights for each criterion, and ranking so as to produce recommendations. Tests performed using the Spearman correlation test with a total of 8 tests resulted in values ​​of 0.64, 0.83, 0.61, 0.91, 0.65, 0.78, 0.64 and 0.78. So we get four strong relationships, three very strong relationships, and one close to perfect relationship. All test results have a direct relationship. It was concluded that the results of the ranking of the system using the FAHP method with the results of the ranking of experts there is a match.
Pengelompokan Sentimen Pada Twitter Tentang Pendapat Masyarakat Terhadap Karantina Selama Pandemi COVID-19 Menggunakan Metode DBSCAN Noerhayati Djumaah Manis; Yuita Arum Sari; Imam Cholissodin
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 2 (2021): Februari 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

Corona Virus 2019 (COVID-19) has now spread rapidly throughout the world since December 2019, so quarantine is carried out to limit the spread of the disease. The implementation of quarantine raises pros and cons from the public which makes the public express all their opinions and criticisms via Twitter. However, every tweet uploaded by the public does not contain the appropriate meaning so a sentiment analysis is necessary. The classification mechanism can be used to determine the polarity of sentiments but classification has its drawbacks. In the classification there is an unsupervised classification or clustering. The K-Means method is often used for clustering, but it still has weaknesses. Therefore, this study conducted a sentiment clustering on Twitter about public opinion of quarantine during COVID-19 pandemic using the DBSCAN method. Based on the results of tests carried out with 200 data, the best silhouette coefficient value is 0.32 at an epsilon value of 20 and a minPts value of 15, while the best davies bouldin index value is 0.10 at an epsilon value of 15 and a minPts value of 15. This research also gets more analysis results on neutral sentiment, which means that the public is of a neutral opinion towards quarantine during the COVID-19 pandemic.
Pengaruh Metode Word Embedding dalam Vector Space Model pada Pemerolehan Informasi Materi IPA Siswa SMP Ibnu Rasyid Wijayanto; Imam Cholissodin; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 3 (2021): Maret 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

The Covid-19 pandemic in early 2019 made the face-to-face learning system in schools transformed into online learning. Online learning requires students to access digital learning materials, but the materials in the search results is often too broad which causes difficulties for students including junior high school students. This can be overcome with an Information Retrieval System that can make it easier for junior high school students to learn the desired materials, for example science materials. The Information Retrieval System in this study uses the Vector Space Model (VSM) method and the weighting using the Term Frequency Inverse-Document Frequency (TF-IDF) method. Systems that use the TF-IDF and VSM methods are tested with a combination of the TF-IDF, VSM and Word Embedding methods to determine the effect of the Word Embedding Method on the system. The result from this research is that word embedding can have an effect. The precision, recall, F-measure and accuracy values in the combined system test of the VSM and TF-IDF methods are 0.395, 0.8628, 0.5375, and 0.9306, respectively. The precision, recall, F-measure and system test accuracy values with the addition of Word Embedding in the VSM and TF-IDF methods are 0.38, 0.8880, 0.52822, and 0.9286, respectively. The effect of Word Embedding is that word embedding retrives more documents so that the range of documents obtained is larger. However, the use of additional word embedding in the vector space model can cause a reduction in the level of relevance because documents that should be irrelevant and unwanted by the user are likely to be retrieved by the system.
Pemerolehan Informasi Pada Alkitab Berbahasa Indonesia Dengan Bm25f Dan Query Expansion Wordnet Bahasa Amelia Kosasih; Putra Pandu Adika; Yuita Arum Sari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 5 (2021): Mei 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

