A Survey on Opinion Mining: From Stance to Product Aspect
IEEE AccessPublished 1 January 2019Open access
Rui Wang, Deyu Zhou, Mingmin Jiang, Jiasheng Si, Yang Yang
Citations73
SJR quartileQ1
SJR score0.85
SNIP1.50
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
The general framework of opinion mining is introduced and the evaluation metrics are described, and the methodologies for stance detection on different sources, such as online forum and social media are discussed.
Abstract
With the prevalence of social media and online forum, opinion mining, aiming at analyzing and discovering the latent opinion in user-generated reviews on the Internet, has become a hot research topic. This survey focuses on two important subtasks in this field, stance detection and product aspect mining, both of which can be formalized as the problem of the triple (target, aspect, opinion) extraction. In this paper, we first introduce the general framework of opinion mining and describe the evaluation metrics. Then, the methodologies for stance detection on different sources, such as online forum and social media are discussed. After that, approaches for product aspect mining are categorized into three main groups which are corpus level aspect extraction, corpus level aspect, and opinion mining, and document level aspect and opinion mining based on the processing units and tasks. And then we discuss the challenges and possible solutions. Finally, we summarize the evolving trend of the reviewed methodologies and conclude the survey.
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.
DROPS (Schloss Dagstuhl – Leibniz Center for Informatics)AI-Assisted Pipeline for Dynamic Generation of Trustworthy Health Supplement Content at Scale
45,681 Citations2018Kefallinos, Dionysios, Alexandris, Georgios +6 more
arXiv (Cornell University)Efficient Estimation of Word Representations in Vector Space
18,050 Citations2013Tomáš Mikolov, Kai Chen +2 more
Two novel model architectures for computing continuous vector representations of words from very large data sets are proposed and it is shown that these vectors provide state-of-the-art performance on the authors' test set for measuring syntactic and semantic word similarities.
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.
ACM SIGMOD RecordMining frequent patterns without candidate generation
6,360 Citations2000Jiawei Han, Jian Pei +1 more
Foundations and Trends® in Information RetrievalOpinion Mining and Sentiment Analysis
6,204 Citations2008Bo Pang, Lillian Lee
This survey covers techniques and approaches that promise to directly enable opinion-oriented information-seeking systems and focuses on methods that seek to address the new challenges raised by sentiment-aware applications, as compared to those that are already present in more traditional fact-based analysis.
Recurrent neural network based language model
5,349 Citations2010Tomáš Mikolov, Martin Karafiát +3 more
Results indicate that it is possible to obtain around 50% reduction of perplexity by using mixture of several RNN LMs, compared to a state of the art backoff language model.
A Convolutional Neural Network for Modelling Sentences
3,561 Citations2014Nal Kalchbrenner, Edward Grefenstette +1 more
A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Recognizing contextual polarity in phrase-level sentiment analysis
3,379 Citations2005Theresa Wilson, Janyce Wiebe +1 more
A new approach to phrase-level sentiment analysis is presented that first determines whether an expression is neutral or polar and then disambiguates the polarity of the polar expressions.
Synthesis lectures on human language technologiesSentiment Analysis and Opinion Mining
3,241 Citations2012Bing Liu
This book is a comprehensive introductory and survey text that covers all important topics and the latest developments in the field with over 400 references and is suitable for students, researchers and practitioners who are interested in social media analysis in general and sentiment analysis in particular.
Ain Shams Engineering JournalSentiment analysis algorithms and applications: A survey
3,211 Citations2014Walaa Medhat, Ahmed H. Yousef +1 more
This survey paper tackles a comprehensive overview of the last update in this field of sentiment analysis with sophisticated categorizations of a large number of recent articles and the illustration of the recent trend of research in the sentiment analysis and its related areas.
SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining.
2,652 Citations2010Stefano Baccianella, Andrea Esuli +1 more
This work discusses SENTIWORDNET 3.0, a lexical resource explicitly devised for supporting sentiment classification and opinion mining applications, and reports on the improvements concerning aspect (b) that it embodies with respect to version 1.0.
