A comparative assessment of sentiment analysis and star ratings for consumer reviews

Al-Natour S, Turetken O, (2020), A comparative assessment of sentiment analysis and star ratings for consumer reviews, International Journal of Information Management, Volume 54, October 2020, 102132


Mots clés : Analyse des sentiments, Bouche à oreille, Avis des consommateurs, Apprentissage automatique, Évaluation comparative

Résumé : Le bouche à oreille électronique est important et abondant dans les domaines de consommation. Les consommateurs et les fournisseurs de produits / services ont besoin d’aide pour comprendre et naviguer dans les espaces d’informations qui en résultent, qui sont vastes et dynamiques. Le ton général ou la polarité des avis, blogs ou tweets fournit une telle aide. Dans cet article, nous explorons la viabilité de l’analyse automatique des sentiments pour évaluer la polarité d’un produit ou d’un examen de service. Pour ce faire, nous examinons le potentiel des principales approches de l’analyse des sentiments, ainsi que les notes en étoiles, pour capturer le véritable sentiment d’un avis

Grandes lignes :

  • L’analyse des sentiments peut être utilisée pour déterminer le ton général d’un avis de consommateur.
  • Nous comparons la sortie de plusieurs outils d’analyse des sentiments entre eux et avec les notes en étoiles.
  • Les résultats montrent que l’analyse des sentiments peut remplacer, et surpasse souvent, les notes.
  • Facteurs contextuels, tels que le type de produit, une précision d’analyse des sentiments modérée.

Abe, 2005
S. AbeSupport vector machines for pattern classification, Vol. 2, Springer (2005)

Agarwal et al., 2011A. Agarwal, B. Xie, I. Vovsha, O. Rambow, R.J. PassonneauSentiment analysis of twitter dataProceedings of the Workshop on Language in Social Media (LSM 2011) (2011), pp. 30-38

Alaei et al., 2019A.R. Alaei, S. Becken, B. StanticSentiment analysis in tourism: Capitalizing on big dataJournal of Travel Research, 58 (2) (2019), pp. 175-191

Annett and Kondrak, 2008M. Annett, G. KondrakA Comparison of Sentiment Analysis Techniques: Polarizing Movie Blogs, Paper Presented at the Conference of the Canadian Society for Computational Studies of Intelligence (2008)

Appel et al., 2016O. Appel, F. Chiclana, J. Carter, H. FujitaA hybrid approach to the sentiment analysis problem at the sentence levelKnowledge-Based Systems, 108 (2016), pp. 110-124

Bulbul et al., 2014C. Bulbul, N. Gross, S. Shin, J. KatzWhen the path to purchase becomes the path to purposeThink with google (2014

Chang et al., 2017Y.-C. Chang, C.-H. Ku, C.-H. ChenSocial media analytics: Extracting and visualizing Hilton hotel ratings and reviews from TripAdvisorInternational Journal of Information Management (2017)

Chatterjee, 2019S. ChatterjeeExplaining customer ratings and recommendations by combining qualitative and quantitative user generated contentsDecision Support Systems, 119 (2019), pp. 14-22

Chen and Xie, 2008Y. Chen, J. XieOnline consumer review: Word-of-mouth as a new element of marketing communication mixManagement Science, 54 (3) (2008), pp. 477-491

Cheung and Lee, 2012C.M. Cheung, M.K. LeeWhat drives consumers to spread electronic word of mouth in online consumer-opinion platformsDecision Support Systems, 53 (1) (2012), pp. 218-225

Chopra et al., 2016D. Chopra, N. Joshi, I. MathurMastering natural language processing with pythonPackt Publishing Ltd. (2016)

Cicchetti, 1994D.V. CicchettiGuidelines, criteria, and rules of thumb for evaluating normed and standardized assessment instruments in psychologyPsychological Assessment, 6 (4) (1994), p. 284

Dang et al., 2009Y. Dang, Y. Zhang, H. ChenA lexicon-enhanced method for sentiment classification: An experiment on online product reviewsIEEE Intelligent Systems, 25 (4) (2009), pp. 46-53

Dang et al., 2010Y. Dang, Y. Zhang, H. ChenA lexicon-enhanced method for sentiment classification: An experiment on online product reviewsIEEE Intelligent Systems, 25 (4) (2010), pp. 46-53

De Maeyer, 2012P. De MaeyerImpact of online consumer reviews on sales and price strategies: A review and directions for future researchJournal of Product and Brand Management, 21 (2) (2012), pp. 132-139

Feldman, 2013R. FeldmanTechniques and applications for sentiment analysisCommunications of the ACM, 56 (4) (2013), pp. 82-89

Gao et al., 2015S. Gao, J. Hao, Y. FuThe Application and Comparison of Web Services for Sentiment Analysis in Tourism, Paper Presented at the 2015 12th International Conference on Service Systems and Service Management (ICSSSM) (2015)

Ghasemaghaei et al., 2018M. Ghasemaghaei, S.P. Eslami, K. Deal, K. HassaneinReviews’ length and sentiment as correlates of online reviews’ ratingsInternet Research, 28 (3) (2018), pp. 544-563

