Gender bias in sentiment analysis
Open accessAbstract
Purpose: The purpose of this paper is to test if there are biases in lexical sentiment analysis accuracy between reviews authored by males and females. Design/methodology/approach: This paper uses data sets of TripAdvisor reviews of hotels and restaurants in the UK written by UK residents to contrast the accuracy of lexical sentiment analysis for males and females. Findings: Male sentiment is harder to detect because it is less explicit. There was no evidence that this problem could be solved by gender-specific lexical sentiment analysis. Research limitations/implications: Only one lexical sentiment analysis algorithm was used. Practical implications: Care should be taken when drawing conclusions about gender differences from automatic sentiment analysis results. When comparing opinions for product aspects that appeal differently to men and women, female sentiments are likely to be overrepresented, biasing the results. Originality/value: This is the first evidence that lexical sentiment analysis is less able to detect the opinions of one gender than another.
Integrity signals
Registry
Cites
Statistics
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?
Performances of sentiment analysis of male- and female-authored texts are extremely variable and potentially biased.
“performances of sentiment analysis of male- and female-authored texts are extremely variable80 and potentially biased81.”
From Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare (2020) · cites this paper as [80]
Cites
Opinion Mining and Sentiment Analysis
Pang, B., & Lee, L. (2008) · now publishers, Inc. eBooks · doi:10.1561/9781601981516 · Cited by 6,957 · see citing works
boyd, D., & Crawford, K. (2012) · Information, Communication & Society · doi:10.1080/1369118x.2012.678878 · Cited by 5,479 · see citing works
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 · see citing works
Sentiment Analysis and Opinion Mining
Zhang, L., & Liu, B. (2017) · Encyclopedia of Machine Learning and Data Mining · doi:10.1007/978-1-4899-7687-1_907 · Cited by 3,299 · see citing works
SentiWordNet 3.0: An Enhanced Lexical Resource for Sentiment Analysis and Opinion Mining
Baccianella, S., Esuli, A., & Sebastiani, F. (2010) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/2jktnrykui9s · Cited by 2,691 · see citing works
Turney, P. D. (2001) · Annual Meeting of the Association for Computational Linguistics (ACL) · doi:10.3115/1073083.1073153 · Cited by 2,354 · cited 1× · see citing works
“Machine learning techniques typically split reviews into collections of words or phrases and then train an algorithm to detect patterns of association with sentiment (e.g., Turney, 2002).”
BackgroundThumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of ReviewsPreprint
Turney, P. D. (2002) · arXiv (Cornell University) · doi:10.48550/arxiv.cs/0212032 · Cited by 1,584 · cited 1× · see citing works
“Machine learning techniques typically split reviews into collections of words or phrases and then train an algorithm to detect patterns of association with sentiment (e.g., Turney, 2002).”
BackgroundSentiment strength detection in short informal text
Thelwall, M., Buckley, K., Paltoglou, G., Cai, D., & Kappas, A. (2010) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21416 · Cited by 1,449 · see citing works
Self-citationSentiment strength detection for the social web
Thelwall, M., Buckley, K., & Paltoglou, G. (2012) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.21662 · Cited by 1,062 · see citing works
Self-citationTirunillai, S., & Tellis, G. J. (2014) · Journal of Marketing Research · doi:10.1509/jmr.12.0106 · Cited by 780 · cited 1× · see citing works
“It is widely used within marketing and customer relations management through the online monitoring of customer opinions towards products and services expressed in social media or review sites (Pekar & Ou, 2008; Schweidel & Moe, 2014; Tirunillai & Tellis, 2014).”
