Recognizing contextual polarity in phrase-level sentiment analysis
Open accessThe DOI matches its Crossref record; 25 of the 25 references it cites were found in a registry or an index.
Abstract
This paper presents a new approach to phrase-level sentiment analysis that first determines whether an expression is neutral or polar and then disambiguates the polarity of the polar expressions. With this approach, the system is able to automatically identify the contextual polarity for a large subset of sentiment expressions, achieving results that are significantly better than baseline.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Mining and summarizing customer reviews
Hu, M., & Liu, B. (2004) · Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1014052.1014073 · Cited by 7,793
A Comprehensive Grammar of the English Language
Huddleston, R., Quirk, R., Greenbaum, S., Leech, G., & Svartvik, J. (1988) · Language · doi:10.2307/415437 · Cited by 7,587
A Comprehensive Grammar of the English Language
Beauvais, P. J., Quirk, R., Greenbaum, S., Leech, G., & Svartvik, J. (1987) · College Composition and Communication · doi:10.2307/357731 · Cited by 5,488
Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
Peter, P., & Turney (2002) · Cited by 3,650
A sentimental education: sentiment analysis using subjectivity summarization based on minimum cuts
Pang, B., & Lee, L. (2004) · Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics - ACL '04 · doi:10.3115/1218955.1218990 · Cited by 3,301
Thumbs up or thumbs down?: semantic orientation applied to unsupervised classification of reviews
Turney, P. D. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073153 · Cited by 2,352
BoosTexter: A Boosting-based System for Text Categorization
Schapire, R. E., & Singer, Y. (2000) · Machine Learning · doi:10.1023/a:1007649029923 · Cited by 2,188
Mining the peanut gallery: opinion extraction and semantic classification of product reviews
Dave, K., Lawrence, S., & Pennock, D. M. (2003) · Proceedings of the twelfth international conference on World Wide Web - WWW '03 · doi:10.1145/775152.775226 · Cited by 1,916
Annotating Expressions of Opinions and Emotions in Language
Wiebe, J., Wilson, T., & Cardie, C. (2005) · Language Resources and Evaluation · doi:10.1007/s10579-005-7880-9 · Cited by 1,755
Self-citationThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews
Turney, P. D. (2002) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0212032 · Cited by 1,575
Cited by
Items 101–139 of 139
Kang, D., & Park, Y. (2014) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.07.101 · Cited by 268
DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks
Chen, T., Borth, D., Darrell, T. J., & Chang, S. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1410.8586 · Cited by 257
Happiness Is Assortative in Online Social Networks
Bollen, J., Gonçalves, B., Ruan, G., & Mao, H. (2011) · Artificial Life · doi:10.1162/artl_a_00034 · Cited by 257
Sentiment analysis in medical settings: New opportunities and challenges
Denecke, K., & Deng, Y. (2015) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2015.03.006 · Cited by 254
Opinion Mining and Information Fusion: A survey
Balazs, J. A., & Velásquez, J. D. (2016) · Information Fusion · doi:10.1016/j.inffus.2015.06.002 · Cited by 253
Multi-aspect Sentiment Analysis with Topic Models
Lu, B., Ott, M., Cardie, C., & Tsou, B. K. (2011) · 2011 IEEE 11th International Conference on Data Mining Workshops · doi:10.1109/icdmw.2011.125 · Cited by 248
“5 We also tried other topic numbers in the range of [5-30] with a step of 5, with performance decreasing with increasing K, in most cases.”
BackgroundMethodVehicle defect discovery from social media
Abrahams, A. S., Jiao, J., Wang, G. A., & Fan, W. (2012) · Decision Support Systems · doi:10.1016/j.dss.2012.04.005 · Cited by 247
“For OpinionFinder, two subjectivity classifiers were available; we used both but, for brevity, show only the results from the classifier which produced the OpinionFinder results with the strongest fit.”
MethodInfluentialTowards an intelligent framework for multimodal affective data analysis
Poria, S., Cambria, E., Hussain, A., & Huang, G.-B. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.10.005 · Cited by 236
Symeonidis, S., Effrosynidis, D., & Arampatzis, A. (2018) · Expert Systems with Applications · doi:10.1016/j.eswa.2018.06.022 · Cited by 229
DCU: Aspect-based Polarity Classification for SemEval Task 4
Wagner, J., Arora, P., Cortes, S., Barman, U., Bogdanova, D., Foster, J., & Tounsi, L. (2014) · Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014) · doi:10.3115/v1/s14-2036 · Cited by 222
Sentiment analysis and opinion mining on educational data: A survey
Shaik, T., Tao, X., Dann, C., Xie, H., Li, Y., & Galligan, L. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2022.100003 · Cited by 215
“The approaches are SentiWordNet [36], Opinion Finder [37], Bing Liu’s Opinion Lexicon [38], MPQA subjectivity lexicon [39], Harvard General Inquirer [40], AFINN [41], SentiFul [42], Vader [43], TextBlob [44] and so on.”
