Attribute Sentiment Scoring with Online Text Reviews: Accounting for Language Structure and Missing Attributes
The DOI matches its Crossref record; 61 of the 62 references it cites were found in a registry or an index, and 1 are not checked yet.
Abstract
The authors address two significant challenges in using online text reviews to obtain fine-grained, attribute-level sentiment ratings. First, in contrast to methods that rely on word frequency, they develop a deep learning convolutional–long short-term memory hybrid model to account for language structure. The convolutional layer accounts for spatial structure (adjacent word groups or phrases), and long short-term memory accounts for the sequential structure of language (sentiment distributed and modified across nonadjacent phrases). Second, they address the problem of missing attributes in text when constructing attribute sentiment scores, as reviewers write about only a subset of attributes and remain silent on others. They develop a model-based imputation strategy using a structural model of heterogeneous rating behavior. Using Yelp restaurant review data, they show superior attribute sentiment scoring accuracy with their model. They identify three reviewer segments with different motivations: status seeking, altruism/want voice, and need to vent/praise. Surprisingly, attribute mentions in reviews are driven by the need to inform and vent/praise rather than by attribute importance. The heterogeneous model-based imputation performs better than other common imputations and, importantly, leads to managerially significant corrections in restaurant attribute ratings. More broadly, the results suggest that social science research should pay more attention to reducing measurement…
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Aspect-based sentiment analysis can help firms understand consumer needs [62] and motivations [11].”
From Sentiment Analysis in the Age of Generative AI (2024) · cites this paper as [11]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“LSTM is a variant of the recurrent neural networks (RNN) that specializes in handling longer contextual information (Hochreiter and Schmidhuber 1997).”
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 6×
“Table A1: Match and Attention Comparison: Treatment (Attribute Scores) N Mean (SD) Match Attention Treatment 74 0.7 (0.46) 0.94 (0.46) Control 90 0.38 (0.49) 0.83(0.49) p 0.01 p 0.05 Table A2: Top attribute and sentiment words Attribute Attribute words Positive Sentiment Words Negative Sentiment Words Food Food, chick…”
Influentialnull (2016) · Philosophy Study · doi:10.17265/2159-5313/2016.09.003 · Cited by 28,317
Convolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 3×
“Polarity Reversal Confusion Matrix for Sentiment Accuracy: Though the CS literature typically uses accuracy as a performance metric for the fine-grained (multi-class) sentiment classification (Socher et al. 2013, Kim 2014), there can be other useful metrics of performance.”
Advances in Neural Information Processing Systems 25
Zhang, Y., Sutton, C. A., Storkey, A., & Zoubin Ghahramani, A. (2012) · Cited by 12,653
RUBIN, D. B. (1976) · Biometrika · doi:10.1093/biomet/63.3.581 · Cited by 9,925
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878
The Effect of Word of Mouth on Sales: Online Book Reviews
Chevalier, J. A., & Mayzlin, D. (2006) · Journal of Marketing Research · doi:10.1509/jmkr.43.3.345 · Cited by 6,003
Harris, Z. S. (1954) · WORD · doi:10.1080/00437956.1954.11659520 · Cited by 4,807
Statistical Analysis With Missing Data
Ghosh, S. (1988) · Technometrics · doi:10.1080/00401706.1988.10488446 · Cited by 4,576 · cited 1×
“The most common approach is to then intro- 10 duce new identifying restrictions by explicitly justifying a model of missingness for the context at hand, and estimate the joint model of missingness with the behavioral model (Little and Rubin 2019, Mohan and Pearl 2018).”
Lexicon-based methods for sentiment analysis
Taboada, M., Brooke, J., Tofiloski, M., Voll, K., & Stede, M. (2011) · Computational Linguistics · doi:10.1162/coli_a_00049 · Cited by 3,301
Twitter as a Corpus for Sentiment Analysis and Opinion Mining
Pak, A., & Paroubek, P. (2010) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/47akcj8foo4d · Cited by 2,704 · cited 1×
“These are more detailed relative to previous studies (Pak and Paroubek 2010, Berger et al. 2010) that focus on two (i.e. positive and negative) or three levels (i.e. positive, neutral and negative) of sentiments.”