Generating Typed Dependency Parses from Phrase Structure Parses
2,304 Citations2006Marie-Catherine de Marneffe, Bill MacCartney +1 more
A system for extracting typed dependency parses of English sentences from phrase structure parses that captures inherent relations occurring in corpus texts that can be critical in real-world applications is described.
Biographies, Bollywood, Boom-boxes and Blenders: Domain Adaptation for Sentiment Classification
2,026 Citations2007John Blitzer, Mark Dredze +1 more
This work extends to sentiment classification the recently-proposed structural correspondence learning (SCL) algorithm, reducing the relative error due to adaptation between domains by an average of 30% over the original SCL algorithm and 46% over a supervised baseline.
Journal of the American Statistical AssociationObjective Criteria for the Evaluation of Clustering Methods
1,841 Citations1971William Rand
Opinion observer
1,604 Citations2005Bing Liu, Minqing Hu +1 more
A novel framework for analyzing and comparing consumer opinions of competing products is proposed, and a new technique based on language pattern mining is proposed to extract product features from Pros and Cons in a particular type of reviews.
A Survey of Opinion Mining and Sentiment Analysis
1,331 Citations2012Bing Liu, Lei Zhang
Sentiment analysis or opinion mining is the computational study of people’s opinions, appraisals, attitudes, and emotions toward entities, individuals, issues, events, topics and their attributes.
Mining opinion features in customer reviews
1,273 Citations2004Minqing Hu, Bing Liu
This project aims to summarize all the customer reviews of a product by mining opinion/product features that the reviewers have commented on and a number of techniques are presented to mine such features.
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.
Joint sentiment/topic model for sentiment analysis
972 Citations2009Chenghua Lin, Yulan He
A novel probabilistic modeling framework based on Latent Dirichlet Allocation (LDA), called joint sentiment/topic model (JST), which detects sentiment and topic simultaneously from text is proposed, which is fully unsupervised.
Neural Information Processing SystemsHierarchical Topic Models and the Nested Chinese Restaurant Process
938 Citations2003Thomas L. Griffiths, Michael I. Jordan +2 more
A Bayesian approach is taken to generate an appropriate prior via a distribution on partitions that allows arbitrarily large branching factors and readily accommodates growing data collections.
NPARCEmotions Evoked by Common Words and Phrases: Using Mechanical Turk to Create an Emotion Lexicon
873 Citations2010Saif M. Mohammad, Peter D. Turney
This paper shows how to create a high-quality, moderate-sized emotion lexicon using Mechanical Turk, and identifies which emotions tend to be evoked simultaneously by the same term and shows that certain emotions indeed go hand in hand.
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.
Modeling online reviews with multi-grain topic models
792 Citations2008Ivan Titov, Ryan McDonald
This paper presents a novel framework for extracting ratable aspects of objects from online user reviews and argues that multi-grain models are more appropriate for this task since standard models tend to produce topics that correspond to global properties of objects rather than aspects of an object that tend to be rated by a user.
Aspect and sentiment unification model for online review analysis
772 Citations2011Yohan Jo, Alice Oh
This paper proposes Sentence-LDA and extends it to Aspect and Sentiment Unification Model (ASUM), which incorporates aspect and sentiment together to model sentiments toward different aspects and shows that ASUM outperforms other generative models and comes close to supervised classification methods.
Journal of the ACMThe nested chinese restaurant process and bayesian nonparametric inference of topic hierarchies
667 Citations2010David M. Blei, Thomas L. Griffiths +1 more
An application to information retrieval in which documents are modeled as paths down a random tree, and the preferential attachment dynamics of the nCRP leads to clustering of documents according to sharing of topics at multiple levels of abstraction.
Latent aspect rating analysis on review text data
659 Citations2010Hongning Wang, Yue Lu +1 more
Empirical experiments show that the proposed latent rating regression model can effectively solve the problem of LARA, and that the detailed analysis of opinions at the level of topical aspects enabled by the proposed model can support a wide range of application tasks, such as aspect opinion summarization, entity ranking based on aspect ratings, and analysis of reviewers rating behavior.