Giatsoglou et al., 2017M. Giatsoglou, M.G. Vozalis, K. Diamantaras, A. Vakali, G. Sarigiannidis, K.C. ChatzisavvasSentiment analysis leveraging emotions and word embeddingsExpert Systems with Applications, 69 (2017), pp. 214-224

Greco and Polli, 2019F. Greco, A. PolliEmotional text mining: Customer profiling in brand managementInternational Journal of Information Management (2019)

Griffin and Gonzalez, 1995D. Griffin, R. GonzalezCorrelational analysis of dyad-level data in the exchangeable casePsychological Bulletin, 118 (3) (1995), p. 430

Hasan et al., 2018A. Hasan, S. Moin, A. Karim, S. ShamshirbandMachine learning-based sentiment analysis for twitter accountsMathematical and Computational Applications, 23 (1) (2018), p. 11

Hu and Chen, 2016Y.-H. Hu, K. ChenPredicting hotel review helpfulness: The impact of review visibility, and interaction between hotel stars and review ratingsInternational Journal of Information Management, 36 (6) (2016), pp. 929-944

Hutto and Gilbert, 2014C.J. Hutto, E. GilbertVader: A Parsimonious Rule-Based Model for Sentiment Analysis of Social media Text, Paper Presented at the Eighth International AAAI Conference on Weblogs and Social media (2014)

Jeong et al., 2017B. Jeong, J. Yoon, J.-M. LeeSocial media mining for product planning: A product opportunity mining approach based on topic modeling and sentiment analysisInternational Journal of Information Management, 48 (2017), pp. 280-290

Kirilenko et al., 2018A.P. Kirilenko, S.O. Stepchenkova, H. Kim, X. LiAutomated sentiment analysis in tourism: Comparison of approachesJournal of Travel Research, 57 (8) (2018), pp. 1012-1025

Koo and Li, 2016T.K. Koo, M.Y. LiA guideline of selecting and reporting intraclass correlation coefficients for reliability researchJournal of Chiropractic Medicine, 15 (2) (2016), pp. 155-163

Kordzadeh, 2019N. KordzadehInvestigating bias in the online physician reviews published on healthcare organizations’ websitesDecision Support Systems, 118 (2019), pp. 70-82

Lak and Turetken, 2014P. Lak, O. TuretkenStar ratings versus sentiment analysis–a comparison of explicit and implicit measures of opinions2014 47th Hawaii International Conference on System Sciences, IEEE (2014), pp. 796-805

Lerner and Tiedens, 2006J.S. Lerner, L.Z. TiedensPortrait of the angry decision maker: How appraisal tendencies shape anger’s influence on cognitionJournal of Behavioral Decision Making, 19 (2) (2006), pp. 115-137

Liu, 2010B. LiuSentiment analysis and subjectivityHandbook of Natural Language Processing, 2 (2010) (2010), pp. 627-666

Liu, 2012B. LiuSentiment analysis and opinion miningSynthesis Lectures on Human Language Technologies, 5 (1) (2012), pp. 1-167

Maqsood et al., 2020H. Maqsood, I. Mehmood, M. Maqsood, M. Yasir, S. Afzal, F. Aadil, M. Selim, K. MuhammadA local and global event sentiment based efficient stock exchange forecasting using deep learningInternational Journal of Information Management, 50 (2020), pp. 432-451

Mills and Law, 2004J.E. Mills, R. LawHandbook of consumer behavior, tourism, and the internetPsychology Press (2004)

Moraes et al., 2013R. Moraes, J.F. Valiati, W.P.G. NetoDocument-level sentiment classification: An empirical comparison between SVM and ANNExpert Systems with Applications, 40 (2) (2013), pp. 621-633

Mudambi and Schuff, 2010S.M. Mudambi, D. SchuffWhat makes a helpful review? A study of customer reviews on Amazon. comMIS Quarterly, 34 (1) (2010), pp. 185-200CrossRef

Nasukawa and Yi, 2003T. Nasukawa, J. YiSentiment Analysis: Capturing Favorability Using Natural Language Processing, Paper Presented at the Proceedings of the 2nd International Conference on Knowledge Capture (2003)

Nelson, 1970P. NelsonInformation and consumer behaviorThe Journal of Political Economy, 78 (2) (1970), pp. 311-329

Nielsen, 2015M.A. NielsenNeural networks and deep learning, Vol. 2018, Determination press, San Francisco, CA, USA (2015)Pang and Lee, 2005B. Pang, L. LeeSeeing stars: Exploiting class relationships for sentiment categorization with respect to rating scalesProceedings of the 43rd Annual Meeting on Association for Computational Linguistics, Association for Computational Linguistics (2005), pp. 115-124

Pavlou and Dimoka, 2006P.A. Pavlou, A. DimokaThe nature and role of feedback text comments in online marketplaces: Implications for trust building, price premiums, and seller differentiationInformation Systems Research, 17 (4) (2006), pp. 392-414

Payne et al., 1993J.W. Payne, J.R. Bettman, E.J. JohnsonThe adaptive decision makerCambridge University Press (1993)

