Aspect-Based Sentiment Analysis Using Convolutional Neural Network and Bidirectional Long Short-Term Memory
Abstract
In order to improve performance of previous aspect-based sentiment analysis (ABSA) on restaurant reviews in Indonesian language, this paper adapts the research achieving the highest F1 at SemEval 2016. We use feedforward neural network with one-vs-all strategy for aspect category classification (Slot 1), Conditional Random Field (CRF) for opinion target expression extraction (Slot 2), and Convolutional Neural Network (CNN) for sentiment polarity classification (Slot 3). Aside from lexical features we also use additional features learned from neural networks. We train our model on 992 sentences and evaluate them on 382 sentences. Higher performances are achieved for Slot 1 (F1 0.870) and Slot 3 (F1 0.764) but lower on Slot 2 (F1 0.787).
Metrics
Citation History
Topics
Related Documents
Sentiment Analysis Based on Multiscale Convolutional Neural Network and Bidirectional Long Short-Term Memory
Aspect-Based Sentiment Analysis on Twitter Using Bidirectional Long Short-Term Memory
Rizki Annas SholehatErwin Budi SetiawanYuliant Sibaroni
Text-based sentiment analysis using the tetra dominant optimized Deep Convolutional Neural Network enabled Bidirectional Long Short-Term Memory
Lal Babu PurbeyKamlesh Lakhwani
Sentiment Analysis Using Deep Neural Network 1D Convolutional with Long Short Term Memory
Anomaly-Based Network Intrusion Detection Using Bidirectional Long Short Term Memory and Convolutional Neural Network
Isra Al-TuraikiΝajwa AltwaijryAbeer AgilHaya AljodhiSara M. AlharbiLina Alqassem