Claim Missing Document
Check
Articles

Found 12 Documents
Search

Implementation Of Text Mining For Emotion Detection Using The Lexicon Method (Case Study: Tweets About Covid-19) Agus Sasmito Aribowo; Siti Khomsah
Telematika Vol 18, No 1 (2021): Edisi Februari 2021
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v18i1.4341

Abstract

Information and news about Covid-19 received various responses from social media users, including Twitter users. Changes in netizen opinion from time to time are interesting to analyze, especially about the patterns of public sentiment and emotions contained in these opinions. Sentiment and emotional conditions can illustrate the public's response to the Covid-19 pandemic in Indonesia. This research has two objectives, first to reveal the types of public emotions that emerged during the Covid-19 pandemic in Indonesia. Second, reveal the topics or words that appear most frequently in each emotion class. There are seven types of emotions to be detected, namely anger, fear, disgust, sadness, surprise, joy, and trust. The dataset used is Indonesian-language tweets, which were downloaded from April to August 2020. The method used for the extraction of emotional features is the lexicon-based method using the EmoLex dictionary. The result obtained is a monthly graph of public emotional conditions related to the Covid-19 pandemic in the dataset.
PENINGKATAN PEMASARAN PRODUK YANG LESS CONTACT DI DESA WISATA ADILUHUR MELALUI PEMANFAATAN TEKNOLOGI INFORMASI DIMASA PANDEMI COVID - 19 Tri Ginanjar Laksana; Dian Nurdiansyah; Novanda Alim Setya Nugraha; Rima Dias Ramadhani; Siti Khomsah
E-Amal: Jurnal Pengabdian Kepada Masyarakat Vol 2 No 2: Mei 2022
Publisher : LP2M STP Mataram

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

Abstract

Data yang telah dipublikasi oleh Kementrian kesehatan Republik Indonesia tahun 2021, terkait perkembangan virus COVID-19, hingga saat menjadi masalah utama bagi kesehatan masyarakat, khususnya bagi perekonomian di Indonesia. Desa Wisata Adiluhur memiliki beragam desa wisata sehingga dapat menggerakkan perekonomian warga desa. Masyarakat sudah mulai sadar dan ikut terlibat langsung dengan aktivitas pariwisata, dimana mereka memberdayakan diri mereka di berbagai kegiatan ekonomi pariwisata seperti menyewakan homestay, berjualan makanan tradisional, dan membuat kerajinan tangan. Produk-produk hasil penduduk di Desa Adilihur masih dijual secara offline sehingga untuk mendapatkan produk dari desa wisata, masyarakat harus datang langsung. Begitu pula dengan paket wisata museum dan agrowisata belum bisa dibeli secara online. Pengunjung desa wisata Adilihur paling banyak dari daerah Kebumen saja. Tingkat kunjungan jauh menurun ditambah pengelola belum mampu menerapkan standar CHSE atau Cleanliness (Kebersihan), Health (Kesehatan), Safety (Keamanan), dan Environment Sustainability (Kelestarian Lingkungan). Metode pengabdaian masyarakat ini menggunakan penelitian kualitatif dan pendekatan yang digunakan dalam pengabdilan masyarakat ini adalah Community Action Model (CAM), pengabdian masyarakat ini dilakukan dengan cara blended learning antara luring dan daring menggunakan zoom meeting. Program pengabdian masyarakat ini dibuka oleh kepala desa adiluhur dan disambut baik oleh kelompok Desa wisata di adiluhur. Hasil pengabdian masyarakat ini menunjukkan bahwa kegiatan pengabdian masyarakat terkait penerapan teknologi informasi dalam pemasaran produk yang less contact ini mampu meningkatkan pemasaran dan penghasilan kelompok desa wisata, dimana sebelumnya awam/tidak tahu terhadap teknologi informasi. Melalui pengabdian masyarakat ini kelompok desa wisata dapat turut aktif dalam pemasaran melalui internet dalam pemasaran produk dengan less contact di desa adiluhur.
Sentiment Analysis On YouTube Comments Using Word2Vec and Random Forest Siti Khomsah
Telematika Vol 18, No 1 (2021): Edisi Februari 2021
Publisher : Jurusan Teknik Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31315/telematika.v18i1.4493