Using Online Conversations to Study Word-of-Mouth Communication
Godes, D., & Mayzlin, D. (2004) · Marketing Science · doi:10.1287/mksc.1040.0071 · Cited by 2,601
Response strategies for coping with the cognitive demands of attitude measures in surveys
Krosnick, J. A. (1991) · Applied Cognitive Psychology · doi:10.1002/acp.2350050305 · Cited by 2,460 · cited 1×
“This may obviate the need to convert text to numerical attribute sentiment scores; but a key disadvantage is that attribute level questions vastly reduce response rates and quality because of the additional time and cognitive costs on the reviewers (Krosnick 1991, Huang et al. 2015).”
Zhu, F., & Zhang, X. (. (2010) · Journal of Marketing · doi:10.1509/jm.74.2.133 · Cited by 2,363
Do online reviews matter? — An empirical investigation of panel data
Duan, W., Gu, B., & Whinston, A. B. (2008) · Decision Support Systems · doi:10.1016/j.dss.2008.04.001 · Cited by 1,675 · cited 1×
“Some of the early research on user-generated (UGC) content in marketing (e.g., Chevalier and Mayzlin 2006, Dhar and Chang 2009, Duan et al. 2008, Ghose and Ipeirotis 2007, Onishi and Manchanda 2012) uses quantitative metrics like review ratings, volume and word count to infer the impact of UGC on…”
Techniques and applications for sentiment analysis
Feldman, R. (2013) · Communications of the ACM · doi:10.1145/2436256.2436274 · Cited by 1,489
Word of mouth and interpersonal communication: A review and directions for future research
Berger, J. (2014) · Journal of Consumer Psychology · doi:10.1016/j.jcps.2014.05.002 · Cited by 1,469 · cited 2×
“Informativeness: Reviewers write on review platforms to share their experience with others, so one of the major motivations could be to inform or add new information (Berger 2014).”
Learning to Classify Text Using Support Vector Machines
Joachims, T. (2002) · Springer eBooks · doi:10.1007/978-1-4615-0907-3 · Cited by 1,366 · cited 9×
“This is in line with past literature that has shown that SVMs are the best Machine Learning based text classifiers.”
InfluentialFake It Till You Make It: Reputation, Competition, and Yelp Review Fraud
Luca, M., & Zervas, G. (2016) · Management Science · doi:10.1287/mnsc.2015.2304 · Cited by 1,263
Gentzkow, M., Kelly, B., & Taddy, M. (2019) · Journal of Economic Literature · doi:10.1257/jel.20181020 · Cited by 1,236 · cited 2×
“In particular, we note that the large improvements in sentiment scoring accuracy (for both valence and fine grained) using our method suggests that social science research using text analysis (Gentzkow et al. 2019) should pay more attention to advanced NLP methods to reduce measurement error in their constructed varia…”
Self-Selection and Information Role of Online Product Reviews
Li, X., & Hitt, L. M. (2008) · Information Systems Research · doi:10.1287/isre.1070.0154 · Cited by 1,125
Handbook of Natural Language Processing
(2010) · Chapman & Hall/CRC eBooks · doi:10.1201/9781420085938 · Cited by 1,092
Deriving the Pricing Power of Product Features by Mining Consumer Reviews
Archak, N., Ghose, A., & Ipeirotis, P. G. (2011) · Management Science · doi:10.1287/mnsc.1110.1370 · Cited by 1,007
Promotional Reviews: An Empirical Investigation of Online Review Manipulation
Mayzlin, D., Dover, Y., & Chevalier, J. (2014) · American Economic Review · doi:10.1257/aer.104.8.2421 · Cited by 937
Survey on Aspect-Level Sentiment Analysis
Schouten, K., & Frasincar, F. (2016) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2015.2485209 · Cited by 832 · cited 1×
“We note that the computer science literature in fine-grained sentiment scoring is still evolving and it remains an open problem in natural language processing (Schouten and Frasincar 2015).”
