{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:54:04Z","timestamp":1772121244517,"version":"3.50.1"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soc. Netw. Anal. Min."],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Sentiment analysis tools are frequently employed to analyze large amounts of natural language data gathered from social networks and generate valuable insights on public opinion. Research has discovered that these tools tend to be biased against some demographic groups, based on social attributes such as gender, age, and ethnicity. Sentiment classification works dealt with this issue by means of data balancing and algorithmic approaches. However, one crucial limitation of existing methods is the inability to tackle social bias while maintaining satisfactory model performance. In this paper, we aim to fill this gap by proposing a sentiment classification method that entails ethnicity-aware algorithmic design. Specifically, our method involves balanced training and a custom ethnicity-aware loss function that leverages ethnicity group information to foster a fair model optimization process. The proposed loss incentivizes the model to iteratively improve accuracy for currently underperforming demographic or social groups, therefore simultaneously decreasing social bias and boosting overall performance. Our extensive qualitative and quantitative experimental evaluation involving a large corpus of user reviews demonstrated the effectiveness of the proposed method, also when compared to popular baselines for sentiment classification.<\/jats:p>","DOI":"10.1007\/s13278-024-01369-9","type":"journal-article","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T10:02:34Z","timestamp":1729764154000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mitigating social bias in sentiment classification via ethnicity-aware algorithmic design"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8366-6059","authenticated-orcid":false,"given":"Roberto","family":"Corizzo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1070-8267","authenticated-orcid":false,"given":"Franziska Sofia","family":"Hafner","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"issue":"1","key":"1369_CR1","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s13278-023-01107-7","volume":"13","author":"J Anthal","year":"2023","unstructured":"Anthal J, Sharma B, Manhas J (2023) Hybrid optimization-based deep learning classifier for sentiment classification using review data. Soc Netw Anal Min 13(1):109","journal-title":"Soc Netw Anal Min"},{"key":"1369_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118710","volume":"212","author":"M Arbane","year":"2023","unstructured":"Arbane M, Benlamri R, Brik Y, Alahmar AD (2023) Social media-based covid-19 sentiment classification model using bi-lstm. Expert Syst Appl 212:118710","journal-title":"Expert Syst Appl"},{"key":"1369_CR3","doi-asserted-by":"crossref","unstructured":"Areshey A, Mathkour H (2024) Exploring transformer models for sentiment classification: A comparison of bert, roberta, albert, distilbert, and xlnet. Exp Syst e13701","DOI":"10.1111\/exsy.13701"},{"key":"1369_CR4","doi-asserted-by":"crossref","unstructured":"Asyrofi MH, Yang Z, Yusuf INB, Kang HJ, Thung F, Lo D (2021) BiasFinder: Metamorphic test generation to uncover bias for sentiment analysis systems. IEEE Trans Softw Eng 1\u20131","DOI":"10.1109\/TSE.2021.3136169"},{"issue":"1","key":"1369_CR5","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s13278-022-01004-5","volume":"13","author":"Y Ayyappa","year":"2022","unstructured":"Ayyappa Y, Siva Kumar A (2022) Optimized long short-term memory-based stock price prediction with sentiment score. Soc Netw Anal Min 13(1):13","journal-title":"Soc Netw Anal Min"},{"key":"1369_CR6","unstructured":"Barry J (2017) Sentiment analysis