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

Abstract

As an Indonesian who had a religion, holy book is something important that cannot be separated from worship. Thanks to technological advances, it is increasingly easier to find information, such as in reading holy books. Time becomes so much important so we are always required to be fast even in obtaining information. However, this is not matched by the content of the holy book which is not just few. Therefore, we need an information retrieval system that can generate information that user wants precisely and quickly. BM25F method used for ranking documents because it considers the document structure by giving weight to each field. In addition, the query expansion technique using a thesaurus in the form of WordNet is also applied to solve the problem of human mistakes or ambiguities of the queries entered by the user. Tests conducted on the boost value on the BM25F get the best results at title boost 5 and content boost 1 with an average precision@k value of 0.95 at k=5 and an average r-precision value of 0.84. Testing without using query expansion produces an average precision@k value of 0.896 and an average r-precision value of 0.956, while testing using query expansion produces an average value of precision@k of 0.884 and an average r-precision value of 0.936.
Co-Authors Achmad Arwan Achmad Dinda Basofi Sudirman Ade Kurniawan Adella Ayu Paramitha Adi Mashabbi Maksun Adinugroho, Sigit Agus Wahyu Widodo Ahmad Efriza Irsad Ahmad Fauzi Ahsani Akbar Imani Yudhaputra Akhmad Muzanni Safi'i Akhmad Rohim Akmilatul Maghfiroh Alip Setiawan Amalia Safitri Hidayati Amelia Kosasih Andina Dyanti Putri Anggita Mahardika Ani Enggarwati Arrizal Amin Barbara Sonya Hutagaol Bayu Rahayudi Berlian Bidari Ratna Sari B Binti Najibah Agus Ratri Budi Darma Setiawan Cahya Chaqiqi Candra Dewi Chindy Putri Beauty Dea Valentina Delischa Novia Sabilla Destin Eva Dila Purnama Sari Devinta Setyaningtyas Atmaja Dhimas Anjar Prabowo Dian Eka Ratnawati Dika Perdana Sinaga Dyva Agna Fauzan Edy Santoso Eka Dewi Lukmana Sari Eka Novita Shandra Fachrul Rozy Saputra Rangkuti Fadhil Yusuf Rahadika Fajar Pradana Fakhruddin Farid Irfani Faraz Dhia Alkadri Farid Rahmat Hartono Fatwa Reza Rizqika Febriana Ranta Lidya Fida Dwi Febriani Fira Sukmanisa Fitra Abdurrachman Bachtiar Fitria Indriani Frisma Yessy Nabella Gabriel Mulyawan Gagas Budi Waluyo Galuh Fadillah Grandis Gregorius Ivan Sebastian Hafid Satrio Priambodo Hamim Fathul Aziz Haris Bahtiar Asidik Ian Lord Perdana Ibnu Rasyid Wijayanto Imam Cholissodin Imam Cholissodin Inas Istiqlaliyyah Indriati Indriati Irma Pujadayanti Ivan Ivan Juniman Arief Karunia Ayuningsih Kenza Dwi Anggita Kresentia Verena Septiana Toy Kukuh Wiliam Mahardika Lita Handayani Tampubolon M. Ali Fauzi M. Ali Fauzi Mala Nurhidayati Marji Marji Moch Alyur Ridho Moch. Ali Fauzi Mohammad Rizky Hidayatullah Muh. Arif Rahman Muhammad Abdan Mulia Muhammad Bima Zehansyah Muhammad Faiz Al-Hadiid Muhammad Rizky Setiawan Muhammad Sanzabi Libianto Muhammad Tanzil Furqon Muhammad Zaini Rahman Nadhif Sanggara Fathullah Noerhayati Djumaah Manis Nova Amynarto Novan Dimas Pratama Novanto Yudistira Nugroho Dwi Saksono Nur Aisyah Asriani Ofi Eka Novyanti Panji Gemilang Panji Prasuci Saputra Pretty Natalia Hutapea Putra Pandu Adika Putra Pandu Adikara Putri Harnis Raditya Rinandyaswara Randy Cahya Wihandika Randy Ramadhan Rasif Nidaan Khofia Ahmadah Ratih Kartika Dewi Ratna Tri Utami Refi Fadholi Renaza Afidianti Nandini Rendi Cahya Wihandika Restu Amara Rezza Pratama Rhevitta Widyaning Palupi Rifki Akbar Siregar Rizky Ardiawan Rizky Maulana Iqbal Rosintan Fatwa Safira Dyah Karina San Sayidul Akdam Augusta Sarah Najla Adha Sarah Yuli Evangelista Simarmata Sigit Adi Nugroho Sigit Adinugroho Sinta Kusuma Wardani Sulaiman Triarjo Supraptoa Supraptoa Sutrisno Sutrisno Tibyani Tibyani Tri Rahayuni Tuahta Ramadhani Utaminingrum, Fitri Vriza Wahyu Saputra Wahyuni Lubis Willy Karunia Sandy Yosua Dwi Amerta