A Joint Model of Text and Aspect Ratings for Sentiment Summarization
638 Citations2008Ivan Titov, Ryan McDonald
A statistical model is proposed which is able to discover corresponding topics in text and extract textual evidence from reviews supporting each of these aspect ratings, a fundamental problem in aspect-based sentiment summarization.
Lecture notes in computer scienceSemantic Sentiment Analysis of Twitter
516 Citations2012Hassan Saif, Yulan He +1 more
This paper introduces a novel approach of adding semantics as additional features into the training set for sentiment analysis by adding its semantic concept from tweets as an additional feature, and measures the correlation of the representative concept with negative/positive sentiment.
An Unsupervised Aspect-Sentiment Model for Online Reviews
507 Citations2010Samuel Brody, Noémie Elhadad
An unsuper-vised system for extracting aspects and determining sentiment in review text is presented, which is simple and flexible with regard to domain and language, and takes into account the influence of aspect on sentiment polarity.
Proceedings of the 17th international conference on Computational linguistics -The Berkeley FrameNet Project
500 Citations1998Collin F. Baker, Charles J. Fillmore +1 more
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.
Get out the vote
497 Citations2006Matt Thomas, Bo Pang +1 more
It is found that the incorporation of sources of information regarding relationships between discourse segments, such as whether a given utterance indicates agreement with the opinion expressed by another, yields substantial improvements over classifying speeches in isolation.
Extracting Product Features and Opinions from Reviews
490 Citations2007Ana-Maria Popescu, Orena Etzioni
TUbilio (Technical University of Darmstadt)Extracting Opinion Targets in a Single and Cross-Domain Setting with Conditional Random Fields
480 Citations2010Niklas Jakob, Iryna Gurevych
This paper model the problem as an information extraction task, which is addressed based on Conditional Random Fields (CRF), and employs the supervised algorithm by Zhuang et al. (2006), which represents the state-of-the-art on the employed data.
Expert Systems with ApplicationsA survey on sentiment detection of reviews
478 Citations2009Huifeng Tang, Songbo Tan +1 more
This survey discusses related issues and main approaches to these problems, namely, subjectivity classification, word sentiment classification, document sentiment classification and opinion extraction.
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.
ACM Transactions on Internet TechnologyStance and Sentiment in Tweets
435 Citations2017Saif M. Mohammad, Parinaz Sobhani +1 more
It is shown that although knowing the sentiment expressed by a tweet is beneficial for stance classification, it alone is not sufficient and additional unlabeled data is used through distant supervision techniques and word embeddings to further improve stance classification.
An Unsupervised Neural Attention Model for Aspect Extraction
428 Citations2017Ruidan He, Wee Sun Lee +2 more
A novel neural approach that improves coherence by exploiting the distribution of word co-occurrences through the use of neural word embeddings, and uses an attention mechanism to de-emphasize irrelevant words during training, further improving the coherence of aspects.
Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis
422 Citations2016Wenya Wang, Sinno Jialin Pan +2 more
A novel joint model that integrates recursive neural networks and conditional random fields into a unified framework for explicit aspect and opinion terms co-extraction and is flexible to incorporate hand-crafted features into the proposed model to further boost its information extraction performance.
Singapore Management University Institutional Knowledge (InK) (Singapore Management University)Jointly Modeling Aspects and Opinions with a MaxEnt-LDA Hybrid
414 Citations2010Xin Zhao, Jing Jiang +2 more
This paper proposes a MaxEnt-LDA hybrid model to jointly discover both aspects and aspect-specific opinion words and shows that with a relatively small amount of training data, this model can effectively identify aspect and opinion words simultaneously.
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
413 Citations2018Hu Xu, Bing Liu +2 more
This paper is the first to report such double embeddings based CNN model for aspect extraction and achieve very good results, outperforming state-of-the-art sophisticated existing methods.
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.
Decision Support SystemsWhose and what chatter matters? The effect of tweets on movie sales
367 Citations2013Huaxia Rui, Yizao Liu +1 more
The study investigates whether and how Twitter WOM affects movie sales by estimating a dynamic panel data model using publicly available data and well-known machine learning algorithms and reveals the potential values of monitoring people's intentions and sentiments on Twitter and identifying influential users for companies wishing to harness the power of social broadcasting networks.
