Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels’ reviews
Journal of Computational SciencePublished 14 November 2017
Mohammad AL-Smadi, Omar Qawasmeh, Mahmoud Al‐Ayyoub, Yaser Jararweh, Brij B. Gupta
Citations333
SJR quartileQ2
SJR score0.70
SNIP1.21
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 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.
Abstract
International audience
Keywords
Computer ScienceDecision Sciences
Communications of the ACMImageNet classification with deep convolutional neural networks
75,709 Citations2017Alex Krizhevsky, Ilya Sutskever +1 more
A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
arXiv (Cornell University)Distributed Representations of Words and Phrases and their Compositionality
18,086 Citations2013Tomáš Mikolov, Ilya Sutskever +3 more
This paper presents a simple method for finding phrases in text, and shows that learning good vector representations for millions of phrases is possible and describes a simple alternative to the hierarchical softmax called negative sampling.
Transactions of the Association for Computational LinguisticsEnriching Word Vectors with Subword Information
9,784 Citations2017Piotr Bojanowski, Édouard Grave +2 more
A new approach based on the skipgram model, where each word is represented as a bag of character n-grams, with words being represented as the sum of these representations, which achieves state-of-the-art performance on word similarity and analogy tasks.
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.
Journal of Marketing ResearchThe Effect of Word of Mouth on Sales: Online Book Reviews
5,939 Citations2006Judith A. Chevalier, Dina Mayzlin
Software Framework for Topic Modelling with Large Corpora
3,806 Citations2010R Rehr Uv Rek, Petr Sojka
This work describes a Natural Language Processing software framework which is based on the idea of document streaming, i.e. processing corpora document after document, in a memory independent fashion, and implements several popular algorithms for topical inference, including Latent Semantic Analysis and Latent Dirichlet Allocation in a way that makes them completely independent of the training corpus size.
Encyclopedia of Machine Learning and Data MiningSentiment Analysis and Opinion Mining
3,319 Citations2017Lei Zhang, Bing Liu
Learning Word Vectors for Sentiment Analysis
3,299 Citations2011Andrew L. Maas, Raymond E. Daly +4 more
This work presents a model that uses a mix of unsupervised and supervised techniques to learn word vectors capturing semantic term--document information as well as rich sentiment content, and finds it out-performs several previously introduced methods for sentiment classification.
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.
Class-based n -gram models of natural language
2,893 Citations1992Peter F. Brown, P.V. deSouza +3 more
This work addresses the problem of predicting a word from previous words in a sample of text and discusses n-gram models based on classes of words, finding that these models are able to extract classes that have the flavor of either syntactically based groupings or semanticallybased groupings, depending on the nature of the underlying statistics.
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.
Discriminative training methods for hidden Markov models
1,889 Citations2002Michael Collins
Experimental results on part-of-speech tagging and base noun phrase chunking are given, in both cases showing improvements over results for a maximum-entropy tagger.
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.
Computers and the HumanitiesAnnotating Expressions of Opinions and Emotions in Language
1,770 Citations2005Janyce Wiebe, Theresa Wilson +1 more
The manual annotation process and the results of an inter-annotator agreement study on a 10,000-sentence corpus of articles drawn from the world press are presented.
Extracting product features and opinions from reviews
1,720 Citations2005Ana-Maria Popescu, Oren Etzioni
Opine is introduced, an unsupervised information-extraction system which mines reviews in order to build a model of important product features, their evaluation by reviewers, and their relative quality across products.
Domain adaptation for large-scale sentiment classification: A deep learning approach
1,563 Citations2011Xavier Glorot, Antoine Bordes +1 more
A deep learning approach is proposed which learns to extract a meaningful representation for each review in an unsupervised fashion and clearly outperform state-of-the-art methods on a benchmark composed of reviews of 4 types of Amazon products.
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.
IEEE Intelligent SystemsNew Avenues in Opinion Mining and Sentiment Analysis
1,222 Citations2013Erik Cambria, Björn W. Schuller +2 more
The history, current use, and future of opinion mining and sentiment analysis are discussed, along with relevant techniques and tools.