Abstract

Purpose: This study aims to determine the accuracy of sentiment classification using the Random-Forest, and Word2Vec Skip-gram used for features extraction. Word2Vec is one of the effective methods that represent aspects of word meaning and, it helps to improve sentiment classification accuracy.Methodology: The research data consists of 31947 comments downloaded from the YouTube channel for the 2019 presidential election debate. The dataset consists of 23612 positive comments and 8335 negative comments. To avoid bias, we balance the amount of positive and negative data using oversampling. We use Skip-gram to extract features word. The Skip-gram will produce several features around the word the context (input word). Each of these features contains a weight. The feature weight of each comment is calculated by an average-based approach. Random Forest is used to building a sentiment classification model. Experiments were carried out several times with different epoch and window parameters. The performance of each model experiment was measured by cross-validation.Result: Experiments using epochs 1, 5, and 20 and window sizes of 3, 5, and 10, obtain the average accuracy of the model is 90.1% to 91%. However, the results of testing reach an accuracy between 88.77% and 89.05%. But accuracy of the model little bit lower than the accuracy model also was not significant. In the next experiment, it recommended using the number of epochs and the window size greater than twenty epochs and ten windows, so that accuracy increasing significantly.Value: The number of epoch and window sizes on the Skip-Gram affect accuracy. More and more epoch and window sizes affect increasing the accuracy.
The Accuracy Comparison Between Word2Vec and FastText On Sentiment Analysis of Hotel Reviews Siti Khomsah; Rima Dias Ramadhani; Sena Wijaya
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 6 No 3 (2022): Juni 2022
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (380.214 KB) | DOI: 10.29207/resti.v6i3.3711

Abstract

Word embedding vectorization is more efficient than Bag-of-Word in word vector size. Word embedding also overcomes the loss of information related to sentence context, word order, and semantic relationships between words in sentences. Several kinds of Word Embedding are often considered for sentiment analysis, such as Word2Vec and FastText. Fast Text works on N-Gram, while Word2Vec is based on the word. This research aims to compare the accuracy of the sentiment analysis model using Word2Vec and FastText. Both models are tested in the sentiment analysis of Indonesian hotel reviews using the dataset from TripAdvisor.Word2Vec and FastText use the Skip-gram model. Both methods use the same parameters: number of features, minimum word count, number of parallel threads, and the context window size. Those vectorizers are combined by ensemble learning: Random Forest, Extra Tree, and AdaBoost. The Decision Tree is used as a baseline for measuring the performance of both models. The results showed that both FastText and Word2Vec well-to-do increase accuracy on Random Forest and Extra Tree. FastText reached higher accuracy than Word2Vec when using Extra Tree and Random Forest as classifiers. FastText leverage accuracy 8% (baseline: Decision Tree 85%), it is proofed by the accuracy of 93%, with 100 estimators.
Big Data Analytics to Analyze Sentiment, Emotions, and Perceptions of Travelers (Case Study: Tourism Destination in Purwokerto Indonesia) Siti Khomsah; Rima Dias Ramadhani; Sena Wijayanto
Jurnal E-Komtek (Elektro-Komputer-Teknik) Vol 5 No 2 (2021)
Publisher : Politeknik Piksi Ganesha Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37339/e-komtek.v5i2.791

