Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review
Expert Systems with ApplicationsPublished 6 October 2018
Hai Duong Ha, PWC Prasad, Angelika Maag, Abeer Alsadoon
Citations617
SJR quartileQ1
SJR score1.85
SNIP2.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This article aims to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.
Abstract
The increasing volume of user-generated content on the web has made sentiment analysis an important tool for the extraction of information about the human emotional state. A current research focus for sentiment analysis is the improvement of granularity at aspect level, representing two distinct aims: aspect extraction and sentiment classification of product reviews and sentiment classification of target-dependent tweets. Deep learning approaches have emerged as a prospect for achieving these aims with their ability to capture both syntactic and semantic features of text without requirements for high-level feature engineering, as is the case in earlier methods. In this article, we aim to provide a comparative review of deep learning for aspect-based sentiment analysis to place different approaches in context.
Keywords
Computer Science
Neural ComputationLong Short-Term Memory
98,079 Citations1997Sepp Hochreiter, Jürgen Schmidhuber
A novel, efficient, gradient based method called long short-term memory (LSTM) is introduced, which can learn to bridge minimal time lags in excess of 1000 discrete-time steps by enforcing constant error flow through constant error carousels within special units.
Glove: Global Vectors for Word Representation
33,769 Citations2014Jeffrey Pennington, Richard Socher +1 more
A new global logbilinear regression model that combines the advantages of the two major model families in the literature: global matrix factorization and local context window methods and produces a vector space with meaningful substructure.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
24,447 Citations2014Kyunghyun Cho, Bart van Merriënboer +5 more
Qualitatively, the proposed RNN Encoder‐Decoder model learns a semantically and syntactically meaningful representation of linguistic phrases.
Neural NetworksDeep learning in neural networks: An overview
18,033 Citations2014Jürgen Schmidhuber
This historical survey compactly summarizes relevant work, much of it from the previous millennium, review deep supervised learning, unsupervised learning, reinforcement learning & evolutionary computation, and indirect search for short programs encoding deep and large networks.
arXiv (Cornell University)Neural Machine Translation by Jointly Learning to Align and Translate
14,565 Citations2014Dzmitry Bahdanau
Convolutional Neural Networks for Sentence Classification
13,798 Citations2014Yoon Kim
The CNN models discussed herein improve upon the state of the art on 4 out of 7 tasks, which include sentiment analysis and question classification, and are proposed to allow for the use of both task-specific and static vectors.
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
11,710 Citations2013Tomáš Mikolov, Kai Chen +2 more
arXiv (Cornell University)Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
10,728 Citations2014Jun‐Young Chung, Çaǧlar Gülçehre +2 more
These advanced recurrent units that implement a gating mechanism, such as a long short-term memory (LSTM) unit and a recently proposed gated recurrent unit (GRU), are found to be comparable to LSTM.
Mining and summarizing customer reviews
7,714 Citations2004Minqing Hu, Bing Liu
This research aims to mine and to summarize all the customer reviews of a product, and proposes several novel techniques to perform these tasks.
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
6,774 Citations2013Richard Socher, Alex Perelygin +5 more
A Sentiment Treebank that includes fine grained sentiment labels for 215,154 phrases in the parse trees of 11,855 sentences and presents new challenges for sentiment compositionality, and introduces the Recursive Neural Tensor Network.
arXiv (Cornell University)Natural Language Processing (almost) from Scratch
5,172 Citations2011Ronan Collobert, Jason Weston +4 more
Neural Architectures for Named Entity Recognition
4,428 Citations2016Guillaume Lample, Miguel Ballesteros +3 more
Comunicacio presentada a la 2016 Conference of the North American Chapter of the Association for Computational Linguistics, celebrada a San Diego (CA, EUA) els dies 12 a 17 of juny 2016.
Natural Language Processing (almost) from Scratch
3,987 Citations2011Ronan Collobert, Jason Weston +4 more
Studies in computational intelligenceSupervised Sequence Labelling with Recurrent Neural Networks
3,084 Citations2012Alex Graves
A new type of output layer that allows recurrent networks to be trained directly for sequence labelling tasks where the alignment between the inputs and the labels is unknown, and an extension of the long short-term memory network architecture to multidimensional data, such as images and video sequences.