BackgroundTufekci, Z. (2014) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v8i1.14517 · Cited by 780 · cited 2× · see citing works
“Although the potential for bias in big data analyses has previously been noted (Bollier, 2010; Boyd & Crawford, 2012; Hofacker, Malthouse, & Sultan, 2016; Tufekci, 2014), the source found here is more subtle than demographic differences in the people that express opinions online and is not due to analyst bias but is a…”
BackgroundAutomatically Categorizing Written Texts by Author Gender
Koppel, M. (2002) · Literary and Linguistic Computing · doi:10.1093/llc/17.4.401 · Cited by 623 · see citing works
Discriminating Gender on Twitter
Burger, J. D., Henderson, J. C., Kim, G., & Zarrella, G. (2011) · Cited by 581 · see citing works
The relationship between customer satisfaction and loyalty: Cross-industry differences
Grønholdt, L., Martensen, A., & Kristensen, K. (2000) · Total Quality Management · doi:10.1080/09544120050007823 · Cited by 519 · see citing works
Opinion Mining and Sentiment Analysis
Liu, B. (2011) · Springer eBooks · doi:10.1007/978-3-642-19460-3_11 · Cited by 484 · see citing works
Forecasting elections with non-representative polls
Wang, W., Rothschild, D., Goel, S., & Gelman, A. (2015) · International Journal of Forecasting · doi:10.1016/j.ijforecast.2014.06.001 · Cited by 371 · see citing works
Navigating by the Stars: Investigating the Actual and Perceived Validity of Online User Ratings
de Langhe, B., Fernbach, P. M., & Lichtenstein, D. R. (2015) · Journal of Consumer Research · doi:10.1093/jcr/ucv047 · Cited by 329 · see citing works
Listening in on Social Media: A Joint Model of Sentiment and Venue Format Choice
Schweidel, D. A., & Moe, W. W. (2014) · Journal of Marketing Research · doi:10.1509/jmr.12.0424 · Cited by 323 · cited 1× · see citing works
“It is widely used within marketing and customer relations management through the online monitoring of customer opinions towards products and services expressed in social media or review sites (Pekar & Ou, 2008; Schweidel & Moe, 2014; Tirunillai & Tellis, 2014).”
BackgroundBig data analytics for knowledge generation in tourism destinations – A case from Sweden
Fuchs, M., Höpken, W., & Lexhagen, M. (2014) · Journal of Destination Marketing & Management · doi:10.1016/j.jdmm.2014.08.002 · Cited by 308 · see citing works
Big Data and consumer behavior: imminent opportunities
Hofacker, C. F., Malthouse, E. C., & Sultan, F. (2016) · Journal of Consumer Marketing · doi:10.1108/jcm-04-2015-1399 · Cited by 255 · see citing works
Ma, L., Sun, B., & Kekre, S. (2015) · Marketing Science · doi:10.1287/mksc.2015.0912 · Cited by 252 · see citing works
Measuring and Managing Consumer Sentiment in an Online Community Environment
Homburg, C., Ehm, L., & Artz, M. (2015) · Journal of Marketing Research · doi:10.1509/jmr.11.0448 · Cited by 196 · see citing works
Exploring Demographic Language Variations to Improve Multilingual Sentiment Analysis in Social Media
Volkova, S., Wilson, T., & Yarowsky, D. (2013) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d13-1187 · Cited by 191 · see citing works
On the impact of emotions on author profiling
Rangel, F., & Rosso, P. (2016) · Information Processing & Management · doi:10.1016/j.ipm.2015.06.003 · Cited by 92 · cited 1× · see citing works
“More generally, there are gender differences in the extent to which sentiment is expressed in the social web (Bagić Babac & Podobnik, 2016; Rangel & Rosso, 2016; Thelwall, Wilkinson, & Uppal, 2010; Volkova & Yoram, 2015), perhaps echoing common stylistic differences (e.g., Koppel, Argamon, &…”
BackgroundVolkova, S., & Bachrach, Y. (2015) · Cyberpsychology Behavior and Social Networking · doi:10.1089/cyber.2014.0609 · Cited by 71 · cited 1× · see citing works
“The same is true for some other words and linguistic features, such as exclamation marks (Burger, Henderson, Kim, & Zarrella, 2011; Volkova & Yarowsky, 2014).”
BackgroundDiscovery of subjective evaluations of product features in hotel reviews
Pekar, V., & Ou, S. (2008) · Journal Of Vacation Marketing · doi:10.1177/1356766707087522 · Cited by 71 · cited 1× · see citing works
“It is widely used within marketing and customer relations management through the online monitoring of customer opinions towards products and services expressed in social media or review sites (Pekar & Ou, 2008; Schweidel & Moe, 2014; Tirunillai & Tellis, 2014).”
BackgroundWeb crawling ethics revisited: Cost, privacy, and denial of service
Thelwall, M. A., & Stuart, E. (2006) · Journal of the American Society for Information Science and Technology · doi:10.1002/asi.20388 · Cited by 67 · see citing works
Self-citationCompetitive intelligence in social media Twitter: iPhone 6 vs. Galaxy S5
Kim, Y., Dwivedi, R., Zhang, J., & Jeong, S. R. (2016) · Online Information Review · doi:10.1108/oir-03-2015-0068 · Cited by 59 · see citing works
Weber, I. G., Ukkonen, A., & Gionis, A. (2012) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/2124295.2124369 · Cited by 45 · see citing works
What Men Say, What Women Hear: Finding Gender-Specific Meaning Shades
Mihalcea, R. F., & Garimella, A. (2016) · IEEE Intelligent Systems · doi:10.1109/mis.2016.71 · Cited by 36 · cited 1× · see citing works
“This is a similar rationale to that of a genderaware word sense disambiguation program for blog posts (Mihalcea & Garimella, 2016).”