MethodThe effect of negation on sentiment analysis and retrieval effectiveness
Jia, L., Yu, C., & Meng, W. (2009) · Proceedings of the 18th ACM conference on Information and knowledge management · doi:10.1145/1645953.1646241 · Cited by 209
“In this paper, we assume that sentimental terms are either individual word or multi-word phrases whose polarities have been pre-determined by methods such as [15, 16, 18] and negation terms are either individual negation words or negation phrases.”
MethodSemi-supervised learning for big social data analysis
Hussain, A., & Cambria, E. (2018) · Neurocomputing · doi:10.1016/j.neucom.2017.10.010 · Cited by 205
“These probabilities are usually trained from linguistic corpora [27, 28, 29].”
BackgroundSelect-additive learning: Improving generalization in multimodal sentiment analysis
Wang, H., Meghawat, A., Morency, L.-P., & Xing, E. P. (2017) · 2017 IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme.2017.8019301 · Cited by 203
“Originating from analysis of the textual modality, sentiment analysis has been carried out at the word level [15], phrase level [16] and sentence level [17].”
BackgroundSentiment analysis of political communication: combining a dictionary approach with crowdcoding
Haselmayer, M., & Jenny, M. (2017) · Quality & Quantity · doi:10.1007/s11135-016-0412-4 · Cited by 202
“The classification of text as positive, negative, or neutral, is denoted by expressions such as polarity, valence or tone (Wilson et al. 2005; Young and Soroka 2012; Thelwall and Buckley 2013; Gonza´lez-Bailo´n and Paltoglou 2015; Mohammad 2016).”
BackgroundExploiting Social Network Structure for Person-to-Person Sentiment Analysis
West, R., Paskov, H. S., Leskovec, J., & Potts, C. (2014) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00184 · Cited by 198
“Recent work in sentiment analysis has brought in topical, contextual, and social information to make more nuanced predictions about language (Jurafsky et al., 2014; Wilson et al., 2005; Blitzer et al., 2007).”
BackgroundWang, S., Li, D., Song, X., Wei, Y., & Li, H. (2011) · Expert Systems with Applications · doi:10.1016/j.eswa.2011.01.077 · Cited by 191
Open Domain Targeted Sentiment
Mitchell, M., Aguilar, J., Wilson, T., & Van Durme, B. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1171 · Cited by 191
“For English, we use the MPQA lexicon (Wilson et al., 2005), which identifies 12,296 manually and semi-automatically produced subjective terms along with their polarity.”
BackgroundMethodSelf-citationAl-Smadi, M., Al-Ayyoub, M., Jararweh, Y., & Qawasmeh, O. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2018.01.006 · Cited by 189
Hajek, P., Barushka, A., & Munk, M. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04757-2 · Cited by 186
“Polarity-based features were represented by the numbers of positive/negative words that match two popular lexicons, the OpinionFinder lexicon [11, 72] and Bing Liu’s opinion lexicon [29].”
BackgroundSentiment analysis: A survey on design framework, applications and future scopes
Bordoloi, M., & Biswas, S. K. (2023) · Artificial Intelligence Review · doi:10.1007/s10462-023-10442-2 · Cited by 183
Korkontzelos, I., Nikfarjam, A., Shardlow, M., Sarker, A., Ananiadou, S., & Gonzalez, G. H. (2016) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2016.06.007 · Cited by 173
Jha, A., & Mamidi, R. (2017) · Proceedings of the Second Workshop on NLP and Computational Social Science · doi:10.18653/v1/w17-2902 · Cited by 169
“To detect contextual polarity using phrase-level sentiment analysis, Wilson et al. (2005) identify whether a phrase is neutral or polar.”
MethodDetecting Stance in Tweets And Analyzing its Interaction with Sentiment
Sobhani, P., Mohammad, S., & Kiritchenko, S. (2016) · Proceedings of the Fifth Joint Conference on Lexical and Computational Semantics · doi:10.18653/v1/s16-2021 · Cited by 130
“The lexicons used include NRC Emotion Lexicon (Mohammad and Turney, 2010), Hu and Liu Lexicon (Hu and Liu, 2004), MPQA Subjectivity Lexicon (Wilson et al., 2005), and NRC Hashtag Sentiment and Emoticon Lexicons (Kiritchenko et al., 2014b).”
MethodSentiment analysis on tweets for social events
Zhou, X., Tao, X., Yong, J., & Yang, Z. (2013) · Proceedings of the 2013 IEEE 17th International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd.2013.6581022 · Cited by 124
Women through the glass ceiling: gender asymmetries in Wikipedia
Wagner, C., Graells-Garrido, E., Garcia, D., & Menczer, F. (2016) · EPJ Data Science · doi:10.1140/epjds/s13688-016-0066-4 · Cited by 115
Who Falls for Online Political Manipulation?
Badawy, A., Lerman, K., & Ferrara, E. (2019) · Companion Proceedings of The 2019 World Wide Web Conference · doi:10.1145/3308560.3316494 · Cited by 105
“Sentiment: Features such as: arousal, valence and dominance scores [36], happiness score [18], polarization and strength [37], and emotion score [1].”