End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF
2,589 Citations2016Xuezhe Ma, Eduard Hovy
A novel neutral network architecture is introduced that benefits from both word- and character-level representations automatically, by using combination of bidirectional LSTM, CNN and CRF, thus making it applicable to a wide range of sequence labeling tasks.
Attention-based LSTM for Aspect-level Sentiment Classification
2,344 Citations2016Yequan Wang, Minlie Huang +2 more
This paper reveals that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect, and proposes an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.
SemEval-2014 Task 4: Aspect Based Sentiment Analysis
1,881 Citations2014Maria Pontiki, Dimitrios Galanis +4 more
SemEval2014 Task 4 aimed to foster research in the field of aspect-based sentiment analysis, where the goal is to identify the aspects of given target entities and the sentiment expressed for each aspect.
Wiley Interdisciplinary Reviews Data Mining and Knowledge DiscoveryDeep learning for sentiment analysis: A survey
1,868 Citations2018Lei Zhang, Shuai Wang +1 more
An overview of deep learning is given and a comprehensive survey of its current applications in sentiment analysis is provided.
Machine LearningDistributed representations, simple recurrent networks, and grammatical structure
1,381 Citations1991Jeffrey L. Elman
arXiv (Cornell University)Recent Trends in Deep Learning Based Natural Language Processing
1,254 Citations2017Tom Young, Devamanyu Hazarika +2 more
SemEval-2016 Task 5: Aspect Based Sentiment Analysis
1,224 Citations2016Maria Pontiki, Dimitrios Galanis +16 more
This paper describes the SemEval 2016 shared task on Aspect Based Sentiment Analysis (ABSA), a continuation of the respective tasks of 2014 and 2015, which attracted 245 submissions from 29 teams and provided 19 training and 20 testing datasets.
SemEval-2015 Task 12: Aspect Based Sentiment Analysis
1,152 Citations2015Maria Pontiki, Dimitrios Galanis +3 more
The task provided manually annotated reviews in three domains (restaurants, laptops and hotels), and a common evaluation procedure, to foster research beyond sentenceor text-level sentiment classification towards Aspect Based Sentiment Analysis.
arXiv (Cornell University)Convolutional Neural Networks for Sentence Classification
1,116 Citations2014Yoon Kim
Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification
1,066 Citations2014Li Dong, Furu Wei +4 more
AdaRNN adaptively propagates the sentiments of words to target depending on the context and syntactic relationships between them and it is shown that AdaRNN improves the baseline methods.
Recurrent Attention Network on Memory for Aspect Sentiment Analysis
1,024 Citations2017Peng Chen, Zhongqian Sun +2 more
A novel framework based on neural networks to identify the sentiment of opinion targets in a comment/review that adopts multiple-attention mechanism to capture sentiment features separated by a long distance, so that it is more robust against irrelevant information.
arXiv (Cornell University)Comparative Study of CNN and RNN for Natural Language Processing
894 Citations2017Wenpeng Yin, Katharina Kann +2 more
This work is the first systematic comparison of CNN and RNN on a wide range of representative NLP tasks, aiming to give basic guidance for DNN selection.
Knowledge-Based SystemsAspect extraction for opinion mining with a deep convolutional neural network
852 Citations2016Soujanya Poria, Erik Cambria +1 more
This paper used a 7-layer deep convolutional neural network to tag each word in opinionated sentences as either aspect or non-aspect word, and developed a set of linguistic patterns for the same purpose and combined them with the neural network.
IEEE Transactions on Knowledge and Data EngineeringSurvey on Aspect-Level Sentiment Analysis
828 Citations2015Kim Schouten, Flavius Frăsincar
An in-depth overview of the current state-of-the-art of aspect-level sentiment analysis is given, showing the tremendous progress that has been made in finding both the target, which can be an entity as such, or some aspect of it, and the corresponding sentiment.
Synthesis lectures on human language technologiesNeural Network Methods for Natural Language Processing
771 Citations2017Yoav Goldberg
This book focuses on the application of neural network models to natural language data, and introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural Networks, conditioned-generation models, and attention-based models.
Expert Systems with ApplicationsImproving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN
726 Citations2016Tao Chen, Ruifeng Xu +2 more
A divide-and-conquer approach which first classifies sentences into different types, then performs sentiment analysis separately on sentences from each type, which shows that sentence type classification can improve the performance of sentence-level sentiment analysis.
