Learning opinions in user-generated web content
Published 1 January 2011
M. S Okolova, G. L Apalme
Citations10
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.
Abstract
The user-generated Web content has been intensively analyzed in Information Extraction and Natural Language Processing research. Web-posted reviews of consumer goods are studied to find customer opinions about the products. We hypothesize that nonemotionally charged descriptions can be applied to predict those opinions. The descriptions may include indicators of product size (tall), commonplace (some), frequency of happening (often), and reviewer certainty (maybe). We first construct patterns of how the descriptions are used in consumer-written texts and then represent individual reviews through these patterns. We propose a semantic hierarchy that organizes individual words into opinion types. We run machine learning algorithms on five data sets of user-written product reviews: four are used in classification experiments, another one for regression and classification. The obtained results support the use of non-emotional descriptions in opinion learning. 1 Opinions in user-generated Web content The user-generated Web content refers to publicly available data produced by the Web end users (Directorate for Science, Technology and Industry, 2007). For instance, blogs, social network profiles, and consumer-written product reviews are parts of the user-generated textual content. In those texts, users share their personal stories, discuss life experience, and comment on various events, making the Web content more personalized and subjective. This rapidly growing phenomenon has attracted attention of many researchers, at the same time adding new analysis areas to the field of text and language studies. In traditional text mining applications, texts (documents) were often classified according to their topics. In studies of usergenerated texts, the focus shifted from topic classification to sentiment and opinion analysis. Opinion studies often analyze user-written reviews to predict opinions about the consumed goods. Our work focuses on opinion analysis methods applicable when the product consumers reveal their opinions in a non-emotional way. We want to establish a link between non-emotional expressions and reviewer’s opinions.
Keywords
Computer ScienceSocial Sciences
TESOL QuarterlyLongman Grammar of Spoken and Written English
8,230 Citations2000Kathleen M. Broussard, Douglas Biber +4 more
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.
Thumbs up?
6,987 Citations2002Bo Pang, Lillian Lee +1 more
This work considers the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative, and concludes by examining factors that make the sentiment classification problem more challenging.
now publishers, Inc. eBooksOpinion Mining and Sentiment Analysis
6,745 Citations2008Bo Pang, Lillian Lee
College Composition and CommunicationA Comprehensive Grammar of the English Language
5,535 Citations1987P Beauvais, Randolph Quirk +3 more
Meeting of the Association for Computational LinguisticsThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
3,654 Citations2002Peter Peter, Turney
SENTIWORDNET: A Publicly Available Lexical Resource for Opinion Mining
2,489 Citations2006Andrea Esuli, Fabrizio Sebastiani
SENTIWORDNET is a lexical resource in which each WORDNET synset is associated to three numerical scores Obj, Pos and Neg, describing how objective, positive, and negative the terms contained in the synset are.
Zeitschrift für Anglistik und AmerikanistikThe Cambridge Grammar of the English Language
2,417 Citations2005R. E. Huddleston, Geoffrey K. Pullum
Seeing stars
2,127 Citations2005Bo Pang, Lillian Lee
A meta-algorithm is applied, based on a metric labeling formulation of the rating-inference problem, that alters a given n-ary classifier's output in an explicit attempt to ensure that similar items receive similar labels.
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.
The MIT Press eBooksAnalysis of Representations for Domain Adaptation
2,023 Citations2007Shai Ben-David, John Blitzer +2 more
The theory illustrates the tradeoffs inherent in designing a representation for domain adaptation and gives a new justification for a recently proposed model which explicitly minimizes the difference between the source and target domains, while at the same time maximizing the margin of the training set.
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.
IEEE Transactions on Acoustics Speech and Signal ProcessingEstimation of probabilities from sparse data for the language model component of a speech recognizer
1,645 Citations1987Slava M. Katz
The model offers, via a nonlinear recursive procedure, a computation and space efficient solution to the problem of estimating probabilities from sparse data, and compares favorably to other proposed methods.
Opinion spam and analysis
1,520 Citations2008Nitin Jindal, Bing Liu
It is shown that opinion spam is quite different from Web spam and email spam, and thus requires different detection techniques, and therefore requires some novel techniques to detect them.
ACM Transactions on Information SystemsMeasuring praise and criticism
1,509 Citations2003Peter D. Turney, Michael L. Littman
This article introduces a method for inferring the semantic orientation of a word from its statistical association with a set of positive and negative paradigm words, based on two different statistical measures of word association.
Cambridge University Press eBooksLanguage and the Internet
1,472 Citations2001David Crystal
Covering a range of Internet genres, including e-mail, chat, and the Web, this is a revealing account of how the Internet is radically changing the way the authors use language.