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.
Recognizing Stances in Ideological On-Line Debates
307 Citations2010Swapna Somasundaran, Janyce Wiebe
This work constructs an arguing lexicon automatically from a manually annotated corpus and builds supervised systems employing sentiment and arguing opinions and their targets as features, which perform substantially better than a distribution-based baseline.
Structure-Aware Review Mining and Summarization
284 Citations2010Fangtao Li, Chao Han +5 more
This paper proposes a new machine learning framework based on Conditional Random Fields that can employ rich features to jointly extract positive opinions, negative opinions and object features for review sentences and shows that structure-aware models outperform many state-of-the-art approaches to review mining.
Aspect Term Extraction with History Attention and Selective Transformation
282 Citations2018Xin Li, Lidong Bing +3 more
Experimental results over four benchmark datasets clearly demonstrate that the new framework for tackling ATE can outperform all state-of-the-art methods.
OpinionMiner
267 Citations2009Wei Jin, Hung Hay Ho +1 more
The OpinionMiner system designed in this work aims to mine customer reviews of a product and extract high detailed product entities on which reviewers express their opinions.
Extracting and Ranking Product Features in Opinion Documents
267 Citations2010Lei Zhang, Bing Liu +2 more
The problem is formulated as a bipartite graph and the well-known web page ranking algorithm HITS is used to find important features and rank them high and demonstrates promising results on diverse real-life datasets.
Expert Systems with ApplicationsReview-based measurement of customer satisfaction in mobile service: Sentiment analysis and VIKOR approach
266 Citations2013Daekook Kang, Yongtae Park
A new framework for measurement of customer satisfaction for mobile services by combining VIKOR (in Serbian: ViseKriterijumsa Optimizacija I Kompromisno Resenje) and sentiment analysis is developed, which believes that the proposed customer-review-based approach not only saves time and effort in measuring customer satisfaction, but also captures the real voices of customers.
National University of SingaporeAspect Ranking: Identifying Important Product Aspects from Online Consumer Reviews
236 Citations2011Jianxing Yu, Zheng-Jun Zha +2 more
This paper develops an aspect ranking algorithm, which aims to automatically identify important product aspects from online consumer reviews by simultaneously considering the aspect frequency and the influence of consumers' opinions given to each aspect on their overall opinions.
Red Opal
235 Citations2007Christopher Scaffidi, Kevin Bierhoff +4 more
A new search system called Red Opal is presented that enables users to locate products rapidly based on features, and which products to show when a user specifies a desired product feature.
Journal of the American Society for Information Science and TechnologyMining opinions from the Web: Beyond relevance retrieval
207 Citations2007Lun‐Wei Ku, Hsin‐Hsi Chen
To demonstrate and evaluate the proposed opinion mining algorithms, news and bloggers' articles are adopted and positive and negative sentiment words and their weights are mined on the basis of Chinese word structures.
ILDA
202 Citations2011Samaneh Moghaddam, Martin Ester
This paper introduces Interdependent Latent Dirichlet Allocation (ILDA) model, a probabilistic graphical models which aim to extract aspects and corresponding ratings of products from online reviews and conducts experiments on a real life dataset, Epinions.com.
Opinion digger
194 Citations2010Samaneh Moghaddam, Martin Ester
An unsupervised method is proposed, called Opinion Digger, which extracts important aspects of a product and determines the overall consumer's satisfaction for each, by estimating a rating in the range from 1 to 5, and is demonstrated on a real life dataset that was crawled from Epinions.com.
Summarizing Opinions: Aspect Extraction Meets Sentiment Prediction and They Are Both Weakly Supervised
189 Citations2018Stefanos Angelidis, Mirella Lapata
An opinion summarization dataset is introduced that includes a training set of product reviews from six diverse domains and human-annotated development and test sets with gold standard aspect annotations, salience labels, and opinion summaries.
Lirias (KU Leuven)A short introduction to probabilistic soft logic
181 Citations2012Angelika Kimmig, Stephen H. Bach +3 more
This paper provides an overview of the PSL language and its techniques for inference and weight learning.