BackgroundSystematic literature review on context-based sentiment analysis in social multimedia
Kumar, A., & Garg, G. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-019-7346-5 · Cited by 86
“Knowledge is domain dependent and validity of facts change along with context switches [55].”
BackgroundSentiment analysis of user comments for one-class collaborative filtering over ted talks
Pappas, N., & Popescu-Belis, A. (2013) · Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval · doi:10.1145/2484028.2484116 · Cited by 81
“Given the lack of ground-truth labels, we focused on dictionary-based methods and specifically on an extension of the rule-based sentiment classifier presented in [10] and implemented in [7](1).”
MethodSong lyrics have become simpler and more repetitive over the last five decades
Parada-Cabaleiro, E., Mayerl, M., Brandl, S., Skowron, M., Schedl, M., Lex, E., & Zangerle, E. (2024) · Scientific Reports · doi:10.1038/s41598-024-55742-x · Cited by 73
Antoine, J.-Y., Villaneau, J., & Lefeuvre, A. (2014) · Proceedings of the 14th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.3115/v1/e14-1058 · Cited by 87
“A basic task in opinion mining consists in classifying the polarity of a given text, which should be either a sentence (Wilson and al., 2005), a speech turn or a complete document (Turney, 2002).”
BackgroundLai, M., Tambuscio, M., Patti, V., Ruffo, G., & Rosso, P. (2019) · Data & Knowledge Engineering · doi:10.1016/j.datak.2019.101738 · Cited by 61
“Sentiment resources, such as EmoLex in [46], MPQA in [67], Hu&Liu in [29], and NRC Hashtag in [44], have also been used.”
MethodDynaSent: A Dynamic Benchmark for Sentiment Analysis
Potts, C., Wu, Z., Geiger, A., & Kiela, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.186 · Cited by 56
“Other important examples are Opin-ionFinder (Wilson et al., 2005), LIWC (Pennebaker et al., 2007), MPQA, Opinion Lexicon (Liu, 2011), SentiWordNet (Baccianella et al., 2010), and the valence and arousal ratings of Warriner et al. (2013).”
BackgroundNatural language processing techniques for researching and improving peer feedback
Xiong, W., Litman, D., & Schunn, C. (2012) · Journal of Writing Research · doi:10.17239/jowr-2012.04.02.3 · Cited by 36
Small decisions with big impact on data analytics
Diesner, J. (2015) · Big Data & Society · doi:10.1177/2053951715617185 · Cited by 32
“…pairs (occasionally enriched with additional information such as parts of speech), that can be used to assess, for example, the subjectivity, emotionality, honesty, and morale of (pieces of) text data or their authors (Graham et al., 2009; Tausczik and Pennebaker, 2010; Wilson et al., 2005).”
BackgroundMethodExploiting the topology property of social network for rumor detection
Yang, Y., Niu, K., & He, Z. (2015) · 2015 12th International Joint Conference on Computer Science and Software Engineering (JCSSE) · doi:10.1109/jcsse.2015.7219767 · Cited by 31
Identifying and Avoiding Confusion in Dialogue with People with Alzheimer's Disease
Chinaei, H., Currie, L. C., Danks, A., Lin, H., Mehta, T., & Rudzicz, F. (2017) · Computational Linguistics · doi:10.1162/coli_a_00290 · Cited by 30
“We also compute objectivity measures using the MPQA Subjectivity Lexicon (Wilson, Wiebe, and Hoffmann 2005), which categorizes words by their subjectivity (strong or weak) and their prior, out-of-context, polarity (positive, negative, both, or neutral).”
MethodTowards Evaluating Narrative Quality In Student Writing
Somasundaran, S., Flor, M., Chodorow, M., Molloy, H., Gyawali, B., & McCulla, L. (2018) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00007 · Cited by 29
“We use two lexicons for detecting sentiment and subjective words: the MPQA subjectivity lexicon (Wilson et al., 2005) and a sentiment lexicon, AS-SESS, developed for essay scoring (Beigman Kle-banov et al., 2012).”
MethodTalk2Me: Automated linguistic data collection for personal assessment
Komeili, M., Pou-Prom, C., Liaqat, D., Fraser, K. C., Yancheva, M., & Rudzicz, F. (2019) · PLOS ONE · doi:10.1371/journal.pone.0212342 · Cited by 23
“We measure the polarity of transcripts by computing averages and standard deviations of norms derived from the Multi-Perspective Question Answering (MPQA) lexicon [58] and the Stanford Sentiment analyzer [59].”
Method
Metadata
- Authors
- Wilson, T., Wiebe, J., & Hoffmann, P.
- Venue
- Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing - HLT '05
- Published
- 2005
- Pages
- 347-354
- OpenAlex
- W2022204871
- Cited by
- 3,345
- References
- 25
- FWCI
- 30.77
- Type
- conference paper
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.