ResultA sentiment analysis of who participates, how and why, at social media sport websites
Babac, M. B., & Podobnik, V. (2016) · Online Information Review · doi:10.1108/oir-02-2016-0050 · Cited by 32 · cited 1× · see citing works
“More generally, there are gender differences in the extent to which sentiment is expressed in the social web (Bagić Babac & Podobnik, 2016; Rangel & Rosso, 2016; Thelwall, Wilkinson, & Uppal, 2010; Volkova & Yoram, 2015), perhaps echoing common stylistic differences (e.g., Koppel, Argamon, &…”
BackgroundThe Good, the Bad and the Neutral: Affective Profile in Dialog System-User Communication
Skowron, M., Rank, S., Theunis, M., & Sienkiewicz, J. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24600-5_37 · Cited by 28 · see citing works
Who creates value in a user innovation community? A case study of MyStarbucksIdea.com
Lee, H., & Suh, Y. (2016) · Online Information Review · doi:10.1108/oir-04-2015-0132 · Cited by 22 · cited 1× · see citing works
“Online Information Review. doi: 10.1108/OIR-052017-0139 than from another, and a system that detects sentiment to help select good ideas (Lee & Suh, 2016) might have a bias towards the opinions of one gender.”
BackgroundInfluentialTweets speak louder than leaders and masses
Gul, S., Mahajan, I. M., Nisa, N. T., Shah, T. A., Jan, A., & Ahmad, S. (2016) · Online Information Review · doi:10.1108/oir-10-2015-0330 · Cited by 22 · see citing works
Book genre and author gender: Romance>Paranormal‐Romance to Autobiography>Memoir
Thelwall, M. A. (2016) · Journal of the Association for Information Science and Technology · doi:10.1002/asi.23768 · Cited by 21 · see citing works
Self-citation
Flagged first, then by citations
4 of the 39 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050 · see citing works
“…(2015); Blodgett et al. (2016); Blodgett and O’Connor (2017); Blodgett et al. (2018); Curry and Rieser (2018); Dixon et al. (2018); Park et al. (2018); Thelwall (2018); Webster et al. (2018); Badjatiya et al. (2019); Bagdasaryan et al. (2019); Bamman et al. (2019); Bhargava and Forsyth (2019); Cao…”
Sex and gender differences and biases in artificial intelligence for biomedicine and healthcare
Cirillo, D., Catuara-Solarz, S., Morey, C., Guney, E., Subirats, L., Mellino, S., Gigante, A., Valencia, A., Rementeria, M. J., Chadha, A. S., et al. (2020) · npj Digital Medicine · doi:10.1038/s41746-020-0288-5 · Cited by 553 · see citing works
Mohammad, S. M. (2016) · Emotion Measurement · doi:10.1016/b978-0-08-100508-8.00009-6 · Cited by 391 · see citing works
“ricans names as being more angry than sentences that mention European American names, and sentences that mention women as being more emotional (more happy / more sad) than sentences that mention men. Thelwall (2018) found that automatic sentiment analysis systems are somewhat less accurate on customer reviews written…”
BackgroundExploring gender biases in ML and AI academic research through systematic literature review
Shrestha, S., & Das, S. (2022) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2022.976838 · Cited by 105 · see citing works
“…resolution, the majority of detection methods discussed in these papers target NLP tasks like sentiment analysis (Kiritchenko and Mohammad, 2018; Thelwall, 2018; Sarraf et al., 2021), information retrieval (Rekabsaz and Schedl, 2020), Word Embeddings (Leavy, 2018; Guo and Caliskan, 2021) and a…”
Mohammad, S. M. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-821124-3.00011-9 · Cited by 90 · see citing works
Investigating Bias in Facial Analysis Systems: A Systematic Review
Khalil, A., Ahmed, S. G., Khattak, A. M., & Al-Qirim, N. A. Y. (2020) · IEEE Access · doi:10.1109/access.2020.3006051 · Cited by 80 · see citing works
Álvarez‐Carmona, M. Á., Aranda, R., Rodríguez‐González, A. Y., Fajardo‐Delgado, D., Sánchez, M. G., Pérez-Espinosa, H., Martı́nez-Miranda, J., Rodríguez, R. G., Bustio-Martínez, L., & Pacheco, A. D. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2022.10.010 · Cited by 81 · see citing works
Lau, V. W.-Y., Scott, V. L., Warren, M. A., & Bligh, M. C. (2022) · Journal of Organizational Behavior · doi:10.1002/job.2654 · Cited by 72 · see citing works
Perceptions of GHG emissions and renewable energy sources in Europe, Australia and the USA
Zhang, Y., Abbas, M., & Iqbal, W. (2021) · Environmental Science and Pollution Research · doi:10.1007/s11356-021-15935-7 · Cited by 58 · see citing works
“Nasukawa defines sentiment analysis as a big data analytics method that serves to identify the polarity of sentiments in expressions or judgments made by consumers (Thelwall 2018).”