Abstract

Big data analytics can extract travelers' sentiment, emotions, and experiences from their internet opinions. This study analyzes sentiment, emotion, and traveler experiences at eight tourism destinations in Purwokerto Central Java, Indonesia. The methods are lexicon using NCR vocabulary(EmoLex) and word cloud analysis. The results show visitors generally have a positive sentiment. The five destinations with high positive sentiment are the Village (91%), Lokawisata Baturaden(81%), Baturaden Forest (79%), Limpa Kuwus (78%), and Taman Andang(.77%). In comparison, other destinations achieve positive sentiment under 70%. Only a few visitors give negative sentiment to all tourism destinations. The emotion of visitors stands out in Joy and Trust. NRC revealed sadness dan anger emotion but only about 20%. Cloud analysis does not reveal a distinguish keyword because the word feature still contained noise such as conjunction, adverb, and the name of the sites. Further research must consider other text preprocessing to handle noises.
PEMBERDAYAAN DAN PENINGKATAN KAPASITAS KELEMBAGAAN MASYARAKAT DESA MELALUI AGROWISATA BERBAHASA INGGRIS Novanda Alim Setya Nugraha; Siti Khomsah; Rima Dias Ramadhani; Tri Ginanjar Laksana
DEVOTE: Jurnal Pengabdian Masyarakat Global Vol. 1 No. 2 (2022): DEVOTE: Jurnal Pengabdian Masyarakat Global, Desember 2022
Publisher : LPPM Institut Pendidikan Nusantara Global

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (654.782 KB) | DOI: 10.55681/devote.v1i2.402

Abstract

Agribusiness utilizes inorganic waste that can be recycled to produce selling points such as basket bags from plastic waste and dolls from cloth waste. There is a superior product in this business unit, namely processed Jenitri seeds which are processed into handicrafts. Jenitri seeds are not only used as an ornamental tool. In certain beliefs, the work of Jenitri seeds is used as a worship tool and a medical device. Therefore, Jenitri seeds have a fairly high selling value compared to other handicrafts because of their various functions. Adiluhur Tourism Village is a village that is currently under development as a tourist spot with the name Kebumen English Tourism Village (KWIK) and is located in Adiluhur Village, Kec. Adimulyo, Kab. Kebumen. There are 3 business units that are superior and are still in the development stage, namely business units in the fields of tourism (agro-tourism), agriculture (agriculture), and handicrafts (agribusiness). Currently, the primary superior unit in Adiluhur Tourism Village is a business unit in the tourism sector. Agrotourism is managed by CV in collaboration with BUMDes (Village Owned Enterprise) Mulia Jaya. The tour featured in this unit is an introduction to several types of captive animals (various types of snakes, monitor lizards, sea urchins, iguanas, mongooses, Australian geckos, crocodiles, alligator fish, and many more) as well as a museum containing ancient agricultural tools (bronze spoon, harrows, sickles, hoes, nails, antique lamps, and many more). The potential that is being developed in this unit is outbound with the target visitor being Elementary Schools. Not only that, the agro-tourism manager plans to work with the BKSDA (Natural Resources Conservation Center) in caring for the animals in the unit.
Cluster Analysis of Covid-19 in Indonesia Using K-means Method Claudia Larasvaty; Siti Khomsah; Rona Nisa SA
Indonesian Journal of Data Science, IoT, Machine Learning and Informatics Vol 3 No 1 (2023): February
Publisher : Research Group of Data Engineering, Faculty of Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20895/dinda.v3i1.822

Abstract

These days technology are rapidly increasing and developing in various fields, especially data storage. The information that has been stored in a database usually called a dataset. Covid-19 is a new type of respiratory disease that attacks the respiratory system with rapid transmission, followed by the increasing number of Covid-19 cases that continues to increase every day in all provinces in Indonesia. This study aims to cluster the spread of Covid-19 in every province in Indonesia by using the data that obtained from the website named kaggle with many data variables. The method used in this research is K-Means. From many variables in the data, for this study only 3 variables were taken, which are: Number of Recovery, Number of Deaths, and Number of total Cases in Covid-19 in Indonesia. These 3 variables then will be applied using the K-Means method and formed 3 provincial groups. By using the clustering method and the K-means algorithm, this research can be carried out to find the characteristics of the distribution in each province in Indonesia by looking at the best clusters.
IMPLEMENTASI AUGMENTED REALITY SEBAGAI VIRTUAL GUIDE MENGGUNAKAN METODE MARKER BASED TRACKING Alam Patria Utama; Siti Khomsah; Ummi Athiyah
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 8, No 3 (2023)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v8i3.3832