of online reviews using bag-of-words and lstm approaches. Aics (pp. 272\u2013274)"},{"issue":"1","key":"1369_CR7","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1109\/TCSS.2019.2951326","volume":"7","author":"ME Basiri","year":"2019","unstructured":"Basiri ME, Abdar M, Kabiri A, Nemati S, Zhou X, Allahbakhshi F, Yen NY (2019) Improving sentiment polarity detection through target identification. IEEE Trans Comput Soc Syst 7(1):113\u2013128","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1369_CR8","doi-asserted-by":"crossref","unstructured":"Bengio Y (2012) Practical recommendations for gradient-based training of deep architectures. Neural networks: Tricks of the trade: Second edition (pp. 437\u2013478). Springer","DOI":"10.1007\/978-3-642-35289-8_26"},{"issue":"5","key":"1369_CR9","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MIC.2021.3097604","volume":"25","author":"M Bernagozzi","year":"2021","unstructured":"Bernagozzi M, Srivastava B, Rossi F, Usmani S (2021) Gender bias in online language translators: visualization, human perception, and bias\/accuracy tradeoffs. IEEE Internet Comput 25(5):53\u201363","journal-title":"IEEE Internet Comput"},{"issue":"9","key":"1369_CR10","doi-asserted-by":"publisher","first-page":"12405","DOI":"10.1007\/s11042-022-12410-4","volume":"81","author":"P Bhuvaneshwari","year":"2022","unstructured":"Bhuvaneshwari P, Rao AN, Robinson YH, Thippeswamy M (2022) Sentiment analysis for user reviews using bi-lstm self-attention based cnn model. Multimedia Tools Appl 81(9):12405\u201312419","journal-title":"Multimedia Tools Appl"},{"key":"1369_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107134","volume":"226","author":"M Birjali","year":"2021","unstructured":"Birjali M, Kasri M, Beni-Hssane A (2021) A comprehensive survey on sentiment analysis: Approaches, challenges and trends. Knowl-Based Syst 226:107134","journal-title":"Knowl-Based Syst"},{"key":"1369_CR12","unstructured":"Bolukbasi T, Chang K-W, Zou JY, Saligrama V, Kalai AT (2016) Man is to computer programmer as woman is to homemaker? debiasing word embeddings. Adv Neural Inf Process Syst 29"},{"key":"1369_CR13","doi-asserted-by":"crossref","unstructured":"Calais Guerra PH, Veloso A, Meira W, Almeida V (2011) From bias to opinion: a transfer-learning approach to real-time sentiment analysis. Proceedings of the 17th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 150\u2013158). Association for Computing Machinery","DOI":"10.1145\/2020408.2020438"},{"key":"1369_CR14","doi-asserted-by":"crossref","unstructured":"Chan GK (2022) Ai employment decision-making: integrating the equal opportunity merit principle and explainable ai. AI & SOCIETY , 1\u201312","DOI":"10.1007\/s00146-022-01532-w"},{"key":"1369_CR15","doi-asserted-by":"crossref","unstructured":"Charalabidis Y, Maragoudakis M, Loukis E (2015) Opinion mining and sentiment analysis in policy formulation initiatives: The eu-community approach. Electronic participation: 7th ifip 8.5 international conference, epart 2015, thessaloniki, greece, august 30\u2013september 2, 2015, proceedings 7 (pp. 147\u2013160)","DOI":"10.1007\/978-3-319-22500-5_12"},{"key":"1369_CR16","doi-asserted-by":"crossref","unstructured":"Chen Z, Zhang JM, Sarro F, Harman M (2023, may) A comprehensive empirical study of bias mitigation methods for machine learning classifiers. ACM Trans Softw Eng Methodol 32 (4)","DOI":"10.1145\/3583561"},{"key":"1369_CR17","doi-asserted-by":"crossref","unstructured":"Costa-juss\u00e0 MR, Escolano C, Basta C, Ferrando J, Batlle R, Kharitonova K (2022) Interpreting gender bias in neural machine translation: Multilingual architecture matters. Proceedings of the aaai conference on artificial intelligence (Vol. 36, pp. 11855\u201311863)","DOI":"10.1609\/aaai.v36i11.21442"},{"issue":"1","key":"1369_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s13278-024-01250-9","volume":"14","author":"MM