BackgroundSentiment analysis for formative assessment in higher education: a systematic literature review
Grimalt‐Álvaro, C., & Usart, M. (2023) · Journal of Computing in Higher Education · doi:10.1007/s12528-023-09370-5 · Cited by 55 · see citing works
“Thelwall (2018), argues that these techniques (and SA as well) can be gender biased.”
Ghasemaghaei, M., & Kordzadeh, N. (2024) · Information & Management · doi:10.1016/j.im.2024.103921 · Cited by 58 · see citing works
Topic Modelling and Sentiment Analysis of Global Warming Tweets
Qiao, F., & Williams, J. (2021) · Journal of Organizational and End User Computing · doi:10.4018/joeuc.294901 · Cited by 44 · see citing works
“It has been applied in different areas to detect people’s opinions, such as product reviews (Bhuskute, 2020), newspaper article reviews (Pandiaraj et al., 2021), opinions linked to tourism (Yan et al., 2020), wine reviews (Matheson et al., 2019) and gender studies (Thelwall, 2018).”
BackgroundNowacki, M. M., & Niezgoda, A. (2020) · Scandinavian Journal of Hospitality and Tourism · doi:10.1080/15022250.2020.1833362 · Cited by 35 · see citing works
Gender bias in transformers: A comprehensive review of detection and mitigation strategies
Nemani, P., Joel, Y. D., Vijay, P., & Liza, F. F. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100047 · Cited by 33 · see citing works
Sentiment Analysis for Tourism
Thelwall, M. A. (2019) · Springer eBooks · doi:10.1007/978-981-13-6339-9_6 · Cited by 35 · see citing works
Self-citationCarvache‐Franco, O., Carvache‐Franco, M., Carvache‐Franco, W., & Iturralde, K. (2022) · Tourism and Hospitality Research · doi:10.1177/14673584221085470 · Cited by 33 · see citing works
“…positive language than men and avoid writing negative terms in strongly positive reviews or positive terms in strongly negative reviews, it is important to establish the difference in gender sentiment both at the level of sentiment and at the level of linguistic expression (Thelwall, 2018a).”
BackgroundResultInfluentialMikołajczyk, A., Grochowski, M., & Kwasigroch, A. (2020) · Journal of Artificial Intelligence and Soft Computing Research · doi:10.2478/jaiscr-2021-0004 · Cited by 32 · see citing works
Computational Understanding of Narratives: A Survey
Ranade, P., Dey, S., Joshi, A., & Finin, T. (2022) · IEEE Access · doi:10.1109/access.2022.3205314 · Cited by 29 · see citing works
“Another popular 889 method for detecting bias is through sentiment analysis 890 approaches [62], [68], [143].”
MethodSocial media-based urban disaster recovery and resilience analysis of the Henan deluge
Shan, S., & Zhao, F. (2023) · Natural Hazards · doi:10.1007/s11069-023-06010-0 · Cited by 28 · see citing works
“It exhibits human-level accuracy for short social web texts (Thelwall 2018; Vilares et al.”
BackgroundYouTube science channel video presenters and comments: female friendly or vestiges of sexism?