On the evaluation of document analysis components by recall, precision, and accuracy
181 Citations1999Markus Junker, Rainer Hoch +1 more
It is argued that the experimental evaluation on relative small test sets-as is very common in document analysis has to be taken with extreme care from a statistical point of view.
Decision Support SystemsDeriving market intelligence from microblogs
180 Citations2013Yung-Ming Li, Tsung‐Ying Li
It is found that the consideration of user credibility and opinion subjectivity is essential for aggregating microblog opinions and the proposed mechanism can effectively discover market intelligence (MI) for supporting decision-makers.
Lecture notes in computer scienceImplicit Feature Identification via Co-occurrence Association Rule Mining
176 Citations2011Zhen Hai, Kuiyu Chang +1 more
A novel two-phase co-occurrence association rule mining approach to identifying implicit features in reviews, which shows considerable improvements over other related methods including baseline dictionary lookups, statistical semantic association models, and bi-bipartite reinforcement clustering.
Meeting of the Association for Computational LinguisticsCats Rule and Dogs Drool!: Classifying Stance in Online Debate
176 Citations2011Pranav Anand, Marilyn Walker +4 more
The results suggest that methods that take into account the dialogic context of such posts might be fruitful, and demonstrate that the number of subjective expressions varies across debates, a fact correlated with the performance of systems sensitive to sentiment-bearing terms.
Stance Classification of Ideological Debates: Data, Models, Features, and Constraints
170 Citations2013Kazi Saidul Hasan, Vincent Ng
How the performance of a learning-based stance classification system varies with the amount and quality of the training data, the complexity of the underlying model, the richness of the feature set, as well as the application of extra-linguistic constraints is examined.
Stance Classification using Dialogic Properties of Persuasion
164 Citations2012Marilyn Walker, Pranav Anand +2 more
It is shown that representing the dialogic structure of the debates in terms of agreement relations between speakers, greatly improves performance for stance classification, over models that operate on post content and parent-post context alone.
Lecture notes in computer scienceMulti-facet Rating of Product Reviews
148 Citations2009Stefano Baccianella, Andrea Esuli +1 more
This work tackles the problem of rating (i.e., attributing a numerical score of satisfaction to) consumer reviews based on their textual content by exploring several aspects of the problem, with special emphasis on how to generate vectorial representations of the text by means of POS tagging, sentiment analysis, and feature selection for ordinal regression learning.
Support or Oppose? Classifying Positions in Online Debates from Reply Activities and Opinion Expressions
145 Citations2010Akiko Murakami, Rudy Raymond
It is shown that utilizing the textual content of the remarks into the link-based method can yield higher accuracy in the identification task.
Extracting Opinion Expressions with semi-Markov Conditional Random Fields
140 Citations2012Bishan Yang, Claire Cardie
This work extends the original semi-CRF model to allow the modeling of arbitrarily long expressions while accounting for their likely syntactic structure when modeling segment boundaries, and demonstrates that this approach outperforms state-of-the-art methods for both opinion expression tasks.
pkudblab at SemEval-2016 Task 6 : A Specific Convolutional Neural Network System for Effective Stance Detection
125 Citations2016Wei Wan, Xiao Zhang +3 more
A convolutional neural network for stance detection in tweets is developed and a ”vote scheme” for prediction instead of predicting when the accuracy of validation set reaches its maximum is designed.
Joint Models of Disagreement and Stance in Online Debate
123 Citations2015Dhanya Sridhar, James R. Foulds +3 more
This work comprehensively evaluates the possible modeling choices on eight topics across two online debate corpora and introduces a scalable unified probabilistic modeling framework for stance classification models that are collective, reason about disagreement, and can model stance at either the author level or at the post level.
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.
Lifelong Learning CRF for Supervised Aspect Extraction
118 Citations2017Lei Shu, Hu Xu +1 more
This paper shows that if the system has performed aspect extraction from many past domains and retained their results as knowledge, Conditional Random Fields (CRF) can leverage this knowledge in a lifelong learning manner to extract in a new domain markedly better than the traditional CRF without using this prior knowledge.