Philander and Zhong, 2016K. Philander, Y. ZhongTwitter sentiment analysis: Capturing sentiment from integrated resort tweetsInternational Journal of Hospitality Management, 55 (2016) (2016), pp. 16-24

Pirolli, 2007P. PirolliInformation foraging theory: Adaptive interaction with informationOxford University Press (2007)Google Sch

olarPozzi et al., 2016F.A. Pozzi, E. Fersini, E. Messina, B. LiuSentiment analysis in social networksMorgan Kaufmann (2016)

Prabowo and Thelwall, 2009R. Prabowo, M. ThelwallSentiment analysis: A combined approachJournal of Informetrics, 3 (2) (2009), pp. 143-157

Pradhan et al., 2016V.M. Pradhan, J. Vala, P. BalaniA survey on Sentiment Analysis Algorithms for opinion miningInternational Journal of Computer Applications, 133 (9) (2016), pp. 7-11

Qiu et al., 2012L. Qiu, J. Pang, K.H. LimEffects of conflicting aggregated rating on eWOM review credibility and diagnosticity: The moderating role of review valenceDecision Support Systems, 54 (1) (2012), pp. 631-643

Ragini et al., 2018J.R. Ragini, P.R. Anand, V. BhaskarBig data analytics for disaster response and recovery through sentiment analysisInternational Journal of Information Management, 42 (2018), pp. 13-24

Rathore and Ilavarasan, 2020A.K. Rathore, P.V. IlavarasanPre-and post-launch emotions in new product development: Insights from twitter analytics of three productsInternational Journal of Information Management, 50 (2020), pp. 111-127

Ribeiro et al., 2016F.N. Ribeiro, M. Araújo, P. Gonçalves, M.A. Gonçalves, F. BenevenutoSentibench-a benchmark comparison of state-of-the-practice sentiment analysis methodsEPJ Data Science, 5 (1) (2016), p. 23

Roussinov and Turetken, 2009D. Roussinov, O. TuretkenExploring models for semantic category verificationInformation Systems, 34 (8) (2009), pp. 753-765

Saif et al., 2016H. Saif, Y. He, M. Fernandez, H. AlaniContextual semantics for sentiment analysis of TwitterInformation Processing & Management, 52 (1) (2016), pp. 5-19

Schuckert et al., 2015M. Schuckert, X. Liu, R. LawHospitality and tourism online reviews: Recent trends and future directionsJournal of Travel & Tourism Marketing, 32 (5) (2015), pp. 608-62

Schumaker et al., 2012R.P. Schumaker, Y. Zhang, C.-N. Huang, H. ChenEvaluating sentiment in financial news articlesDecision Support Systems, 53 (3) (2012), pp. 458-464

Taboada et al., 2011M. Taboada, J. Brooke, M. Tofiloski, K. Voll, M. StedeLexicon-based methods for sentiment analysisComputational Linguistics, 37 (2) (2011), pp. 267-307

Thavasimani and Missier, 2016P. Thavasimani, P. MissierFacilitating Reproducible Research by Investigating Computational Metadata, Paper Presented at the 2016 IEEE International Conference on Big Data (Big Data) (2016)

Valdivia et al., 2017A. Valdivia, M.V. Luzón, F. HerreraSentiment analysis in tripadvisorIEEE Intelligent Systems, 32 (4) (2017), pp. 72-77

Vijayarani and Janani, 2016S. Vijayarani, R. JananiText mining: Open source tokenization tools-an analysisAdvanced Computational Intelligence: An International Journal (ACII), 3 (1) (2016), pp. 37-47

Wang et al., 2015Y. Wang, J. Yuan, J. LuoAmerica Tweets China: A Fine-Grained Analysis of the State and Individual Characteristics Regarding Attitudes Towards China, Paper Presented at the 2015 IEEE International Conference on Big Data (Big Data). (2015)

Wilson et al., 2005T. Wilson, J. Wiebe, P. HoffmannRecognizing contextual polarity in phrase-level sentiment analysisProceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (2005), pp. 347-354

Wu et al., 2019P. Wu, X. Li, S. Shen, D. HeSocial media opinion summarization using emotion cognition and convolutional neural networksInternational Journal of Information Management (2019)

Ye et al., 2009Q. Ye, Z. Zhang, R. LawSentiment classification of online reviews to travel destinations by supervised machine learning approachesExpert Systems with Applications, 36 (3) (2009), pp. 6527-6535

Zhang et al., 2011Z. Zhang, Q. Ye, Z. Zhang, Y. LiSentiment classification of Internet restaurant reviews written in CantoneseExpert Systems with Applications, 38 (6) (2011), pp. 7674-7682

Zhao et al., 2012J. Zhao, L. Dong, J. Wu, K. XuMoodlens: An Emoticon-Based Sentiment Analysis System for Chinese Tweets, Paper Presented at the Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2012)

Zhu and Zhang, 2010F. Zhu, X. ZhangImpact of online consumer reviews on sales: The moderating role of product and consumer characteristicsJournal of Marketing, 74 (2) (2010), pp. 133-148