International Conference on Computational LinguisticsDeep Convolutional Neural Networks for Sentiment Analysis of Short Texts
1,191 Citations2014Cícero dos Santos, Maíra Gatti de Bayser
A new deep convolutional neural network is proposed that exploits from characterto sentence-level information to perform sentiment analysis of short texts and achieves state-of-the-art results for single sentence sentiment prediction.
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.
Journal of Artificial Intelligence ResearchSentiment Analysis of Short Informal Texts
890 Citations2014Svetlana Kiritchenko, Xiaodan Zhu +1 more
A state-of-the-art sentiment analysis system that detects (a) the sentiment of short informal textual messages such as tweets and SMS (message-level task) and (b) the Sentiment of a word or a phrase within a message (term- level task).
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.
arXiv (Cornell University)A new ANEW: Evaluation of a word list for sentiment analysis in microblogs
739 Citations2011Finn Årup Nielsen
This work wanted to examine how well ANEW and other word lists performs for the detection of sentiment strength in microblog posts in comparison with a new word list specifically constructed for microblogs.
Synthesis lectures on human language technologiesIntroduction to Arabic Natural Language Processing
724 Citations2010Nizar Habash
SemEval-2014 Task 9: Sentiment Analysis in Twitter
615 Citations2014Sara Rosenthal, Alan Ritter +2 more
The Sentiment Analysis in Twitter task is described, a continuation of the last year’s task that ran successfully as part of SemEval2013 and introduced three new test sets: regular tweets, sarcastic tweets, and LiveJournal sentences.
International Conference on Learning RepresentationsHow to Construct Deep Recurrent Neural Networks
577 Citations2014Razvan Pascanu, Çaǧlar Gülçehre +2 more
arXiv (Cornell University)A new ANEW: Evaluation of a word list for sentiment analysis in\n microblogs
537 Citations2011Finn Årup Nielsen
Bag of Tricks for Efficient Text Classification
513 Citations2017Armand Joulin, Édouard Grave +2 more
A simple and efficient baseline for text classification is explored that shows that the fast text classifier fastText is often on par with deep learning classifiers in terms of accuracy, and many orders of magnitude faster for training and evaluation.
OpinionFinder
471 Citations2005Theresa Wilson, Paul Hoffmann +7 more
OpinionFinder is a system that performs subjectivity analysis, automatically identifying when opinions, sentiments, speculations, and other private states are present in text.
Natural Language Processing and Text Mining
470 Citations2007Anne Kao, Stephen R. Poteet
This state-of-the-art survey is a must-have for advanced students, professionals, and researchers.
arXiv (Cornell University)NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets
460 Citations2013Saif M. Mohammad, Svetlana Kiritchenko +1 more
Representing text chunks
449 Citations1999Erik F. Tjong Kim Sang, Jorn Veenstra
It is shown that the the data representation choice has a minor influence on chunking performance, however, equipped with the most suitable data representation, the memory-based learning chunker was able to improve the best published chunking results for a standard data set.
arXiv (Cornell University)Enriching Word Vectors with Subword Information
439 Citations2016Piotr Bojanowski, Édouard Grave +2 more
Information Technology & TourismWhat Motivates Consumers to Write Online Travel Reviews?
431 Citations2008Kyung Hyan Yoo, Ulrike Gretzel
The results indicate that online travel review writers are mostly motivated by helping a travel service provider, concerns for other consumers, and needs for enjoyment/positive self-enhancement.
arXiv (Cornell University)NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of\n Tweets
419 Citations2013Saif M. Mohammad, Svetlana Kiritchenko +1 more
This paper describes how it created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detects the sentimentof a term within a message (term-leveltask).
Synthesis lectures on human language technologiesIntroduction to Arabic Natural Language Processing
290 Citations2010Nizar Habash
Journal of the American Society for Information Science and TechnologyOCA: Opinion corpus for Arabic
264 Citations2011Mohammed Rushdi‐Saleh, María Teresa Martín Valdivia +2 more
A new Arabic corpus for the OM task that has been made available to the scientific community for research purposes is presented, containing 500 movie reviews collected from different web pages and blogs in Arabic.