Deep Pyramid Convolutional Neural Networks for Text Categorization
Johnson, R., & Zhang, T. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1052 · Cited by 823
Mittal, V., Kumar, P., & Tsiros, M. (1999) · Journal of Marketing · doi:10.1177/002224299906300206 · Cited by 805
Tirunillai, S., & Tellis, G. J. (2014) · Journal of Marketing Research · doi:10.1509/jmr.12.0106 · Cited by 774
Mine Your Own Business: Market-Structure Surveillance Through Text Mining
Netzer, O., Feldman, R., Goldenberg, J., & Fresko, M. (2012) · Marketing Science · doi:10.1287/mksc.1120.0713 · Cited by 750 · cited 6×
“Another research stream focused on using UGC in blogs and review forums to extract insights around customer needs and brand positioning (e.g., Büschken and Allenby 2016; Lee and Bradlow 2011; Netzer et al. 2012; Tirunillai and Tellis 2014).”
InfluentialA new ANEW: Evaluation of a word list for sentiment analysis in microblogs
Nielsen, F. Å. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.2903 · Cited by 712 · cited 2×
“For e.g., AFINN lexicon (Nielsen 2011) and Stanford Sentiment Treebank (Socher et al. 2013) have words and phrases with 5-levels of sentiment classification, however, they are built on Twitter and rotten.tomatoes.com movie review dataset respectively and have limited overlap of words and attributes…”
Positive Effects of Negative Publicity: When Negative Reviews Increase Sales
Berger, J., Sorensen, A. T., & Rasmussen, S. J. (2010) · Marketing Science · doi:10.1287/mksc.1090.0557 · Cited by 658
Latent aspect rating analysis on review text data: a rating regression approach
Wang, H., Lu, Y., & Zhai, C. (2010) · Proceedings of the 16th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/1835804.1835903 · Cited by 650
A C-LSTM Neural Network for Text Classification
Zhou, C., Sun, C., Liu, Z., & Lau, F. C. M. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.08630 · Cited by 641 · cited 2×
“Consequently, deep learning models (Kim 2014; Socher et al. 2013; Zhou et al. 2015) combined with meaning-infused word vectors (Mikolov et al.”
Dimensional Sentiment Analysis Using a Regional CNN-LSTM Model
Wang, J., Yu, L.-C., Lai, K. R., & Zhang, X. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) · doi:10.18653/v1/p16-2037 · Cited by 584 · cited 2×
“In many challenging text and image classification problems (Wang et al. 2016), hybrid models that combine the strengths and mitigate the shortcomings of each individual model have been found to improve performance.”
Does Chatter Matter? The Impact of User-Generated Content on Music Sales
Dhar, V., & Chang, E. A. (2009) · Journal of Interactive Marketing · doi:10.1016/j.intmar.2009.07.004 · Cited by 519 · cited 1×
“Some of the early research on user-generated (UGC) content in marketing (e.g., Chevalier and Mayzlin 2006, Dhar and Chang 2009, Duan et al. 2008, Ghose and Ipeirotis 2007, Onishi and Manchanda 2012) uses quantitative metrics like review ratings, volume and word count to infer the impact of UGC on…”
Identifying Customer Needs from User-Generated Content
Timoshenko, A., & Hauser, J. R. (2019) · Marketing Science · doi:10.1287/mksc.2018.1123 · Cited by 513
Beyond the Stars: Improving Rating Predictions using Review Text Content.
Ganu, G., Elhadad, N., & Marian, A. (2009) · International Workshop on the Web and Databases · Cited by 498
Automated Marketing Research Using Online Customer Reviews
Lee, T. Y., & Bradlow, E. T. (2011) · Journal of Marketing Research · doi:10.1509/jmkr.48.5.881 · Cited by 460
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing
Yarowsky, D., Baldwin, T., Korhonen, A., Livescu, K., & Bethard, S. J. (2013) · Empirical Methods in Natural Language Processing · Cited by 422
Insufficient effort responding: Examining an insidious confound in survey data.
Huang, J. L., Liu, M., & Bowling, N. A. (2015) · Journal of Applied Psychology · doi:10.1037/a0038510 · Cited by 416
Dimensional commensurability and cue utilization in comparative judgment
Slovic, P., & MacPhillamy, D. (1974) · Organizational Behavior and Human Performance · doi:10.1016/0030-5073(74)90013-0 · Cited by 397
(2011) · Econometrica · doi:10.3982/ecta7743 · Cited by 382 · cited 1×
“We adapt the approach in Arcidiacono and Miller (2011) to estimate the parameters with unobserved heterogeneity.”