Abstract

Perkembangan teknologi informasi sangat siginfikan antara lain dibidang Augmented Reality (AR). Teknologi Augmented Reality telah berkembang akhir-akhir ini dan telah diterapkan di berbagai bidang seperti e-commerce, pemasaran, hiburan dan pariwisata. Teknologi AR memiliki potensi besar sebagai sarana pendidikan pariwisata untuk memberikan hal-hal baru kepada masyarakat. Aplikasi ini bertujuan untuk memberikan informasi yang interaktif menggunakan teknologi AR. Manfaat dari aplikasi ini adalah memberikan alternatif lain sebagai pengganti atau pelengkap pemandu tour yang lebih efektif dan menarik. Aplikasi ini menggunakan metode marker-based tracking, metode ini akan memunculkan objek Animasi 2D, 3D, video, audio, ataupun teks. Aplikasi   dengan cara scan dari kamera yang kemudian akan muncul dalam layar smartphone melalui pengenalan sebuah penanda. Pengembangan perangkat lunak ini menggunakan metode Waterfall, dimana pembuatan perangkat lunak dilakukan dengan cara berurutan dimulai dari Analisa, desain, penerapan dan pengujian. Hasil dari penelitian mengenai pembuatan aplikasi augmented reality sebagai media edukasi Candi Arjuna yaitu Aplikasi berjalan dengan baik minimal pada android 6 sampai dengan android 11. Serta intensitas Cahaya 20 lx – 500 lx dengan sudut 30 – 90 dengan jarak marker 30 cm – 90 cm adalah komposisi yang baik untuk menampilkan objek. Untuk pengujian fungsionalitas Black-Box menunjukan seluruh tombol antar muka berjalan sesuai dengan yang diharapkan.
DIVERSIFIKASI PRODUK KERAJINAN DI DESA WISATA KAMPUNG TUDUNG KABUPATEN KEBUMEN PROVINSI JAWA TENGAH Siti Khomsah; Novanda Alim Setya Nugraha; Halim Qista Karima; Aditya Dwi Putro Wicaksono; Lulu Mufidah; Fajar Ibrahim
Prosiding Seminar Nasional Pengabdian Kepada Masyarakat Vol 4 No 1 (2023): PROSIDING SEMINAR NASIONAL PENGABDIAN KEPADA MASYARAKAT - SNPPM2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Negeri Jakarta

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

Abstract

Abstract The main product of the bamboo-craftsmen group in Grujugan Village, Kebumen Regency, Central Java, is a bamboo cap (tudung). Because the tudung product has taken root in the community, Grujugan Village has branded itself as a Tudung Village. The problem of bamboo craftsmen in Grujugan Village is the lack of ability to innovate and diversify product. Therefore, this community service aims to train and mentoring craftsmen in product diversification. The method used is training and mentoring. During the training, the instructor teaches how to create new crafts, that are plates made from coconut sticks. Mentoring was held on July-August. Based on observations before the service was carried out, as many as 95% of the participants had not mastered making woven stick plates. After training and mentoring, 75% of participants were able to make stick plates, of which 50% were able to make stick plates neatly, while the other 25% of the participants were only at the stage of being able to understand the technique of weaving sticks into plates. In conclusion, this community service can enhance the abilities and skills of craftsmen, boost their innovation capabilities, and enable them to create new products in Tudung Village. Abstrak Produk utama kelompok perajin bambu di Desa Grujugan Kabupaten Kebumen Jawa Tengah adalah tudung (caping bambu). Karena produk tudung yang sudah mengakar di masyarakat, Desa Grujugan membranding diri sebagai Kampung Tudung dengan ciri khas kerajinan tudung. Meskipun lama menggeluti kriya bambu, namun variasi produk belum banyak. Selain tudung, perajin membuat peralatan rumah tangga seperti besek, kukusan, dan tenggok. Permasalahan perajin bambu di Desa Grujugan adalah kurangnya kemampuan inovasi dan diversifikasi jenis produk. Oleh karenanya, pengabdian masyarakat ini bertujuan melatih dan mendampingi perajin untuk diversifikasi produk Kampung Tudung berupa piring anyaman kepada kelompok perajin Desa Grujugan. Metode yang digunakan adalah praktik langsung dan pendampingan. Pelatihan secara spesifik mengajarkan bagaimana membuat piring anyaman dari bahan yang lebih sesuai yaitu lidi. Pendampingan diberikan selama bulan Juli- Agustus. Berdasarkan observasi sebelum dilakukan pengabdian, sebanyak 95% peserta belum menguasai teknik pembuatan piring anyaman lidi. Setelah pelatihan dan pendampingan, 75% peserta mampu membuat piring lidi, dimana 50% mampu membuat piring lidi dengan rapi, sedangkan 25% peserta lainnya baru pada tahap mampu memahami teknik menganyam lidi menjadi piring. Kesimpulannya, pengabdian masyarakat yang dilaksanakan dapat meningkatan kemampuan dan ketrampilan perajin, meningkatkan kemampuan inovasi perajin, dan mampu menghasilkan produk baru di Kampung Tudung.
DIGITALISASI DESA UNTUK MENINGKATKAN KUALITAS LAYANAN INFORMASI DAN MEWUJUDKAN KEBUMEN SMART VILLAGE Aditya Dwi Putro; Siti Khomsah; Ummi Athiyah; Novanda Alim Setya Nugraha; Sausan
Prosiding Seminar Nasional Pengabdian Kepada Masyarakat Vol 4 No 1 (2023): PROSIDING SEMINAR NASIONAL PENGABDIAN KEPADA MASYARAKAT - SNPPM2023
Publisher : Lembaga Penelitian dan Pengabdian kepada Masyarakat Universitas Negeri Jakarta