Thelwall, M. A., & Más-Bleda, A. (2018) · Aslib Journal of Information Management · doi:10.1108/ajim-09-2017-0204 · Cited by 26 · see citing works
Self-citationGender bias in machine learning for sentiment analysis
Thelwall, M. A. (2018) · Online Information Review · doi:10.1108/oir-05-2017-0153 · Cited by 26 · see citing works
Self-citationWord Association Thematic Analysis
Thelwall, M. A. (2021) · Synthesis lectures on information concepts, retrieval, and services · doi:10.2200/s01071ed1v01y202012icr072 · Cited by 37 · see citing works
Self-citationExamining and mitigating gender bias in text emotion detection task
Odbal, O., Zhang, G., & Ananiadou, S. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.057 · Cited by 21 · see citing works
Gender-based multi-aspect sentiment detection using multilabel learning
Kumar, J. A., Trueman, T. E., & Cambria, E. (2022) · Information Sciences · doi:10.1016/j.ins.2022.05.057 · Cited by 21 · see citing works
Schlegelmilch, B. B., Sharma, K., & Garg, S. (2022) · International Marketing Review · doi:10.1108/imr-06-2021-0194 · Cited by 19 · see citing works
Venkit, P. N., Srinath, M., & Wilson, S. (2023) · Workshop on Trustworthy Natural Language Processing (TrustNLP) · doi:10.18653/v1/2023.trustnlp-1.3 · Cited by 23 · see citing works
Investigating fairness in machine learning-based audio sentiment analysis
Luitel, S., Liu, Y., & Anwar, M. M. (2024) · AI and Ethics · doi:10.1007/s43681-024-00453-2 · Cited by 16 · see citing works
“Several studies [33–35] addressed bias within text-based sentiment analysis.”
Hixson, T. (2019) · Journal of Map & Geography Libraries · doi:10.1080/15420353.2020.1719266 · Cited by 14 · see citing works
Twitter Sentiment Analysis on Airline Tweets in India Using R Language
Sreeja, I., Sunny, J. V., & Jatian, L. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1427/1/012003 · Cited by 13 · see citing works
Thelwall, M. A., Thelwall, S., & Fairclough, R. (2021) · Journal of Data and Information Science · doi:10.2478/jdis-2021-0018 · Cited by 12 · see citing works
Self-citationUnveiling metaverse sentiments using machine learning approaches
Natarajan, T., Pragha, P., Dhalmahapatra, K., & Raghavan, D. R. V. (2024) · Kybernetes · doi:10.1108/k-11-2023-2268 · Cited by 14 · see citing works
Pollán, R. R. (2020) · Anuario electrónico de estudios en Comunicación Social Disertaciones · doi:10.12804/revistas.urosario.edu.co/disertaciones/a.7774 · Cited by 10 · see citing works
OpinionML—Opinion Markup Language for Sentiment Representation
Attik, M., Missen, M. M. S., Coustaty, M., Choi, G. S., Alotaibi, F. S., Akhtar, N., Jhandir, M. Z., Prasath, V. B. S., Salamat, N., & Husnain, M. (2019) · Symmetry · doi:10.3390/sym11040545 · Cited by 8 · see citing works
Jung, S., Salminen, J. O., & Jansen, B. J. J. (2022) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3532203 · Cited by 8 · see citing works
“Thelwall [50] observed that the process of sampling social media data might result in an unrepresentative sample that distorts findings and limits their generalizability.”
BackgroundMethodInfluentialOber, T. M., Carter, M. F., Coggins, M. R., Filonczuk, A., Kim, C., Hong, M. R., & Cheng, Y. (2022) · Computers in the Schools · doi:10.1080/07380569.2022.2090764 · Cited by 7 · see citing works
“For example, individual differences in sentiment scores have been documented concerning certain demographic factors (Díaz et al., 2018; Kiritchenko & Mohammad, 2018; Thelwall, 2018).”
BackgroundKhoo, L. S., Bay, J. Q., Yap, M. L. K., Lim, M. K., Chong, C. Y., Yang, Z., & Lo, D. (2023) · IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER) · doi:10.1109/saner56733.2023.00066 · Cited by 7 · see citing works
“Sentiment analysis (SA) estimates feelings, emotions, or opinions expressed in a text typically represented in a range of scalar or binary values [1].”
BackgroundAll work and no play: A text analysis
Downer, K., Wells, C., & Crichton, C. (2019) · International Journal of Market Research · doi:10.1177/1470785318821849 · Cited by 7 · see citing works
“There have been studies relating sentiment analysis of text to scalar responses, which we discuss later—and some authors have looked at whether there are differences between genders in the output (Thelwall, 2018).”
BackgroundWang, Q., Ma, L., Huang, L., & Wang, L. (2020) · Online Information Review · doi:10.1108/oir-01-2020-0025 · Cited by 7 · see citing works
García‐Holgado, A., Vázquez‐Ingelmo, A., & García‐Peñalvo, F. J. (2024) · IEEE Transactions on Education · doi:10.1109/te.2024.3411409 · Cited by 6 · see citing works
“This inquiry encompasses machine learning-based analyses across diverse domains [42], [43], sentiment analysis [44] language processing [45], [46], facial recognition [47], and more.”