Sentence-Based Text Analysis for Customer Reviews
Büschken, J., & Allenby, G. M. (2016) · Marketing Science · doi:10.1287/mksc.2016.0993 · Cited by 351 · cited 4×
“4 Tellis (2014), Hollenbeck (2018), Puranam et al. (2017) and Büschken and Allenby (2016).”
InfluentialWisdom of crowds: Conducting importance-performance analysis (IPA) through online reviews
Bi, J.-W., Liu, Y., Fan, Z.-P., & Zhang, J. (2019) · Tourism Management · doi:10.1016/j.tourman.2018.09.010 · Cited by 330
Designing novel review ranking systems: predicting the usefulness and impact of reviews
Ghose, A., & Ipeirotis, P. G. (2007) · Proceedings of the ninth international conference on Electronic commerce · doi:10.1145/1282100.1282158 · Cited by 322
Mining Brand Perceptions from Twitter Social Networks
Culotta, A., & Cutler, J. (2016) · Marketing Science · doi:10.1287/mksc.2015.0968 · Cited by 254
Marketing activity, blogging and sales
Onishi, H., & Manchanda, P. (2012) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2011.11.003 · Cited by 211
Finite Mixture Distributions, Sequential Likelihood and the EM Algorithm
Arcidiacono, P., & Jones, J. B. (2003) · Econometrica · doi:10.1111/1468-0262.00431 · Cited by 197 · cited 1×
“We then nest the above procedure within another iterative EM procedure as in Arcidiacono and Jones (2003) to estimate the mixture model with unobserved heterogeneity.”
(2015) · arXiv (Cornell University) · Cited by 182
Liu, X., Lee, D., & Srinivasan, K. (2019) · Journal of Marketing Research · doi:10.1177/0022243719866690 · Cited by 178 · cited 1×
“Recently, marketing scholars have used deep learning models for text analysis to answer important questions such as need identification (Timoshenko and Hauser 2018) and the impact of reading reviews on particular attributes on purchasing decisions (Liu et al. 2019), but their focus is not on fine-grained sentiment and…”
Graphical Models for Processing Missing Data
Mohan, K., & Pearl, J. (2021) · Journal of the American Statistical Association · doi:10.1080/01621459.2021.1874961 · Cited by 158
Online Reputation Mechanisms and the Decreasing Value of Chain Affiliation
Hollenbeck, B. (2018) · Journal of Marketing Research · doi:10.1177/0022243718802844 · Cited by 142 · cited 2×
“4 Tellis (2014), Hollenbeck (2018), Puranam et al. (2017) and Büschken and Allenby (2016).”
Attribute performance and customer satisfaction over time: evidence from two field studies
Mittal, V., Katrichis, J. M., & Kumar, P. (2001) · Journal of Services Marketing · doi:10.1108/eum0000000005655 · Cited by 134
Peloza, J., Ye, C., & Montford, W. J. (2015) · Journal of Public Policy & Marketing · doi:10.1509/jppm.13.037 · Cited by 127
Puranam, D., Narayan, V., & Kadiyali, V. (2017) · Marketing Science · doi:10.1287/mksc.2017.1048 · Cited by 102
Examining the Relevance of Online Customer Textual Reviews on Hotels’ Product and Service Attributes
Xu, X. (2018) · Journal of Hospitality & Tourism Research · doi:10.1177/1096348018764573 · Cited by 100 · cited 1×
“…and (even) nursing homes, crowd-sourced online review platforms have emerged as an alternative and less expensive source of scalable, real-time feedback for businesses to listen in on their markets for both performance tracking as well as competitive benchmarking (e.g., Xu 2019, Li et al. 2019).”
Improved Sentence Modeling using Suffix Bidirectional LSTMPreprint
Brahma, S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.07340 · Cited by 46 · cited 1×
“The accuracy of the convolutional-LSTM in the task of 5-level sentiment classification is 50%—lower than state of art accuracy 56% reported in (Brahma 2018), but on a different dataset for which we do not know the differential mix of “hard” versus “easy” sentences in the corpus.”