Decision Support SystemsSubjectivity and sentiment analysis: An overview of the current state of the area and envisaged developments
264 Citations2012Andrés Montoyo, Patricio Martínez-Barco +1 more
This introduction presents an overview of the current state of research in the Natural Language Processing tasks of subjectivity and sentiment analysis, as well as their application domains and closely-related research field of emotion detection.
Computer Speech & LanguageSAMAR: Subjectivity and sentiment analysis for Arabic social media
258 Citations2013Muhammad Abdul-Mageed, Mona Diab +1 more
The results show that using either lemma or lexeme information is helpful, as well as using the two part of speech tagsets (RTS and ERTS), but that lemmatization and the ERTS POS tagset are present in a majority of the settings.
Meeting of the Association for Computational LinguisticsSubjectivity and Sentiment Analysis of Modern Standard Arabic
246 Citations2011Muhammad Abdul-Mageed, Mona Diab +1 more
This study presents a newly developed manually annotated corpus of Modern Standard Arabic together with a new polarity lexicon and shows that by explicitly accounting for the rich morphology the system is able to achieve significantly higher levels of performance.
arXiv (Cornell University)How to Construct Deep Recurrent Neural Networks
245 Citations2013Razvan Pascanu, Çaǧlar Gülçehre +2 more
Coooolll: A Deep Learning System for Twitter Sentiment Classification
243 Citations2014Duyu Tang, Furu Wei +3 more
A neural network with hybrid loss function 1 is developed to learn SSWE, which encodes the sentiment information of tweets in the continuous representation of words, which can be easily re-implemented with the publicly available sentiment-specific word embedding.
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.
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
234 Citations2015Ojha, Atul Kr., Doğruöz, A. Seza +4 more
Proceedings of the NAACL HLT 2010 Workshop on Computational Approaches to Analysis and Generation of Emotion in Text
218 Citations2010Diana Inkpen, Carlo Strapparava
Combining distributional and morphological information for part of speech induction
208 Citations2003Alexander Clark
Algorithms for clustering words into classes from unlabelled text using unsupervised algorithms, based on distributional and morphological information, are discussed, showing how the use of morphological Information can improve the performance on rare words.
LABR: A Large Scale Arabic Book Reviews Dataset
207 Citations2013Mohamed Aly, Amir F. Atiya
This work introduces LABR, the largest sentiment analysis dataset to-date for the Arabic language, which consists of over 63,000 book reviews, each rated on a scale of 1 to 5 stars, and investigates the properties and presents its statistics.
Sentence-Level and Document-Level Sentiment Mining for Arabic Texts
182 Citations2010Noura Farra, Elie Challita +2 more
It is shown, with high accuracy, that it is feasible to extract the sentiment of an Arabic document based on the classes of its sentences, and a hierarchical classification scheme is proposed that uses the results of the sentence- level classifier as input to the document-level classifier.
AWATIF: A Multi-Genre Corpus for Modern Standard Arabic Subjectivity and Sentiment Analysis
161 Citations2012Muhammad Abdul-Mageed, Mona Diab
AWATIF, a multi-genre corpus of Modern Standard Arabic labeled for subjectivity and sentiment analysis (SSA) at the sentence level, is presented and its linguistically-motivated and genre-nuanced annotation guidelines are presented.
International Conference on Computational LinguisticsWord Embeddings and Convolutional Neural Network for Arabic Sentiment Classification
155 Citations2016Abdelghani Dahou, Shengwu Xiong +3 more
A scheme of Arabic sentiment classification, which evaluates and detects the sentiment polarity from Arabic reviews and Arabic social media, is studied and it is shown that the proposed scheme outperforms the existed methods on 4 out of 5 balanced and unbalanced datasets.
