Text Classification Using Long Short-Term Memory With GloVe Features

Sari, Winda; Rini, Dian Palupi; Malik, Reza Firsandaya

doi:10.26555/jiteki.v5i2.15021

Cited by 35 publications

(28 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Oleh karena itu, sangat penting untuk Merinda Lestandy, Abdurrahim Abdurrahim, Lailis Syafa'ah Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 5 No. 4 (2021) 802 -808 DOI: https://doi.org/10.29207/resti.v5i4.3308 Creative Commons Attribution 4.0 International License (CC BY 4.0) 803 mendeteksi dan menyaringnya agar tidak terjadi penyebaran informasi yang tidak benar.…”

Section: Pendahuluanunclassified

“…Analisis sentimen adalah suatu proses yang bertujuan untuk mengetahui apakah polaritas suatu data berupa teks (dokumen, kalimat, paragraf) akan mengarah ke positif, negatif, atau netral [4]. Klasifikasi teks dari postingan media sosial [5], [6] selalu menjadi masalah penelitian yang menarik dan memiliki tantangan tertentu. Kajian analisis sentimen media sosial tentang COVID-19 menghasilkan lima tema relevan yang berkisar dari positif hingga negatif [7]- [11].…”

Section: Pendahuluanunclassified

See 1 more Smart Citation

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Lestandy

Abdurrahim

Syafaah

2021

RESTI

View full text Add to dashboard Cite

COVID-19 has become a global pandemic including Indonesia, so the government is taking vaccinations as a preventive measure. The public's response to this continues to appear on social media platforms, one of which is Twitter. Tweets about the COVID-19 vaccine have generated various kinds of positive and negative opinions in the community. Therefore, it is very important to detect and filter it to prevent the spread of incorrect information. Sentiment analysis is a method used to determine the content of a dataset in the form of negative, positive or neutral text. The dataset in this study was obtained from 5000 COVID-19 vaccine tweets with the distribution of 3800 positive sentiment tweets, 800 negative sentiment tweets and 400 neutral sentiment tweets. The dataset obtained is then pre-processed data to optimize data processing. There are 4 stages of pre-processing, including remove punctuation, case folding, stemming and tokenizing. This study examines the performance of RNN and Naïve Bayes by adding the TF-IDF (Term Frequency-Inverse Document Frequency) technique which aims to give weight to the word relationship (term) of a document. The test results show that RNN (TF-IDF) has a greater accuracy of 97.77% compared to Naïve Bayes (TF-IDF) of 80%.

show abstract

Section: Pendahuluanunclassified

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Lestandy

Abdurrahim

Syafaah

2021

RESTI

View full text Add to dashboard Cite

show abstract

“…Glove comes with the advantage that it does not just depend on local context (surrounding) information of words but on the global co-occurrence of words in a given corpus by creating a cooccurrence matrix of words in a given corpus unlike Word2Vec which relies on local contextual (surrounding) word information. Glove embeddings has been used in many text problems [18,19]. Embedding comes in some versions with respect to the size of tokens used.…”

Section: B Glove Embeddingsmentioning

confidence: 99%

Analysis of Text Feature Extractors using Deep Learning on Fake News

Ahmed

Ghazanfar

Hussain

et al. 2021

Eng. Technol. Appl. Sci. Res.

View full text Add to dashboard Cite

Social media and easy internet access have allowed the instant sharing of news, ideas, and information on a global scale. However, rapid spread and instant access to information/news can also enable rumors or fake news to spread very easily and rapidly. In order to monitor and minimize the spread of fake news in the digital community, fake news detection using Natural Language Processing (NLP) has attracted significant attention. In NLP, different text feature extractors and word embeddings are used to process the text data. The aim of this paper is to analyze the performance of a fake news detection model based on neural networks using 3 feature extractors: TD-IDF vectorizer, Glove embeddings, and BERT embeddings. For the evaluation, multiple metrics, namely accuracy, precision, F1, recall, AUC ROC, and AUC PR were computed for each feature extractor. All the transformation techniques were fed to the deep learning model. It was found that BERT embeddings for text transformation delivered the best performance. TD-IDF has been performed far better than Glove and competed the BERT as well at some stages.

show abstract

“…Demikian pula, output gate baik mencegah atau memungkinkan keadaan sel dari memiliki efek pada unit lain [7]. Forget gate memungkinkan sel untuk mengingat atau melupakan keadaan sebelumnya dengan mengontrol koneksi berulang-ulang sel [8]. Contoh struktur jaringan LSTM diperlihatkan pada Gambar 2.…”

Section: Gambar 1 Tahapan Penelitianunclassified

Klasifikasi Ekspresi Teks Berbahasa Jawa Menggunakan Algoritma Long Short Term Memory

Putra¹,

Musthafa²,

Wibowo³

2021

Komputika

View full text Add to dashboard Cite

Bahasa Jawa bisa dikatakan Bahasa yang unik karena bahasa Jawa mempunyai banyak arti meskipun satu kata yang sama tetapi beda daerah. Suku Jawa adalah suku terbesar yaitu 41% atau sekitar 95.217.022 jiwa. Pulau Jawa juga pengakses internet terbesar khususnya untuk media sosial yaitu 87,13%, dari data tersebut banyak informasi yang bisa didapatkan dari keaktifan suku Jawa dalam menggunakan media sosial. Khususnya adalah data tekstual, tetapi tidak mudah mendapatkan ekspresi atau emosi suku Jawa dari media sosial karena jumlah datanya sangat banyak. Maka dari itu permasalahan ini dapat di analisa. Teks mining merupakan salah satu cara yang tepat karena data media sosial lebih banyak data tekstual. Menggunakan RNN Architecture dan algoritma Longs Short Term Memory (LSTM), data tekstual akan mudah diolah karena data yang banyak akan dirapikan dan di kalsifikasikan. Sehingga data yang banyak itu akan dipilih dan olah sesuai dengan ekspresi, karena penelitian ini berfokus pada ekspresi dan emosi maka data akan di klasisfikasikan dengan LSTM. Dari hasil proses penggunaan LSTM untuk memilah ekspresi menjadi 4 yaitu marah, senang, sedih, dan takut mendapat akurasi 92%. Akurasi tersebut menunjukkan Long Short Term Memory (LSTM) efektif dalam pengklasifikasian ekspresi teks berBahasa Jawa.

show abstract

Text Classification Using Long Short-Term Memory With GloVe Features

Cited by 35 publications

References 28 publications

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Analisis Sentimen Tweet Vaksin COVID-19 Menggunakan Recurrent Neural Network dan Naïve Bayes

Analysis of Text Feature Extractors using Deep Learning on Fake News

Klasifikasi Ekspresi Teks Berbahasa Jawa Menggunakan Algoritma Long Short Term Memory

Contact Info

Product

Resources

About