A semiautomatic annotation approach for sentiment analysis

2021 ◽  
pp. 016555152110065
Author(s):  
Rahma Alahmary ◽  
Hmood Al-Dossari
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Short Term ◽  
Term Memory ◽  
Annotation Process ◽  
Learning Classifiers ◽  
Long Short Term Memory

Sentiment analysis (SA) aims to extract users’ opinions automatically from their posts and comments. Almost all prior works have used machine learning algorithms. Recently, SA research has shown promising performance in using the deep learning approach. However, deep learning is greedy and requires large datasets to learn, so it takes more time for data annotation. In this research, we proposed a semiautomatic approach using Naïve Bayes (NB) to annotate a new dataset in order to reduce the human effort and time spent on the annotation process. We created a dataset for the purpose of training and testing the classifier by collecting Saudi dialect tweets. The dataset produced from the semiautomatic model was then used to train and test deep learning classifiers to perform Saudi dialect SA. The accuracy achieved by the NB classifier was 83%. The trained semiautomatic model was used to annotate the new dataset before it was fed into the deep learning classifiers. The three deep learning classifiers tested in this research were convolutional neural network (CNN), long short-term memory (LSTM) and bidirectional long short-term memory (Bi-LSTM). Support vector machine (SVM) was used as the baseline for comparison. Overall, the performance of the deep learning classifiers exceeded that of SVM. The results showed that CNN reported the highest performance. On one hand, the performance of Bi-LSTM was higher than that of LSTM and SVM, and, on the other hand, the performance of LSTM was higher than that of SVM. The proposed semiautomatic annotation approach is usable and promising to increase speed and save time and effort in the annotation process.

scholarly journals Algoritma LSTM-CNN untuk Binary Klasifikasi dengan Word2vec pada Media Online

2021 ◽  
Vol 8 (1) ◽  
pp. 64
Author(s):  
Dedi Tri Hermanto ◽  
Arief Setyanto ◽  
Emha Taufiq Luthfi
Keyword(s):  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Direct Impact ◽  
Test Results ◽  
Short Term ◽  
Term Memory ◽  
Traditional Markets ◽  
Interesting Topic ◽  
Long Short Term Memory

Media online banyak menghasilkan berbagai macam berita, baik ekonomi, politik, kesehatan, olahraga atau ilmu pengetahuan. Di antara itu semua, ekonomi adalah salah satu topik menarik untuk dibahas. Ekonomi memiliki dampak langsung kepada warga negara, perusahaan, bahkan pasar tradisional tergantung pada kondisi ekonomi di suatu negara. Sentimen yang terkandung dalam berita dapat mempengaruhi pandangan masyarakat terhadap suatu hal atau kebijakan pemerintah. Topik ekonomi adalah bahasan yang menarik untuk dilakukan penelitian karena memiliki dampak langsung kepada masyarakat Indonesia. Namun, masih sedikit penelitian yang menerapkan metode deep learning yaitu Long Short-Term Memory dan CNN untuk analisis sentimen pada artikel finance di Indonesia. Penelitian ini bertujuan untuk melakukan pengklasifikasian judul berita berbahasa Indonesia berdasarkan sentimen positif, negatif dengan menggunakan metode LSTM, LSTM-CNN, CNN-LSTM. Dataset yang digunakan adalah data judul artikel berbahasa Indonesia yang diambil dari situs Detik Finance. Berdasarkan hasil pengujian memperlihatkan bahwa metode LSTM, LSTM-CNN, CNN-LSTM memiliki hasil akurasi sebesar, 62%, 65% dan 74%.Kata Kunci — LSTM, sentiment analysis, CNNOnline media produce a lot of various kinds of news, be it economics, politics, health, sports or science. Among them, economics is one interesting topic to discuss. The economy has a direct impact on citizens, companies, and even traditional markets depending on the economic conditions in a country. The sentiment contained in the news can influence people's views on a matter or government policy. The topic of economics is an interesting topic for research because it has a direct impact on Indonesian society. However, there are still few studies that apply deep learning methods, namely Long Short-Term Memory and CNN for sentiment analysis on finance articles in Indonesia. This study aims to classify Indonesian news headlines based on positive and negative sentiments using the LSTM, LSTM-CNN, CNN-LSTM methods. The dataset used is data on Indonesian language article titles taken from the Detik Finance website. Based on the test results, it shows that the LSTM, LSTM-CNN, CNN-LSTM methods have an accuracy of, 62%, 65% and 74%.Keywords — LSTM, sentiment analysis, CNN

scholarly journals Evaluation of Sentiment Analysis via Word Embedding and RNN Variants for Amazon Online Reviews

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Najla M. Alharbi ◽  
Norah S. Alghamdi ◽  
Eman H. Alkhammash ◽  
Jehad F. Al Amri
Keyword(s):  
Feature Extraction ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Online Reviews ◽  
Word Embedding ◽  
Learning Approaches ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Consumer feedback is highly valuable in business to assess their performance and is also beneficial to customers as it gives them an idea of what to expect from new products. In this research, the aim is to evaluate different deep learning approaches to accurately predict the opinion of customers based on mobile phone reviews obtained from Amazon.com. The prediction is based on analysing these reviews and categorizing them as positive, negative, or neutral. Different deep learning algorithms have been implemented and evaluated such as simple RNN with its four variants, namely, Long Short-Term Memory Networks (LRNN), Group Long Short-Term Memory Networks (GLRNN), gated recurrent unit (GRNN), and update recurrent unit (UGRNN). All evaluated algorithms are combined with word embedding as feature extraction approach for sentiment analysis including Glove, word2vec, and FastText by Skip-grams. The five different algorithms with the three feature extraction methods are evaluated based on accuracy, recall, precision, and F1-score for both balanced and unbalanced datasets. For the unbalanced dataset, it was found that the GLRNN algorithms with FastText feature extraction scored the highest accuracy of 93.75%. This result achieved the highest accuracy on this dataset when compared with other methods mentioned in the literature. For the balanced dataset, the highest achieved accuracy was 88.39% by the LRNN algorithm.

scholarly journals Perbandingan Model Deep Learning untuk Klasifikasi Sentiment Analysis dengan Teknik Natural Languange Processing

2021 ◽  
Vol 7 (2) ◽  
pp. 113-121
Author(s):  
Firman Pradana Rachman
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Sentiment Analysis ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Setiap orang mempunyai pendapat atau opini terhadap suatu produk, tokoh masyarakat, atau pun sebuah kebijakan pemerintah yang tersebar di media sosial. Pengolahan data opini itu di sebut dengan sentiment analysis. Dalam pengolahan data opini yang besar tersebut tidak hanya cukup menggunakan machine learning, namun bisa juga menggunakan deep learning yang di kombinasikan dengan teknik NLP (Natural Languange Processing). Penelitian ini membandingkan beberapa model deep learning seperti CNN (Convolutional Neural Network), RNN (Recurrent Neural Networks), LSTM (Long Short-Term Memory) dan beberapa variannya untuk mengolah data sentiment analysis dari review produk amazon dan yelp.

Sign in / Sign up

Export Citation Format

Share Document