NRC-Canada-2014: Detecting Aspects and Sentiment in Customer Reviews
709 Citations2014Svetlana Kiritchenko, Xiaodan Zhu +2 more
Submissions to SemEval-2014 stood first in detecting aspect categories, first in detects sentiment towards aspects categories, third in detecting aspects terms, and first and second in detecting sentiment towards aspect terms in the laptop and restaurant domains, respectively.
IEEE Intelligent SystemsDeep Learning-Based Document Modeling for Personality Detection from Text
665 Citations2017Navonil Majumder, Soujanya Poria +2 more
Synthesis lectures on human language technologiesNeural Network Methods for Natural Language Processing
656 Citations2017Yoav Goldberg
This book focuses on the application of neural network models to natural language data, and introduces more specialized neural network architectures, including 1D convolutional neural networks, recurrent neural Networks, conditioned-generation models, and attention-based models.
Proceedings of the 2006 Conference on Empirical Methods in Natural Language Processing - EMNLP '06
650 Citations2006
The proceedings of the 11th Conference on Empirical Methods in Natural Language Processing are introduced, organized under the auspices of SIGDAT, the ACL Special Interest Group for linguistic data and corpus-based approaches to NLP.
Sentiment Analysis: Mining Opinions, Sentiments, and Emotions
630 Citations2015Bing Liu
Proceedings of the AAAI Conference on Artificial IntelligenceTargeted Aspect-Based Sentiment Analysis via Embedding Commonsense Knowledge into an Attentive LSTM
608 Citations2018Yukun Ma, Haiyun Peng +1 more
A novel solution to targeted aspect-based sentiment analysis, which tackles the challenges of both aspect- based sentiment analysis and targeted sentiment analysis by exploiting commonsense knowledge by augmenting the LSTM network with a hierarchical attention mechanism.
Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
578 Citations2015Kai Sheng Tai, Richard Socher +1 more
The Tree-LSTM is introduced, a generalization of LSTMs to tree-structured network topologies that outperform all existing systems and strong LSTM baselines on two tasks: predicting the semantic relatedness of two sentences and sentiment classification.
Expert Systems with ApplicationsEnhancing deep learning sentiment analysis with ensemble techniques in social applications
560 Citations2017Óscar Araque, Ignacio Corcuera-Platas +2 more
arXiv (Cornell University)Effective LSTMs for Target-Dependent Sentiment Classification
559 Citations2015Duyu Tang, Bing Qin +2 more
ACM Computing SurveysLike It or Not
542 Citations2016Anastasia Giachanou, Fábio Crestani
Fields related to sentiment analysis in Twitter including Twitter opinion retrieval, tracking sentiments over time, irony detection, emotion detection, and tweet sentiment quantification, tasks that have recently attracted increasing attention are discussed.
Foundations and Trends® in Machine LearningAn Introduction to Conditional Random Fields
529 Citations2012Charles Sutton
Fine-grained Opinion Mining with Recurrent Neural Networks and Word Embeddings
497 Citations2015Pengfei Liu, Shafiq Joty +1 more
This work proposes a general class of discriminative models based on recurrent neural networks and word embeddings that can be successfully applied to fine-grained opinion mining tasks without any taskspecific feature engineering effort.
Studies in fuzziness and soft computingNeural Probabilistic Language Models
491 Citations2006Yoshua Bengio, Holger Schwenk +3 more
This work proposes to fight the curse of dimensionality by learning a distributed representation for words which allows each training sentence to inform the model about an exponential number of semantically neighboring sentences, and incorporates this new language model into a state-of-the-art speech recognizer of conversational speech.
Proceedings of the AAAI Conference on Artificial IntelligenceCoupled Multi-Layer Attentions for Co-Extraction of Aspect and Opinion Terms
440 Citations2017Wenya Wang, Sinno Jialin Pan +2 more
A novel deep learning model, named coupled multi-layer attentions, where each layer consists of a couple of attentions with tensor operators that are learned interactively to dually propagate information between aspect terms and opinion terms.
TTS synthesis with bidirectional LSTM based recurrent neural networks
439 Citations2014Yuchen Fan, Yao Qian +2 more
Recurrent Neural Networks (RNNs) with Bidirectional Long Short Term Memory (BLSTM) cells are adopted to capture the correlation or co-occurrence information between any two instants in a speech utterance for parametric TTS synthesis.
