Target-Dependent Twitter Sentiment Classification with Rich Automatic Features

By Duy-Tin Vo. International Joint Conference on Artificial Intelligence, 2015

365 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e5a241df2f4bc8dca3763131571a2145d139f426

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Bing Liu
2. Zixuan Ke
3. Duyu Tang
4. Shuai Wang
5. Hao Tang
6. Hu Xu
7. Bing Qin
8. Sahisnu Mazumder

Citations in the corpus

• Distantly Supervised Lifelong Learning for Large-Scale Social Media Sentiment Analysis (2017, methodology): “(1) First, we label tweets which contain “:)”, “: )”, “:-)”, “: D”, “=)” as positive examples and tweets which contain “:(”, “: (”, “:-(” as negative ones, in the same way as [22]; (2) Second, we remove all emoticons that are used to collect the training data following the method in [7], and ignore ”
• Stance Detection with Bidirectional Conditional Encoding (2016, background): “Stance Detection: Previous work mostly considered target-specific stance prediction in debates (Hasan and Ng, 2013; Walker et al., 2012) or student essays (Faulkner, 2014).”
• Target-Dependent Sentiment Classification With BERT (2019, methodology): “In order to explicitly distinguish target words from the context, Vo and Zhang [41] divide the original sentence into three parts according to a given target, a left context, a right context and the target itself.”
• Like It or Not (2016, methodology): “The dataset created by Dong et al. was also used by Vo and Zhang [2015], who proposed using a rich set of automatic features.”
• Transfer Capsule Network for Aspect Level Sentiment Classification (2019, background): “In recent years, a number of deep learning methods have been proposed for aspect-level sentiment classification (ASC) tasks (Dong et al., 2014; Vo and Zhang, 2015; Tang et al., 2016; Wang et al., 2016a; Ma et al., 2017; Li et al., 2018; Ma et al., 2018; Wang et al., 2018a).”
• Transformation Networks for Target-Oriented Sentiment Classification (2018, methodology): “The early methods mostly adopted supervised learning approach with extensive hand-coded features (Blair-Goldensohn et al., 2008; Titov and McDonald, 2008; Yu et al., 2011; Jiang et al., 2011; Kiritchenko et al., 2014; Wagner et al., 2014; Vo and Zhang, 2015), and they fail to model the semantic rela”
• Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks (2019, methodology): “1Code and preprocessed datasets are available at https://github.com/GeneZC/ASGCN. based sentiment classification are mainly based on neural network methods (Dong et al., 2014; Vo and Zhang, 2015).”
• Lifelong Learning Memory Networks for Aspect Sentiment Classification (2018, background): “[6], [7], [19], where manual feature engineering and external resources are required.”
• Effective LSTMs for Target-Dependent Sentiment Classification (2015, methodology): “To handle this problem, some recent studies (Dong et al., 2014; Vo and Zhang, 2015) use neural network methods and encode each sentence in continuous and low-dimensional vector space without feature engineering.”
• Attentional Encoder Network for Targeted Sentiment Classification (2019, background): “In recent years, neural network models are designed to automatically learn useful lowdimensional representations from targets and contexts and obtain promising results (Dong et al., 2014; Vo and Zhang, 2015; Tang et al., 2016a).”
• Gated Neural Networks for Targeted Sentiment Analysis (2016, methodology): “We also compare our system with the system of Vo and Zhang (2015), which uses more contextual information and sentiment lexicons.”
• Dependency Graph Enhanced Dual-transformer Structure for Aspect-based Sentiment Classification (2020, methodology): “ral Networks (RNN), Convolutional Neural Networks (CNN) (Dong et al., 2014; Vo and Zhang, 2015) have already been widely applied to aspectbased sentiment classification.”
• Interactive Attention Networks for Aspect-Level Sentiment Classification (2017, background): “…have designed effective neural networks to automatically generate useful low-dimensional representations from targets and their contexts and obtain a promising result on the aspect-level sentiment classification task [Dong et al. , 2014; Vo and Zhang, 2015; Wang et al. , 2016; Tang et al. , 2016b].”
• Target-Dependent Sentiment Classification with Long Short Term Memory (2015, background): “…sentiment classification [Socher et al., 2013b; Tang et al., 2015], opinion expression extraction [Irsoy and Cardie, 2014b], building sentiment lexicon [Tang et al., 2014a], open domain sentiment analysis [Zhang et al., 2015], fine-grained opinion mining [Liu et al., 2015], etc.”
• Aspect Level Sentiment Classification with Deep Memory Network (2016, methodology): “Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures.”
• Multi-grained Attention Network for Aspect-Level Sentiment Classification (2018, background): “Traditional approaches (Jiang et al., 2011; Kiritchenko et al., 2014; Vo and Zhang, 2015) regard this task as the text classification problem and design effective features, which are utilized in statistical learning algorithms for training a classifier.”