Modern Language JournalFundamental Concepts of Language Teaching
1,365 Citations1986June K. Phillips, H. H. Stern
This chapter discusses language education in the classroom and discusses the importance of language pedagogical practices, as well as some of the strategies used to achieve this goal.
IEEE Transactions on Knowledge and Data EngineeringBenchmarking attribute selection techniques for discrete class data mining
1,231 Citations2003Mark A. Hall, Geoffrey Holmes
A benchmark comparison of several attribute selection methods for supervised classification by cross-validating the attribute rankings with respect to a classification learner to find the best attributes.
Choice Reviews OnlineWeb data mining: exploring hyperlinks, contents, and usage data
1,193 Citations2012
Towards answering opinion questions
1,051 Citations2003Hong Yu, Vasileios Hatzivassiloglou
A Bayesian classifier for discriminating between documents with a preponderance of opinions such as editorials from regular news stories is presented, and three unsupervised, statistical techniques for the significantly harder task of detecting opinions at the sentence level are described.
Linguistics and PhilosophyContext Dependence, Disagreement, and Predicates of Personal Taste*
901 Citations2005Peter Lasersohn
Word Frequencies in Written and Spoken English: Based on the British National Corpus
729 Citations2001Geoffrey Leech, Paul Rayson +1 more
This book addressed limitations of earlier word frequency dictionaries of English, that of sample size and breadth by using a large representative corpus of up-to-date written, and importantly, spoken language.
Pattern Grammar: A corpus-driven approach to the lexical grammar of English
699 Citations2000Susan Hunston, Gill Francis
This book describes an approach to lexis and grammar based on the concept of phraseology and of language patterning arising from work on large corpora, intended to contribute to the current debate concerning how corpora challenge existing linguistic theories.
Evaluation: An Introduction
622 Citations2000Geoff Thompson, Susan Hunston
Identifying comparative sentences in text documents
445 Citations2006Nitin Jindal, Bing Liu
This paper first categorizes comparative sentences into different types, and then presents a novel integrated pattern discovery and supervised learning approach to identifying comparative sentences from text documents.
Sentiment Analysis: Adjectives and Adverbs are better than Adjectives Alone
330 Citations2007Farah Benamara, Carmine Cesarano +3 more
This work proposes an AAC-based sentiment analysis technique that uses a linguistic analysis of adverbs of degree that leads to higher accuracy based on Pearson correlation with human subjects and describes the results of experiments.
Conference of the European Chapter of the Association for Computational LinguisticsDetermining Term Subjectivity and Term Orientation for Opinion Mining
306 Citations2006Andrea Esuli, Fabrizio Sebastiani
The task of deciding whether a given term has a positive connotations, or a negative connotation, or has no subjective connotation at all is confronted, and it is shown that determining subjectivity and orientation is a much harder problem than determining orientation alone.
Recognizing stances in online debates
301 Citations2009Swapna Somasundaran, Janyce Wiebe
This paper presents an unsupervised opinion analysis method for debate-side classification, i.e., recognizing which stance a person is taking in an online debate, and shows that this method is substantially better than challenging baseline methods.
Feature subsumption for opinion analysis
263 Citations2006Ellen Riloff, Siddharth Patwardhan +1 more
It is shown that reducing the feature set improves performance on three opinion classification tasks, especially when combined with traditional feature selection.
International Joint Conference on Artificial IntelligenceIdentifying expressions of opinion in context
253 Citations2007Eric Breck, Yejin Choi +1 more
An approach for identifying opinion expressions that uses conditional random fields and achieves expression-level performance within 5% of the human interannotator agreement is presented.
Examining the role of linguistic knowledge sources in the automatic identification and classification of reviews
251 Citations2006Vincent Ng, Sajib Dasgupta +1 more
It is demonstrated that review identification can be performed with high accuracy using only unigrams as features, and the role of four types of simple linguistic knowledge sources in a polarity classification system is examined.
Automatic Extraction of Opinion Propositions and their Holders
216 Citations2004Steven Bethard, Hong Yu +3 more
An extension of semantic parsing techniques, coupled with additional lexical and syntactic features, that can produce labels for propositional opinions as opposed to other syntactic constituents is proposed.
Topic identification for fine-grained opinion analysis
192 Citations2008Veselin Stoyanov, Claire Cardie
This paper provides an operational definition of opinion topic and presents an algorithm for opinion topic identification that, following the new definition, treats the task as a problem in topic coreference resolution.