IEEE Intelligent SystemsSentiment Analysis Is a Big Suitcase
417 Citations2017Erik Cambria, Soujanya Poria +2 more
The authors argue that there are (at least) 15 NLP problems that need to be solved to achieve human-like performance in sentiment analysis, and address the composite nature of the problem via a three-layer structure inspired by the “jumping NLP curves” paradigm.
Opinion Mining with Deep Recurrent Neural Networks
386 Citations2014Ozan İrsoy, Claire Cardie
This approach outperforms previous CRF-based baselines, including the state-of-the-art semi-Markov CRF model, and does so without access to the powerful opinion lexicons and syntactic features relied upon by the semi-CRF, as well as without the standard layer-by-layer pre-training typically required of RNN architectures.
Deep Active Learning for Named Entity Recognition
368 Citations2017Yanyao Shen, Hyokun Yun +3 more
By combining deep learning with active learning, the authors can outperform classical methods even with a significantly smaller amount of training data, and this work shows otherwise.
IEEE Transactions on Knowledge and Data EngineeringSentiment Embeddings with Applications to Sentiment Analysis
335 Citations2015Duyu Tang, Furu Wei +4 more
This work develops a number of neural networks with tailoring loss functions, and applies sentiment embeddings to word-level sentiment analysis, sentence level sentiment classification, and building sentiment lexicons, showing results that consistently outperform context-basedembeddings on several benchmark datasets of these tasks.
Latent aspect rating analysis without aspect keyword supervision
334 Citations2011Hongning Wang, Yue Lu +1 more
A unified generative model is proposed for LARA, which does not need pre-specified aspect keywords and simultaneously mines 1) latent topical aspects, 2) ratings on each identified aspect, and 3) weights placed on different aspects by a reviewer.
Journal of Computational ScienceDeep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews
333 Citations2017Mohammad AL-Smadi, Omar Qawasmeh +3 more
The state-of-the-art approaches based on supervised machine learning are presented to address the challenges of aspect-based sentiment analysis (ABSA) of Arabic Hotels’ reviews and the SVM approach outperforms the other deep RNN approach in the research investigated tasks.
Proceedings of the AAAI Conference on Artificial IntelligenceGated Neural Networks for Targeted Sentiment Analysis
313 Citations2016Meishan Zhang, Yue Zhang +1 more
A sentence-level neural model is proposed to address the limitation of pooling functions, which do not explicitly model tweet-level semantics and gives significantly higher accuracies compared to the current best method for targeted sentiment analysis.
World Wide WebAspect term extraction for sentiment analysis in large movie reviews using Gini Index feature selection method and SVM classifier
310 Citations2016Asha S Manek, P. Deepa Shenoy +2 more
A Gini Index based feature selection method with Support Vector Machine (SVM) classifier is proposed for sentiment classification for large movie review data set and the results show that the Gini index method has better classification performance in terms of reduced error rate and accuracy.
International Conference on Artificial IntelligenceTarget-dependent twitter sentiment classification with rich automatic features
307 Citations2015Duy-Tin Vo, Yue Zhang
This paper shows that competitive results can be achieved without the use of syntax, by extracting a rich set of automatic features from a tweet, using distributed word representations and neural pooling functions to extract features.
PhraseRNN: Phrase Recursive Neural Network for Aspect-based Sentiment Analysis
265 Citations2015Thien Hai Nguyen, Kiyoaki Shirai
A new method is presented that takes both dependency and constituent trees of a sentence into account and significantly outperforms previous methods to identify sentiment of an aspect of an entity.
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
234 Citations2015Ojha, Atul Kr., Doğruöz, A. Seza +4 more
DCU: Aspect-based Polarity Classification for SemEval Task 4
229 Citations2014Joachim Wagner, Piyush Arora +5 more
The DCU team submitted one constrained run for the restaurant domain and one for the laptop domain for sub-task B (aspect term polarity prediction), ranking highest out of 36 systems on the restaurant test set and joint highest on the laptop test set.