Journal of Information ScienceArabic tweets sentiment analysis – a hybrid scheme
152 Citations2015Haifa K. Aldayel, Aqil M. Azmi
A hybrid approach that combines semantic orientation and machine learning techniques is recommended that improved the F-measure of the lexical classifier while the accuracy jumped by 16.41%, achieving an overall F-Measure and accuracy of 84 and 84.01% respectively.
NeurocomputingModeling word perception using the Elman network
136 Citations2008Cheng‐Yuan Liou, Jau-Chi Huang +1 more
Experiments performed on a corpus composed of Shakespeare's writings show its linguistic analysis and categorization abilities.
Mining Arabic Business Reviews
117 Citations2010M.E. El-Hawary, Mohamed Elfeky
This paper shows how to extract the business reviews scattered on the web written in the Arabic language from the web in order to provide them in the search results when a user searches for a business or a category of businesses.
Arabic Opinion Mining Using Combined Classification Approach
117 Citations2011Alaa M. El-Halees
A combined approach that automatically extracts opinions from Arabic documents is presented that consists of three methods, lexicon based method, k-nearest method and maximum entropy method.
Communications in computer and information scienceSubjectivity and Sentiment Analysis of Arabic: A Survey
111 Citations2012Mohammed Korayem, David Crandall +1 more
This paper surveys different techniques for SSA for Arabic and describes the main existing techniques and test corpora for Arabic SSA that have been introduced in the literature.
Human Annotated Arabic Dataset of Book Reviews for Aspect Based Sentiment Analysis
110 Citations2015Mohammad AL-Smadi, Omar Qawasmeh +2 more
Foster the domain of Arabic ABSA, and provides a benchmark human annotated Arabic dataset (HAAD), which consists of books reviews in Arabic which have been annotated by humans with aspect terms and their polarities.
Multi-lingual sentiment analysis of financial news streams
91 Citations2007Khurshid Ahmad, D. Cheng +1 more
It is shown that the local grammar approach, developed on an archive of English (Indo-European language) texts, works equally on the typologically different Chinese (Sino-Asiatic) and Arabic (Semitic) languages.
Proceedings of the 7th ACM conference on Electronic commerce
85 Citations2006
Linguistic Annotation WorkshopSubjectivity and Sentiment Annotation of Modern Standard Arabic Newswire
73 Citations2011Muhammad Abdul-Mageed, Mona Diab
A newly labeled corpus of Modern Standard Arabic from the news domain manually annotated for subjectivity and domain at the sentence level is presented and linguistically-motivated annotation guidelines are summarized.
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.
Information Processing & ManagementA sampling based sentiment mining approach for e-commerce applications
60 Citations2016G. Arul Freeda Vinodhini, R. Chandrasekaran
A modification is proposed in support vector machine based ensemble algorithm which incorporates both oversampling and undersampling to improve the prediction performance and to investigate the combined effect of machine learning classifiers and sampling methods in sentiment classification under imbalanced data distributions.
AraNLP: a Java-based Library for the Processing of Arabic Text.
56 Citations2014Maha Jarallah Althobaiti, Udo Kruschwitz +1 more
The AraNLP library is an attempt to gather most of the vital Arabic text preprocessing tools into one library that can be accessed easily by integrating or accurately adapting existing tools and by developing new ones when required.
Enhancing the determination of aspect categories and their polarities in Arabic reviews using lexicon-based approaches
54 Citations2015Islam Obaidat, Rami Mohawesh +3 more
This work considers two ABSA tasks: aspect category determination and aspect category polarity determination, and makes use of the publicly available human annotated Arabic dataset (HAAD) along with its baseline experiments conducted by HAAD providers.
Sentiue: Target and Aspect based Sentiment Analysis in SemEval-2015 Task 12
54 Citations2015José Saias
This paper describes the participation in SemEval-2015 Task 12, and the opinion mining system sentiue, which used a 3 class polarity classifier, having BoW, lemmas, bigrams after verbs, presence of polarized terms, and punctuation based features.
EliXa: A Modular and Flexible ABSA Platform
51 Citations2015Iñaki San Vicente, Xabier Saralegi +1 more
A modular platform which allows to easily conduct experiments by replacing the modules or adding new features by means of a multiclass SVM algorithm which includes lexical based features such as the polarity values obtained from domain and open polarity lexicons is developed.