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

Abstract

Abstract Villages are the most accurate data source for searching population data. For this reason, the method of collecting population data, filling in data in formats, processing data and presenting population data information to the public must be carried out effectively and efficiently so that the information can be conveyed quickly and accurately. This activity was carried out in 3 stages, namely survey; implementation of activities; and evaluation of activities. The survey was conducted in several villages in Kebumen Regency. The team assisted in re-arranging the Village website username and password at the Kebumen Regency Communication and Information Hall. In this activity, activities were also carried out to update plugins and main information for administration services on the village website. With the theme Village Digitalization to Improve the Quality of Information Services and realize Kebumen Smart, this activity aims to change the management process and administrative services in the Village to be of better quality and make information about Villages in Kebumen Regency easier to find by the wider community by updating contacts and website pages. , apart from that this activity will run on a scheduled basis for ongoing monitoring and evaluation. This also functions to publish information related to Village Programs, BUMDES, UMKM and the potential that exists in the Village. Abstrak Desa merupakan sumber data paling akurat untuk pencarian data kependudukan. Untuk itu, cara pengumpulan data penduduk, pengisian data dalam format, pengolahan data hingga penyajian informasi data kependudukan kepada masyarakat harus dilakukan secara efektif dan efisien agar informasi yang tersampaikan dapat dengan cepat dan akurat. Kegiatan ini dilakukan dalam 3 tahapan yakni survei; implementasi kegiatan; dan evaluasi kegiatan. survei di lakukan di beberapa desa yang berada di Kabupaten Kebumen. Tim melakukan pendampingan pengurusan kembali username dan password website Desa di Balai Kominfo Kabupaten Kebumen. Dalam kegiatan ini juga dilakukan kegiatan memperbaharui Plugin dan Informasi utama untuk layanan administrasi pada website desa. Dengan tema Digitalisasi Desa untuk Meningkatkan Kualitas Layanan Informasi dan mewujudkan Kebumen Smart kegiatan ini memiliki tujuan mengubah proses pengurusan dan layanan administrasi di Desa menjadi lebih baik kualitasnya dan informasi tentang Desa yang berada di Kabupaten Kebumen lebih mudah dicari oleh masyarakat luas dengan memperbaharui kontak dan laman website, terlepas dari itu kegiatan ini akan berjalan secara terjadwal untuk monitoring dan evaluasi yang berkelanjutan. Hal ini juga berfungsi untuk mempublikasikan Informasi yang berkaitan dengan Program Desa, BUMDES, UMKM dan potensi-potensi yang ada di Desa.