Artificial Intelligence ReviewAspect extraction in sentiment analysis: comparative analysis and survey
200 Citations2016Toqir A. Rana, Yu–N Cheah
A comprehensive comparative analysis is conducted among different approaches of aspect extraction, which not only elaborates the performance of any technique but also guides the reader to compare the accuracy with other state-of-the-art and most recent approaches.
arXiv (Cornell University)Multi-Task Cross-Lingual Sequence Tagging from Scratch
197 Citations2016Zhilin Yang, Ruslan Salakhutdinov +1 more
A deep hierarchical recurrent neural network for sequence tagging that employs deep gated recurrent units on both character and word levels to encode morphology and context information, and applies a conditional random field layer to predict the tags.
Cognitive ComputationA Review of Sentiment Analysis Research in Chinese Language
189 Citations2017Haiyun Peng, Erik Cambria +1 more
It is proposed that a more human-like (cognitive) representation of Chinese concepts and their inter-connections could overcome the scarceness of available resources and improve the state of the art of Chinese sentiment analysis.
Artificial Intelligence ReviewMultilingual sentiment analysis: from formal to informal and scarce resource languages
188 Citations2016Siaw Ling Lo, Erik Cambria +2 more
This paper reviews the various current approaches and tools used for multilingual sentiment analysis, identifies challenges along this line of research, and provides several recommendations including a framework that is particularly applicable for dealing with scarce resource languages.
Knowledge-Based SystemsFeature selection and ensemble construction: A two-step method for aspect based sentiment analysis
182 Citations2017Md Shad Akhtar, Deepak Gupta +2 more
A cascaded framework of feature selection and classifier ensemble using particle swarm optimization (PSO) for aspect based sentiment analysis using three classifiers, namely Maximum Entropy, Conditional Random Field and Support Vector Machine are presented.
IEEE Transactions on Knowledge and Data EngineeringWeakly-Supervised Deep Embedding for Product Review Sentiment Analysis
179 Citations2017Wei Zhao, Ziyu Guan +5 more
A novel deep learning framework for product review sentiment classification which employs prevalently available ratings as weak supervision signals and explores two kinds of low level network structure for modeling review sentences, namely, convolutional feature extractors and long short-term memory.
Deep Learning approach for sentiment analysis of short texts
173 Citations2017Abdalraouf Hassan, Ausif Mahmood
Empirical results show that ConvLstm achieved comparable performances with less parameters on sentiment analysis tasks, and exploit LSTM as a substitute of pooling layer in CNN to reduce the loss of detailed local information and capture long term dependencies in sequence of sentences.
Knowledge-Based SystemsLearning multi-grained aspect target sequence for Chinese sentiment analysis
162 Citations2018Haiyun Peng, Yukun Ma +2 more
This paper formalizes the problem of aspect-level sentiment analysis from a different perspective, i.e., that sentiment at aspect target level should be the main focus and proposes to explicitly model the aspect target and conduct sentiment classification directly at the aspect targets level via three granularities.
Applied IntelligenceHybrid sentiment classification on twitter aspect-based sentiment analysis
162 Citations2017Nurulhuda Zainuddin, Ali Selamat +1 more
This research took into account the use of an aspect-based sentiment analysis on Twitter in order to perform a finer-grained analysis and showed that the new hybrid sentiment classification was able to improve the accuracy performance from the existing baseline sentiment classification methods.
IEEE Computational Intelligence MagazineSentiment Data Flow Analysis by Means of Dynamic Linguistic Patterns
160 Citations2015Soujanya Poria, Erik Cambria +3 more
An algorithm that assigns contextual polarity to concepts in text and flows this polarity through the dependency arcs in order to assign a final polarity label to each sentence is presented, which enables a more efficient transformation of unstructured social data into structured information, readily interpretable by machines.
WWW'18 Open Challenge
159 Citations2018Macedo Maia, Siegfried Handschuh +5 more
This challenge focuses on advancing the state-of-the-art of aspect-based sentiment analysis and opinion-based Question Answering for the financial domain.
Expert Systems with ApplicationsUnsupervised method for sentiment analysis in online texts
157 Citations2016Milagros Fernández‐Gavilanes, Tamara Álvarez-López +3 more
This work proposes a novel approach to predicting sentiment in online textual messages such as tweets and reviews, based on an unsupervised dependency parsing-based text classification method that leverages a variety of natural language processing techniques and sentiment features primarily derived from sentiment lexicons.