IEEE/ACM Transactions on Audio Speech and Language ProcessingGlobal Inference for Aspect and Opinion Terms Co-Extraction Based on Multi-Task Neural Networks
106 Citations2018Jianfei Yu, Jing Jiang +1 more
This work first applies a multi-task learning framework to implicitly capture the relations between the two tasks, and proposes a global inference method by explicitly modelling several syntactic constraints among aspect term extraction and opinion term extraction to uncover their intra-task and inter-task relationship.
Cross-Target Stance Classification with Self-Attention Networks
105 Citations2018Chang Xu, Cécile Paris +2 more
This work proposes a neural model that can apply what has been learned from a source target to a destination target, and shows that this model can find useful information shared between relevant targets which improves generalization in certain scenarios.
Exploiting Coherence for the Simultaneous Discovery of Latent Facets and associated Sentiments
105 Citations2011Himabindu Lakkaraju, Chiranjib Bhattacharyya +2 more
This work is the first attempt to combine the notions of syntactic and semantic dependencies in the domain of review mining by jointly discovering latent facets and sentiment topics, and also order the sentiment topics with respect to a multi-point scale, in a language and domain independent manner.
Decision Support SystemsThat is your evidence?: Classifying stance in online political debate
102 Citations2012Marilyn Walker, Pranav Anand +4 more
This work examines stance classification on a corpus of 4731 posts from the debate website ConvinceMe.net, for 14 topics ranging from the playful to the ideological, and suggests that features and methods that take into account the dialogic context of such posts improve accuracy.
International Conference on Computational LinguisticsStance Detection with Hierarchical Attention Network
94 Citations2018Qingying Sun, Zhongqing Wang +2 more
This work presents a neural model to fully employ various linguistic information to construct the document representation and proposes a hierarchical attention network to weigh the importance ofVarious linguistic information, and learn the mutual attention between the document and the linguistic information.
Recursive Neural Structural Correspondence Network for Cross-domain Aspect and Opinion Co-Extraction
85 Citations2018Wenya Wang, Sinno Jialin Pan
A novel recursive neural network is developed that could reduce domain shift effectively in word level through syntactic relations across domains to build structural correspondences and generate an auxiliary task to predict the relation between any two adjacent words in the dependency tree.
Collective Stance Classification of Posts in Online Debate Forums
80 Citations2014Dhanya Sridhar, Lise Getoor +1 more
A novel collective classification approach to stance classification is developed, which makes use of both structural and linguistic features, and which collectively labels the posts’ stance across a network of the users’ posts.
Expert Systems with ApplicationsEnriched LDA (ELDA): Combination of latent Dirichlet allocation with word co-occurrence analysis for aspect extraction
75 Citations2017Mohammadreza Shams, Ahmad Baraani-Dastjerdi
The experimental results indicate that ELDA not only outperforms the state-of-the-art alternatives in terms of topic coherence and precision, but also has no particular dependency on the written language and can be applied to all languages with reasonable accuracy.
International Conference on Computational LinguisticsThe Power of Negative Thinking: Exploiting Label Disagreement in the Min-cut Classification Framework
71 Citations2008Mohit Bansal, Claire Cardie +1 more
This work reports on work in progress that examines several novel heuristics that allow for the addition of label-disagreement information in a way that improves classification accuracy while preserving the efficiency guarantees of the minimum-cut framework.
Lecture notes in computer scienceConnecting Targets to Tweets: Semantic Attention-Based Model for Target-Specific Stance Detection
60 Citations2017Yiwei Zhou, Alexandra I. Cristea +1 more
A novel attention mechanism at the semantic level in the bi-directional GRU-CNN structure, which is more fine-grained than the existing token-level attention mechanism is proposed, which allows the model to automatically attend to useful semantic features of informative tokens in deciding the target-specific stance.
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.
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.
Decision Support SystemsSecondhand seller reputation in online markets: A text analytics framework
54 Citations2018Runyu Chen, Yitong Zheng +3 more
The main contribution of the research is the design of a text analytics framework to assess secondhand sellers' reputation and a new aspect-extraction method that combines the results of domain ontology and topic modeling to extract topical features from product descriptions.