Improving Text Analysis Using Sentence Conjunctions and Punctuation
Büschken, J., & Allenby, G. M. (2020) · Marketing Science · doi:10.1287/mksc.2019.1214 · Cited by 42
How Endogenous Crowd Formation Undermines the Wisdom of the Crowd in Online Ratings
Mens, G. L., Kovács, B., Avrahami, J., & Kareev, Y. (2018) · Psychological Science · doi:10.1177/0956797618775080 · Cited by 37
Digitizing Doctor Demand: The Impact of Online Reviews on Doctor Choice
Vats, S. (2014) · Health & Healthcare in America: From Economics to Policy · Cited by 27
Filling in the Blanks: What Restaurant Patrons Assume About Missing Sanitation Inspection Grades
Gurney, N., & Loewenstein, G. F. (2019) · Journal of Public Policy & Marketing · doi:10.1177/0743915619875419 · Cited by 15
Research works printed but not linked: 4
- Athey Susan, Bayati Mohsen, Doudchenko Nikolay, Imbens Guido, Khosravi Khashayar (2018), “Matrix Completion Methods for Causal Panel Data Models. Technical Report,” Working Paper 25132, National Bureau of Economic Research, https://www.nber.org/system/files/working_papers/w25132/w25132.pdf.
- Dubois David, Chae InYoung, Niessing Joerg, Wee Jean (2016), “AccorHotels and the Digital Transformation: Enriching Experience Through Content Strategies Along the Customer Journey,” case study, INSEAD Business School.
- Goodfellow Ian J, Bengio Yoshua, Courville Aaron C. (2016), Deep Learning. Adaptive Computation and Machine Learning. Cambridge, MA: MIT Press.
- Li Yuanchen Lauren X. Xiaoyuan Lu Susan (2020) “Do Yelp Reviews Influence Consumer Choice in the Presence of Government Ratings? Evidence from US Nursing Homes ” paper presented at INFORMS Conference on Information Systems and Technology (CIST 2020) (November 7).
Cited by
Machine learning and AI in marketing–Connecting computing power to human insights
Ma, L., & Sun, B. (2020) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2020.04.005 · Cited by 602
More than a Feeling: Accuracy and Application of Sentiment Analysis
Hartmann, J., Heitmann, M., Siebert, C., & Schamp, C. (2023) · International Journal of Research in Marketing · doi:10.1016/j.ijresmar.2022.05.005 · Cited by 356
Shrestha, Y. R., Krishna, V., & von Krogh, G. (2021) · Journal of Business Research · doi:10.1016/j.jbusres.2020.09.068 · Cited by 331
Sentiment Analysis in the Age of Generative AI
Krugmann, J. O., & Hartmann, J. (2024) · Customer Needs and Solutions · doi:10.1007/s40547-024-00143-4 · Cited by 189
AI–Human Hybrids for Marketing Research: Leveraging Large Language Models (LLMs) as Collaborators
Arora, N., Chakraborty, I., & Nishimura, Y. (2025) · Journal of Marketing · doi:10.1177/00222429241276529 · Cited by 162
“Methods have evolved from simple lexicons or word lists (Pennebaker and King 1999) to more scalable machine learning (Tirunillai and Tellis 2014) and deep learning methods (Chakraborty, Kim, and Sudhir 2022; Timoshenko and Hauser 2019; Wang et al. 2022) that use word embeddings.”
Self-citation
Metadata
- Authors
- Chakraborty, I., Kim, M., & Sudhir, K.
- Corresponding author
- Chakraborty, Ishita
- Kim, Minkyung
- Sudhir, K.
- Venue
- Journal of Marketing Research
- Publisher
- SAGE Publications
- Published
- 2022-01-04
- Volume
- 59
- Issue
- 3
- Pages
- 600-622
- ISSN
- 0022-2437 (ISSN-L)
- 1547-7193
- OpenAlex
- W3201959652
- Cited by
- 84
- References
- 61
- Citations by year
- 2026: 12 · 2025: 25 · 2024: 22 · 2023: 14 · 2022: 7
- FWCI
- 3.89
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- journals.sagepub.com/page/policies/text-and-data-mining-license (tdm)
- Locations
- Journal of Marketing Research (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › Business, Management and Accounting › Marketing › Digital Marketing and Social Media
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Keywords
- convolutional long short-term memory, language structure, model-based imputation, measurement error
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.