Learning Word Vectors for 157 Languages
157 Citations2018Édouard Grave, Piotr Bojanowski +3 more
This paper describes how high quality word representations for 157 languages were trained on the free online encyclopedia Wikipedia and data from the common crawl project, and introduces three new word analogy datasets to evaluate these word vectors.
Sentic LDA: Improving on LDA with semantic similarity for aspect-based sentiment analysis
156 Citations2016Soujanya Poria, Iti Chaturvedi +2 more
Sentic LDA exploits common-sense reasoning to shift LDA clustering from a syntactic to a semantic level and leverages on the semantics associated with words and multi-word expressions to improve clustering and, hence, outperform state-of-the-art techniques for aspect extraction.
TUbilio (Technical University of Darmstadt)Sentence and Expression Level Annotation of Opinions in User-Generated Discourse
149 Citations2010Cigdem Toprak, Niklas Jakob +1 more
A corpus of consumer reviews from the rateitall and the eopinions websites annotated with opinion-related information is introduced and a two-level annotation scheme is presented for pinpointing the properties and functional components of the evaluations.
DLIREC: Aspect Term Extraction and Term Polarity Classification System
147 Citations2014Zhiqiang Toh, Meng Wan
This paper describes the system used in the Aspect Based Sentiment Analysis Task 4 at the SemEval-2014, which consists of a Conditional Random Field based classifier for Aspect Term Extraction (ATE) and a linear classifiers for Aspects Term Polarity Classification (ATP).
Aspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network
145 Citations2017Jiajun Cheng, Shenglin Zhao +4 more
A HiErarchical ATtention (HEAT) network for aspect-level sentiment classification is proposed, which better allocates appropriate sentiment expressions for a given aspect benefiting from the guidance of aspect terms.
International Conference on Computational LinguisticsA Hybrid Deep Learning Architecture for Sentiment Analysis
130 Citations2016Shad Akhtar, Ayush Kumar +2 more
A novel hybrid deep learning archtecture which is highly efficient for sentiment analysis in resource-poor languages such as Hindi and often outperforms the state-of-art systems is proposed.
Language and Linguistics CompassDeep learning for sentiment analysis
129 Citations2016Lina M. Rojas-Barahona
An overview of deep learning for sentiment analysis is provided in order to place these approaches in context.
arXiv (Cornell University)Interactive Attention Networks for Aspect-Level Sentiment Classification
126 Citations2017Dehong Ma, Sujian Li +2 more
Proceedings of the AAAI Conference on Artificial IntelligenceRecurrent Neural Networks with Auxiliary Labels for Cross-Domain Opinion Target Extraction
120 Citations2017Ying Ding, Jianfei Yu +1 more
This work uses rule-based unsupervised methods to create auxiliary labels and use neural network models to learn a hidden representation that works well for different domains and finds that it can outperform a number of strong baselines with a large margin.
Dyadic Memory Networks for Aspect-based Sentiment Analysis
119 Citations2017Yi Tay, Luu Anh Tuan +1 more
This paper proposes Dyadic Memory Networks (DyMemNN), a novel extension of end-to-end memory networks for aspect-based sentiment analysis (ABSA) that achieves the state-of-the-art performance and outperform many neural architectures across six benchmark datasets.
NLANGP at SemEval-2016 Task 5: Improving Aspect Based Sentiment Analysis using Neural Network Features
118 Citations2016Zhiqiang Toh, Jian Su
This system consists of binary classifiers trained using single layer feedforward network for aspect category classification, and sequential labeling classifiers for opinion target extraction, which achieves the best performances on the English datasets.
IEEE Transactions on Affective ComputingA Neural Word Embeddings Approach for Multi-Domain Sentiment Analysis
112 Citations2017Mauro Dragoni, Giulio Petrucci
An approach exploiting the linguistic overlap between domains to build sentiment models supporting polarity inference for documents belonging to every domain is presented.
Information SciencesJoint multi-grain topic sentiment: modeling semantic aspects for online reviews
98 Citations2016Md. Hijbul Alam, Woo-Jong Ryu +1 more
This work proposes a domain-independent topic sentiment model called Joint Multi-grain Topic Sentiment (JMTS) to extract semantic aspects and confirms that JMTS generates semantic aspects with correlated top words and outperforms state-of-the-art models in several performance metrics.
arXiv (Cornell University)Aspect Level Sentiment Classification with Deep Memory Network
82 Citations2016Duyu Tang, Bing Qin +1 more
Social Network Analysis and MiningSuccesses and challenges of Arabic sentiment analysis research: a literature review
77 Citations2017Mazen El-Masri, Nabeela Altrabsheh +1 more
A comprehensive review of Arabic sentiment analysis is conducted, the pros and cons of the different approaches used and the relevant gaps in the literature are outlined, and recommendations for future Arabic sentimentAnalysis research are suggested.