Computational IntelligenceRECOGNIZING STRONG AND WEAK OPINION CLAUSES
183 Citations2006Theresa Wilson, Janyce Wiebe +1 more
This paper presents the first experimental results classifying the intensity of opinions and other types of subjectivity and classifies the subjectivity of deeply nested clauses using a wide range of features, including new syntactic features developed for opinion recognition.
When Specialists and Generalists Work Together: Overcoming Domain Dependence in Sentiment Tagging
165 Citations2008Alina Andreevskaia, Sabine Bergler
A sentiment annotation system that integrates a corpus-based classifier trained on a small set of annotated in-domain data and a lexicon-based system trained on WordNet, and a new system consisting of the ensemble of two classifiers with precision-based vote weighting that provides significant gains in accuracy and recall.
Mine the easy, classify the hard
165 Citations2009Sajib Dasgupta, Vincent Ng
This work proposes a semi-supervised approach to sentiment classification where it first mine the unambiguous reviews using spectral techniques and then exploit them to classify the ambiguous reviews via a novel combination of active learning, transductive learning, and ensemble learning.
Encyclopedia of Evaluation Encyclopedia of evaluationLogic of Evaluation
134 Citations2012Michael Scriven
A sketch of the arguments for adding the logic of evaluation to the areas of argumentation that have been partly mapped and are worth further work by workers in rhetoric, argumentation, communication, critical thinking, and informal logic.
Proceedings of the International AAAI Conference on Web and Social MediaTargeting Sentiment Expressions through Supervised Ranking of Linguistic Configurations
120 Citations2009Jason S. Kessler, Nicolas Nicolov
A large English corpus of product discussions blogs annotated with semantic types of mentions, coreference, meronymy and sentiment targets is created that proves that coreference and Meronymy are not marginal phenomena but are really central to determining the overall sentiment for the top-level entity.
Crystal: Analyzing Predictive Opinions on the Web
111 Citations2007Soo-Min Kim, Eduard Hovy
An election prediction system based on web users’ opinions posted on an election prediction website, which significantly outperforms several baselines as well as a non-generalized n-gram approach and proposes a novel technique which generalizes n- gram feature patterns.
Sentiment Classification and Polarity Shifting
109 Citations2010Shoushan Li, Sophia Y. M. Lee +3 more
A feature selection method is adopted to automatically generate the training data for a binary classifier on polarity shifting detection of sentences, and each document in the original polarity classification training data is split into two partitions which are used to train two base classifiers respectively for further classifier combination.
National Conference on Artificial IntelligenceTowards a Robust Metric of Opinion
104 Citations2004Kamal Nigam, Matthew Hurst
Journal of PragmaticsOn emotions and the journalistic ideals of factuality and objectivity—Tools for analysis
80 Citations2008Maija Stenvall
Experience Mining: Building a Large-Scale Database of Personal Experiences and Opinions from Web Documents
66 Citations2008Kentaro Inui, Shuya Abe +7 more
This paper proposes a new UGC-oriented language technology application that aims at automatically collecting instances of personal experiences as well as opinions from an explosive number of user generated contents (UGCs) and storing them in an experience database with semantically rich indices.
``Was It Good? It Was Provocative.'' Learning the Meaning of Scalar Adjectives
53 Citations2010Marie-Catherine de Marneffe, Christopher D. Manning +1 more
Group Decision and NegotiationThe Role of Emotion and Language in Dyadic E-negotiations
52 Citations2009Michael J. Hine, Steven A. Murphy +2 more
Social and Personality Psychology CompassHow do People Evaluate Objects? A Brief Review
38 Citations2009Jan De Houwer
Group Decision and NegotiationStrategies and language trends in learning success and failure of negotiation
28 Citations2007Marina Sokolova, Stan Śzpakowicz
A series of Machine Learning experiments are conducted to predict the negotiation outcome from the texts associated with first halves of negotiations, hypothesis is that language signals help predict negotiation outcomes.
Random-Walk Models of Term Semantics: An Application to Opinion-Related Properties
23 Citations2007Andrea Esuli, Fabrizio Sebastiani
This paper contends that two other random-walk algorithms may be equally adequate to this task, and provides an intuitive justification to support this claim.
Lecture notes in computer scienceVerbs Speak Loud: Verb Categories in Learning Polarity and Strength of Opinions
19 Citations2008Marina Sokolova, Guy Lapalme
This work identifies semantic verb categories that capture essential properties of human communication and empirical results show that expressed actions provide a reliable accuracy in learning opinions.
Lecture notes in computer scienceQuery-Based Summarization of Customer Reviews
19 Citations2007Olga Feiguina, Guy Lapalme
It is shown that NLP techniques can be fruitfully used in this context for helping consumers sort out the mass of information displayed in such contexts as consumer reviews about products that have been posted on specialized web sites.