Journal of the Association for Information Science and TechnologyAutomated arabic text classification with <scp>P</scp>‐<scp>S</scp>temmer, machine learning, and a tailored news article taxonomy
49 Citations2015Tarek Kanan, Edward A. Fox
A simple taxonomy for Arabic news stories that is suitable for the needs of Qatar and other nations, is compatible with the subject codes of the International Press Telecommunications Council, and was enhanced with the aid of a librarian expert as well as five Arabic‐speaking volunteers are designed.
An enhanced framework for aspect-based sentiment analysis of Hotels' reviews: Arabic reviews case study
47 Citations2016Mohammad AL-Smadi, Omar Qwasmeh +4 more
This research proposes a framework for aspect-based sentiment analysis (ABSA) of Hotels' reviews by using a reference human annotated Arabic dataset to support ABSA tasks such as aspect category identification, opinion target expression extraction, and opinion sentiment polarity.
2015 IEEE/ACM 8th International Conference on Utility and Cloud Computing (UCC)
46 Citations2015
Cloud2Sim provides a concurrent and distributed cloud simulator, by extendingcloud simulator, using Hazel cast in-memory key-value store, and provides an assessment of the MapReduce implementations of Hazel cast and Infinispan, with means of simulating Map Reduce executions.
Proceedings of the 11th Linguistic Annotation Workshop
37 Citations2017Nathan Schneider, Nianwen Xue +1004 more
The Linguistic Annotation Workshop provides a forum to facilitate the exchange and propagation of research results concerned with the annotation, manipulation, and exploitation of corpora; work towards the harmonization and interoperability from the perspective of the increasingly large number of tools and frameworks for annotated language resources.
Classifying sentiment in arabic social networks: Na&#x00EF;ve search versus Na&#x00EF;ve bayes
34 Citations2012Maher Itani, Rached Zantout +2 more
Two different approaches to classify Arabic Facebook posts are presented, using common patterns used in different Arabic dialects to express opinions and an ordinary probabilistic model, Naïve-Bayes classifier, that assumes the independence of features in determining the class.
ECNU: Extracting Effective Features from Multiple Sequential Sentences for Target-dependent Sentiment Analysis in Reviews
29 Citations2015Zhihua Zhang, Man Lan
This paper describes the systems submitted to the target-dependent sentiment polarity classification subtask in aspect based sentiment analysis (ABSA) task (i.e., Task 12) in SemEval 2015, and their rankings in laptop domain and restaurant domain.
Using Aspect-Based Sentiment Analysis to Evaluate Arabic News Affect on Readers
28 Citations2015Mohammad AL-Smadi, Mahmoud Al‐Ayyoub +2 more
A novel approach of using aspect-based sentiment analysis in evaluating Arabic news posts affect on readers is proposed, which adopts several phases of text processing, features selection, and text classification.
UFAL at SemEval-2016 Task 5: Recurrent Neural Networks for Sentence Classification
25 Citations2016Aleš Tamchyna, Kateřina Veselovská
This paper proposes to utilize neural networks which should be capable of discovering linguistic patterns in the data automatically, thereby reducing the need for language-specific tools and feature engineering.
Proceedings of the ninth conference on European chapter of the Association for Computational Linguistics -
23 Citations1999
This volume contains the papers prepared for the Ninth Conference of the European Chapter of the Association for Computational Linguistics, held 8-12 June in Bergen, Norway, and used a new web-based approach to managing the paper submission and reviewing process this year.
International Journal of Information Technology and Web EngineeringUsing Enhanced Lexicon-Based Approaches for the Determination of Aspect Categories and Their Polarities in Arabic Reviews
21 Citations2016Mohammad AL-Smadi, Islam Obaidat +3 more
This work considers two ABSA tasks: aspect category determination and aspect category polarity determination, and makes use of the publicly available human annotated Arabic dataset HAAD along with its baseline experiments conducted by HAAD providers.
…