Journal of Healthcare EngineeringCombination of Deep Recurrent Neural Networks and Conditional Random Fields for Extracting Adverse Drug Reactions from User Reviews
69 Citations2017Elena Tutubalina, Sergey Nikolenko
A novel model is proposed, uniting recurrent neural architectures and conditional random fields for identifying adverse drug reactions in free-form text, showing improvements over state-of-the-art methods of ADR extraction.
NLANGP: Supervised Machine Learning System for Aspect Category Classification and Opinion Target Extraction
66 Citations2015Zhiqiang Toh, Jian Su
This paper describes the system used in the Aspect Based Sentiment Analysis Task 12 of SemEval-2015, based on two supervised machine learning algorithms: sigmoidal feedforward network to train binary classifiers for aspect category classification, and Conditional Random Fields to train classifier for opinion target extraction.
arXiv (Cornell University)SentiHood: Targeted Aspect Based Sentiment Analysis Dataset for Urban Neighbourhoods
66 Citations2016Marzieh Saeidi, Guillaume Bouchard +2 more
Soft ComputingSentiment analysis of movie reviews: finding most important movie aspects using driving factors
62 Citations2015Viraj Parkhe, Bhaskar Biswas
This work focuses on finding the aspects of a movie review which direct its polarity the most using certain driving factors, which are scores given to the various movie aspects.
Knowledge-Based SystemsNovel Privacy-preserving algorithm based on frequent path for trajectory data publishing
62 Citations2018Yulan Dong, Dechang Pi
TOPF aims to achieve better quality of trajectory data for publishing and strike a balance between the conflicting goals of data usability and data privacy, and is the first paper that uses frequent path to preserve data privacy.
XRCE at SemEval-2016 Task 5: Feedbacked Ensemble Modeling on Syntactico-Semantic Knowledge for Aspect Based Sentiment Analysis
58 Citations2016Caroline Brun, Julien Pérez +1 more
The different components of the system are described, based on composite models combining sophisticated linguistic features with Machine Learning algorithms, which implies opinion target expression detection, aspect category and polarity classification.
TDParse: Multi-target-specific sentiment recognition on Twitter
58 Citations2017Bo Wang, Maria Liakata +2 more
This work develops a method for multi-target specific sentiment recognition, which is developed by using the context around a target as well as syntactic dependencies involving the target to develop state-of-the art performance in both corpora and deep learning models for single-target sentiment.
Lecture notes in computer scienceDependency-Tree Based Convolutional Neural Networks for Aspect Term Extraction
58 Citations2017Hai Ye, Zichao Yan +2 more
This work proposes a novel dependency-tree based convolutional stacked neural network (DTBCSNN) for aspect term extraction, in which tree-based convolution is introduced over sentences’ dependency parse trees to capture syntactic features.
IIT-TUDA at SemEval-2016 Task 5: Beyond Sentiment Lexicon: Combining Domain Dependency and Distributional Semantics Features for Aspect Based Sentiment Analysis
57 Citations2016Ayush Kumar, Sarah Kohail +3 more
arXiv (Cornell University)Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis
57 Citations2016Wenya Wang, Sinno Jialin Pan +2 more
Future Generation Computer SystemsFeature-based Compositing Memory Networks for Aspect-based Sentiment Classification in Social Internet of Things
55 Citations2017Ruixin Ma, Kai Wang +4 more
A new memory network model, called Feature-based Compositing Memory Networks (FCMN), which extracts three kinds of features to enrich the word representation of each context word and design compositing strategies combining feature representations and word embedding to improve the performance of attention mechanism.
Aspect-based Opinion Summarization with Convolutional Neural Networks
55 Citations2016Haibing Wu, Yiwei Gu +2 more
Experimental results show that both cascaded and multitasks CNNs with pre-trained word embedding outperform linear classifiers, and multitask CNN generally performs better than cascaded CNN.
…