BackgroundExamining Gender and Cultural Influences on Customer Emotions
Truong, V. (2025) · Journal of Consumer Behaviour · doi:10.1002/cb.70034 · Cited by 9 · see citing works
“Thelwall (2018) found that women express more positive emotions in online reviews, reinforcing the stereotype that they are more emotionally expressive.”
Cross-lingual Transfer Can Worsen Bias in Sentiment Analysis
Goldfarb-Tarrant, S., Roß, B., & Lopez, A. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.346 · Cited by 10 · see citing works
Nowacki, M. M. (2019) · DOAJ (DOAJ: Directory of Open Access Journals) · doi:10.26349/st.per.0026.04 · Cited by 5 · see citing works
Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages
Goldfarb-Tarrant, S., Lopez, A., Blanco, R., & Marcheggiani, D. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.272 · Cited by 5 · see citing works
Organizational Adoption of Sentiment Analytics in Social Media Networks
Daradkeh, M. K. (2022) · International Journal of Information Technologies and Systems Approach · doi:10.4018/ijitsa.307023 · Cited by 5 · see citing works
Inclination of NLP Applications Towards Stereotypical and Gender Biased ResultsPreprint
Chatterjee, M., Ahmed, A. L. S. A. E., Dadure, P., & Pakray, P. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4096410 · Cited by 5 · see citing works
Mitigating social bias in sentiment classification via ethnicity-aware algorithmic design
Corizzo, R., & Hafner, F. S. (2024) · Social Network Analysis and Mining · doi:10.1007/s13278-024-01369-9 · Cited by 4 · see citing works
“…issue for different types of bias, such as opinion bias (Calais et al. 2011), gender bias (Kiritchenko and Moham-mad 2018; Bolukbasi et al. 2016; Thelwall 2018; Asyrofi et al. 2021; Zhao et al. 2018), racial bias (Kiritchenko and Mohammad 2018; Bolukbasi et al. 2016; Goldfarb-Tarrant et al.…”
InfluentialGhosh, S., Ali, M., Batra, A., Guo, C., Jain, M., Kang, J., Kharchenko, J., Suravajhela, V., Zhou, V., & Aragon, C. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-35891-3_5 · Cited by 4 · see citing works
“While sentiment analysis has commercial benefits, it has been criticized for its potential age bias [18], sexist nature [66], and several other problems (elaborated in Section 2.1).”
InfluentialPredicting Growth in Tourism Industry Using Machine Learning Methods
Ghosal, A., Singh, J., & Singh, A. (2022) · International Conference on Machine Learning, Big Data, Cloud and Parallel Computing (COM-IT-CON) · doi:10.1109/com-it-con54601.2022.9850491 · Cited by 4 · see citing works
The Fears and Hopes of Ukrainian Migrant Workers in Poland in the Pandemic Era
Shelest‐Szumilas, O., & Woźniak, M. (2023) · Journal of International Migration and Integration / Revue de l integration et de la migration internationale · doi:10.1007/s12134-023-01051-7 · Cited by 3 · see citing works
“The interviews were splitted depending on gender as some significant differences in sentiment could be observed between men and women narrations (e.g., Thelwall, 2018; De Amicis et al., 2021).”
Topics and feelings of entrepreneurs during a crisis period: Analysis of business Twitter hashtags
Carvache‐Franco, O., Víquez-Paniagua, A. G., Carvache‐Franco, M., Carvache‐Franco, W., & Pérez-Orozco, A. (2023) · TEC Empresarial · doi:10.18845/te.v17i2.6700 · Cited by 3 · see citing works
“The general score is the highest positive and negative of the words that make up the tweet (Thelwall, 2018).”
BackgroundMethodInfluentialKardaras, D. K., Troussas, C., Barbounaki, S. G., Tselenti, P., & Armyras, K. (2024) · Information · doi:10.3390/info15040236 · Cited by 3 · see citing works
End-to-End Annotator Bias Approximation on Crowdsourced Single-Label Sentiment AnalysisPreprint
Hagerer, G., Szabó, D., Koch, A., Dominguez, M. L. R., Widmer, C., Wich, M., Danner, H., & Groh, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.02326 · Cited by 3 · see citing works
“As an example of this, we utilized the TripAdvisor dataset (Thelwall, 2018).”