Danyal","year":"2024","unstructured":"Danyal MM, Khan SS, Khan M, Ullah S, Ghaffar MB, Khan W (2024) Sentiment analysis of movie reviews based on nb approaches using tf-idf and count vectorizer. Soc Netw Anal Min 14(1):1\u201315","journal-title":"Soc Netw Anal Min"},{"key":"1369_CR19","doi-asserted-by":"crossref","unstructured":"D\u00edaz M, Johnson I, Lazar A, Piper AM, Gergle D (2018) Addressing agerelated bias in sentiment analysis: 2018 CHI conference on human factors in computing systems, CHI 2018. CHI 2018 - Extended Abstracts of the 2018 CHI Conference on Human Factors in Computing Systems","DOI":"10.1145\/3173574.3173986"},{"key":"1369_CR20","first-page":"64","volume":"2","author":"M Geetha","year":"2021","unstructured":"Geetha M, Renuka DK (2021) Improving the performance of aspect based sentiment analysis using fine-tuned bert base uncased model. Int J Intell Netw 2:64\u201369","journal-title":"Int J Intell Netw"},{"key":"1369_CR21","doi-asserted-by":"crossref","unstructured":"Goldfarb-Tarrant S, Lopez A, Blanco R, Marcheggiani D (2023, July) Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages. A. Rogers, J. Boyd-Graber, & N. Okazaki (Eds.), Findings of the Association for Computational Linguistics: ACL 2023 (pp. 4458\u20134468). Toronto, Canada: Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.findings-acl.272"},{"key":"1369_CR22","doi-asserted-by":"crossref","unstructured":"Hafner L, Peifer TP, Hafner FS (2023) Equal accuracy for andrew and abubakar\u2013detecting and mitigating bias in name-ethnicity classification algorithms. AI & society, 1\u201325","DOI":"10.1007\/s00146-022-01619-4"},{"issue":"8","key":"1369_CR23","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0202523","volume":"13","author":"H Han","year":"2018","unstructured":"Han H, Zhang Y, Zhang J, Yang J, Zou X (2018) Improving the performance of lexicon-based review sentiment analysis method by reducing additional introduced sentiment bias. PLoS ONE 13(8):e0202523","journal-title":"PLoS ONE"},{"key":"1369_CR24","doi-asserted-by":"crossref","unstructured":"Han X, Baldwin T, Cohn T (2022) Balancing out bias: Achieving fairness through balanced training. Proceedings of the 2022 conference on empirical methods in natural language processing (pp. 11335\u201311350)","DOI":"10.18653\/v1\/2022.emnlp-main.779"},{"key":"1369_CR25","unstructured":"Hochreiter S, Bengio Y, Frasconi Pea (2001) Gradient flow in recurrent nets: the difficulty of learning long-term dependencies. A Field Guide to Dynamical Recurrent Neural Networks, 237\u2013244"},{"key":"1369_CR26","doi-asserted-by":"publisher","unstructured":"Iqbal M, Karim A, Kamiran F (2015) Bias-aware lexicon-based sentiment analysis. Proceedings of the 30th annual ACM symposium on applied computing (pp. 845\u2013850). Association for Computing Machinery. Retrieved from https:\/\/doi.org\/10.1145\/2695664.2695759","DOI":"10.1145\/2695664.2695759"},{"key":"1369_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2020.113304","volume":"135","author":"J Kazmaier","year":"2020","unstructured":"Kazmaier J, van Vuuren JH (2020) A generic framework for sentiment analysis: Leveraging opinion-bearing data to inform decision making. Decis Support Syst 135:113304","journal-title":"Decis Support Syst"},{"key":"1369_CR28","unstructured":"Kenton JDM-WC, Toutanova LK (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. Proceedings of naacl-hlt (pp. 4171\u20134186)"},{"key":"1369_CR29","doi-asserted-by":"crossref","unstructured":"Kiritchenko S, Mohammad S (2018, June) Examining Gender and Race Bias in Two Hundred Sentiment Analysis Systems. M. Nissim, J. Berant, & A. Lenci (Eds.), Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics (pp. 43\u201353). New Orleans, Louisiana: Association