Lecture notes in computer scienceAn Unsupervised Approach to Product Attribute Extraction
52 Citations2009Santosh Raju, Prasad Pingali +1 more
A new approach which is both unsupervised and domain independent to extract the attributes of products from text descriptions is proposed, able to achieve 92% precision and 62% recall in experiments.
TakeLab at SemEval-2016 Task 6: Stance Classification in Tweets Using a Genetic Algorithm Based Ensemble
50 Citations2016Martin Tutek, Ivan Sekulić +7 more
This paper describes the system for the detection of stances in tweets submitted to SemEval 2016 Task 6A, which ranked 3rd among the 19 systems submitted to this task.
Multi-Target Stance Detection via a Dynamic Memory-Augmented Network
49 Citations2018Penghui Wei, Junjie Lin +1 more
A dynamic memory-augmented network DMAN for multi-target stance detection that utilizes a shared external memory, which is dynamically updated through the learning process, to capture and store stance-indicative information for multiple related targets.
Weakly Supervised Tweet Stance Classification by Relational Bootstrapping
49 Citations2016Javid Ebrahimi, Dejing Dou +1 more
This work investigates collective classification of stances on Twitter, using hinge-loss Markov random fields (HL-MRFs) to constrain the predicted post labels and latent user labels to correspond with the network structure.
Lecture notes in computer scienceHierarchical Latent Tree Analysis for Topic Detection
48 Citations2014Tengfei Liu, Nevin L. Zhang +1 more
A new method for topic detection, where a topic is determined by identifying words that appear with high frequency in the topic and low frequency in other topics, is proposed using a hierarchy of discrete latent variables.
Aspect-based opinion mining from product reviews
46 Citations2012Samaneh Moghaddam, Martin Ester
This tutorial covers opinion mining in online product reviews with the focus on aspect-based opinion mining, a key task in the area of opinion mining and has attracted a lot of researchers in the information retrieval community recently.
USFD at SemEval-2016 Task 6: Any-Target Stance Detection on Twitter with Autoencoders
46 Citations2016Isabelle Augenstein, Andreas Vlachos +1 more
The University of Sheffield’s submission to the SemEval 2016 Twitter Stance Detection weakly supervised task is described, which uses a large set of unlabelled tweets containing all targets and a bag-of-words autoencoder to learn how to produce feature representations of tweets.
Twitter Stance Detection — A Subjectivity and Sentiment Polarity Inspired Two-Phase Approach
43 Citations2017Kuntal Dey, Ritvik Shrivastava +1 more
This paper addresses the problem of detecting the stance of given tweets, with respect to given topics, from user-generated text (tweets), using the SemEval 2016 stance detection task dataset and develops a two-phase feature-driven model.
Generalizing Syntactic Structures for Product Attribute Candidate Extraction
40 Citations2010Yanyan Zhao, Bing Qin +2 more
A novel approach is proposed by generalizing syntactic structures of the product attributes with two strategies: intuitive heuristics and syntactic structure similarity, which shows that the proposed approach is effective.
CU-GWU Perspective at SemEval-2016 Task 6: Ideological Stance Detection in Informal Text
39 Citations2016Heba Elfardy, Mona Diab
Lecture notes in computer scienceDetermining the Polarity and Source of Opinions Expressed in Political Debates
39 Citations2009Alexandra Balahur, Zornitsa Kozareva +1 more
This paper investigates different approaches developed in order to classify opinion and discover opinion sources from text, using affect, opinion and attitude lexicon, and proposes three methods to classify opinion at the speaker intervention level, showing improvements over the classification of individual text segments.
A Target-Guided Neural Memory Model for Stance Detection in Twitter
39 Citations2018Penghui Wei, Wenji Mao +1 more
An endto- end neural model, TGMN-CR, is proposed, which makes better use of target content information and outperforms the state-of-the-art alternative methods when a tweet does not explicitly express opinion about the given target.
Mining newsgroups using networks arising from social behavior
37 Citations2003Rakesh Agrawal, Sridhar Rajagopalan +2 more
…