BackgroundMethodTruong, V. (2025) · Preprints.org · doi:10.20944/preprints202505.0992.v1 · Cited by 6 · see citing works
Fong, H., Niewiadomski, R., & Igraś-Cybulska, M. (2025) · Biannual Conference of the Italian SIGCHI Chapter (CHItaly) · doi:10.1145/3750069.3750352 · Cited by 2 · see citing works
“Studies have applied these tools to analyze sentiment in product reviews [36], political discourse [46], chatbot interactions [28], and platform-specific phenomena like TikTok reactions [23].”
Understanding the Mood of Social Media Messages
Power, R. A., Robinson, B., Dennett, A., Jin, B., & Paris, C. L. (2020) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2020.300 · Cited by 2 · see citing works
“It has also been used to explore question/answering systems, blog comments and issues of gender bias in online reviews [28].”
MethodEmotional Differences in Product and Service Reviews: A Sentiment and Emotion AnalysisPreprint
Truong, V. (2025) · Preprints.org · doi:10.20944/preprints202505.0447.v1 · Cited by 1 · see citing works
SMART-Portal: A data tracking tool for research purposes from social media and news websites
Stieglitz, S., Basyurt, A. S., & Mirbabaie, M. (2022) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2022.069 · Cited by 1 · see citing works
EquiSent: A Scalable Solution for Bias-Aware Gender-Fair Sentiment Modeling
Kundu, P., & Senthilselvi, A. (2025) · International Conference on Advances in Computation, Communication and Information Technology (ICAICCIT) · doi:10.1109/icaiccit68829.2025.11434462 · Cited by 1 · see citing works
“Thelwall [7] reported gender-related sentiment differences, and Kiritchenko and Mohammad [13], [20] systematically evaluated hundreds of sentiment systems.”
Gender classification based on linguistic analysis: A review
Ali, H. T. A., & Nasrawi, D. A. (2024) · AIP conference proceedings · doi:10.1063/5.0234674 · Cited by 1 · see citing works
Decoding nationalistic biases in the Grand Ethiopian Renaissance Dam research
Waktola, D. K. (2024) · International Journal of River Basin Management · doi:10.1080/15715124.2024.2421344 · Cited by 1 · see citing works
“Confirmation bias leads researchers to favor information that aligns with their existing beliefs (Thelwall 2018, Goldfarb-Tarrant et al. 2023).”
Hafner, F. S., Hafner, L., & Corizzo, R. (2025) · Journal of Computational Social Science · doi:10.1007/s42001-025-00382-y · Cited by 2 · see citing works
Using feature-level fusion for multimodal gender recognition for opinion mining videos
Al-Azani, S., & El-Alfy, E.-S. M. (2019) · International Conference on Modeling, Simulation, and Applied Optimization · doi:10.1109/icmsao.2019.8902177 · Cited by 1 · see citing works
“[3], that machine learning sentiment analysis is gender biased, with more accurate results for one gender than the other.”
BackgroundEliciting Bias in Question Answering Models through Ambiguity
Mao, A., Raman, N. J., Shu, M., Li, E., Yang, F., & Boyd-Graber, J. L. (2021) · Workshop on Machine Reading for Question Answering (MRQA) · doi:10.18653/v1/2021.mrqa-1.9 · Cited by 2 · see citing works
“Bias affects applications ranging from sentiment analysis (Thelwall, 2018) to language models (Bor-dia and Bowman, 2019), and many times originates from upstream sources such as word embeddings (Garrido-Muñoz et al., 2021; Manzini et al., 2019).”
BackgroundOne for “All”: a unified model for fine-grained sentiment analysis under three tasks
Lu, H., Yang, J., Hu, C., & Fang, W. H. (2021) · PeerJ Computer Science · doi:10.7717/peerj-cs.816 · Cited by 1 · see citing works
“Bias, such as racial bias and gender bias (Kiritchenko & Mohammad, 2018; Thelwall, 2018), is also a trending topic of concern in different NLP researches.”
BackgroundText Mining in Gender‐Based Research
Yang, K. C. C., & Kang, Y. (2020) · The International Encyclopedia of Gender, Media, and Communication · doi:10.1002/9781119429128.iegmc276
Gender Bias in Occupation Classification from the New York Times Obituaries
Atik, C., & Tekır, S. (2022) · Deu Muhendislik Fakultesi Fen ve Muhendislik · doi:10.21205/deufmd.2022247109
How People Show Their Emotions towards COVID-19 on Twitter Platform
Zhao, L. (2022) · Advances in Journalism and Communication · doi:10.4236/ajc.2022.102012
Oghu, E., Ogbuju, E., Abiodun, T., & Oladipo, F. O. (2023) · Advances in Multidisciplinary & Scientific Research Journal Publication · doi:10.22624/aims/maths/v11n3p1
Yeri, N. G., Mukherjee, D. S., Aziz, S., & Bharathy, G. K. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4623268
Emotional State Monitoring with Personalized Activity Recommendations
Hettiarachchi, H. D. P. M., Ekanayake, M. N., Kaveendhya, G. C., Koralage, O. V., Samarasekara, P., & Kasthurirathna, D. (2023) · International Conference on Advancements in Computing (ICAC) · doi:10.1109/icac60630.2023.10417468
Extracting Gender Textual Nuances Using Text Similarity for Gender Classification Improvement
Ali, H. T. A., & Nasrawi, D. A. (2024) · International Conference of Science and Information Technology in Smart Administration (ICSINTESA) · doi:10.1109/icsintesa62455.2024.10748083
“Mike Thelwall’s, 2018 [20] study on gender biases in lexical sentiment analysis accuracy, algorithms are more likely to identify sentiment from females than from males.”
InfluentialAI Implementation for Social Benefit. Use Cases in Public Sector
Falco, C. C. D., & Romeo, E. (2025) · Springer proceedings in complexity · doi:10.1007/978-3-031-78623-5_3
Conflicting feelings: sociological and computational sentiment in workplace sentiment surveillance
Donahue, E., Canute, M., Akinwumi, A., Adams, P. R., Taboada, M., & Chun, W. H. K. (2025) · AI & Society · doi:10.1007/s00146-025-02600-7
“…and educational status (Henrich et al. 2010), and therefore tend to bias the interpretation of the analysis along axes, such as age (Diaz et al. 2018), gender (Thelwall 2018), disability (Narayanan Venkit, Srinath, and Wilson 2023), and combinations thereof (Kiritchenko and Mohammad 2018).”
CNN-Based Framework for Gender Classification from Text Data
Ali, H. T. A., & Nasrawi, D. A. (2025) · International Conference of Science and Information Technology in Smart Administration (ICSINTESA) · doi:10.1109/icsintesa68165.2025.11413622
“ TripAdvisor [18] : the second is a specific domain dataset provided detailed reviews of restaurants and hotels in the UK using long phrases.”
InfluentialFairness in audio sentiment analysis: A cross-gender evaluation of machine learning models
Islam, M. M., Liu, J., Xiangdong, L., Ahmed, J., Islam, M. M., & Karim, R. (2026) · Franklin Open · doi:10.1016/j.fraope.2026.100762
A Sentiment Analysis of Gender Bias in Digital Spaces
Moreno, A. I., & Moreno, L. R. (2026) · IntechOpen eBooks · doi:10.5772/intechopen.1018295
Venkit, P. N., & Wilson, S. (2021) · arXiv · doi:10.48550/arxiv.2111.13259 · Cited by 14 · see citing works
“[37] tries to depict the gender bias associated to a few sentiment classifiers to know how they score reviews written by both the male and female gender.”
Background
- Authors
- Thelwall, M.
- Affiliations
- University of Wolverhampton (GB)
- Corresponding author
- Thelwall, Mike
- ORCID
- Thelwall, Mike
- Venue
- Online Information Review
- Publisher
- Emerald
- Published
- 2018-02-12
- Volume
- 42
- Issue
- 1
- Pages
- 45-57
- ISSN
- 1468-4527 (ISSN-L)
- OpenAlex
- W2760255222
- Cited by
- 78
- References
- 39
- Citations by year
- 2026: 2 · 2025: 9 · 2024: 9 · 2023: 13 · 2022: 16 · 2021: 10 · 2020: 10 · 2019: 6 · 2018: 2 · 2016: 1
- FWCI
- 2.94
- Type
- journal article
- Language
- en
- Open access
- green
- hdl.handle.net
- Licence
- cc-by-nc-nd
- www.emerald.com/insight/site-policies (tdm)
- Locations
- Online Information Review (publishedVersion)
- Wolverhampton Intellectual Repository and E-Theses (University of Wolverhampton) (acceptedVersion, cc-by-nc-nd)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Social Sciences › General Social Sciences › Computational and Text Analysis Methods
- Social Sciences › Sociology and Political Science › Digital Marketing and Social Media
- Keywords
- gender bias, TripAdvisor reviews, implicit sentiment
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