for Computational Linguistics","DOI":"10.18653\/v1\/S18-2005"},{"key":"1369_CR30","unstructured":"Le Q, Mikolov T (2014) Distributed representations of sentences and documents. Int Conf Mach Learn (pp. 1188\u20131196)"},{"key":"1369_CR31","doi-asserted-by":"crossref","unstructured":"Liu H, Jin W, Karimi H, Liu Z, Tang J (2021, August) The Authors Matter: Understanding and Mitigating Implicit Bias in Deep Text Classification. C. Zong, F. Xia, W. Li, & R. Navigli (Eds.), Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021 (pp. 74\u201385). Association for Computational Linguistics","DOI":"10.18653\/v1\/2021.findings-acl.7"},{"key":"1369_CR32","doi-asserted-by":"crossref","unstructured":"Loureiro D, Barbieri F, Neves L, Espinosa Anke L, Camacho-collados J (2022, May) TimeLMs: Diachronic language models from Twitter. V. Basile, Z. Kozareva, & S. Stajner (Eds.), Proceedings of the 60th annual meeting of the association for computational linguistics: System demonstrations (pp. 251\u2013260). Dublin, Ireland: Association for Computational Linguistics","DOI":"10.18653\/v1\/2022.acl-demo.25"},{"key":"1369_CR33","unstructured":"Lyu H, Fan Y, Xiong Z, Komisarchik M, Luo J (2021) Understanding public opinion toward the# stopasianhate movement and the relation with racially motivated hate crimes in the us. IEEE Trans Comput Soc Syst"},{"key":"1369_CR34","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. Adv Neural Inf Process Syst 3111\u20133119"},{"key":"1369_CR35","doi-asserted-by":"crossref","unstructured":"Munikar M, Shakya S, Shrestha A (2019) Fine-grained sentiment classification using bert. 2019 artificial intelligence for transforming business and society (aitb) (Vol. 1, pp. 1\u20135)","DOI":"10.1109\/AITB48515.2019.8947435"},{"key":"1369_CR36","doi-asserted-by":"crossref","unstructured":"Narayanan Venkit P, Srinath M, Wilson S (2023, July) Automated Ableism: An Exploration of Explicit Disability Biases in Sentiment and Toxicity Analysis Models. A. Ovalle et al. (Eds.), Proceedings of the 3rd Workshop on Trustworthy Natural Language Processing (TrustNLP 2023) (pp. 26\u201334). Toronto, Canada: Association for Computational Linguistics","DOI":"10.18653\/v1\/2023.trustnlp-1.3"},{"key":"1369_CR37","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O et al (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"1369_CR38","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: Global vectors for word representation. Proceedings of the 2014 conference on empirical methods in natural language processing (emnlp) (pp. 1532\u20131543)","DOI":"10.3115\/v1\/D14-1162"},{"key":"1369_CR39","doi-asserted-by":"crossref","unstructured":"Pozzi FA, Fersini E, Messina E, Liu B (2017) Chapter 1 - challenges of sentiment analysis in social networks: An overview. F.A. Pozzi, E. Fersini, E. Messina, & B. Liu (Eds.), Sentiment analysis in social networks (pp. 1\u201311). Morgan Kaufmann","DOI":"10.1016\/B978-0-12-804412-4.00001-2"},{"key":"1369_CR40","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1016\/j.procs.2018.05.109","volume":"132","author":"N.e.a. Saleena","year":"2018","unstructured":"Saleena N.e.a. (2018) An ensemble classification system for twitter sentiment analysis. Procedia Comput Sci 132:937\u2013946","journal-title":"Procedia Comput Sci"},{"key":"1369_CR41","unstructured":"Shen JH, Fratamico L, Rahwan I, Rush AM (2018) Darling or babygirl? investigating stylistic bias in sentiment analysis. Proc. of FATML"},{"issue":"2","key":"1369_CR42","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1111\/coin.12478","volume":"38","author":"B Subba","year":"2022","unstructured":"Subba B, Kumari S (2022) A heterogeneous stacking ensemble based sentiment analysis framework using multiple word embeddings. Comput Intell 38(2):530\u2013559","journal-title":"Comput Intell"},{"issue":"1","key":"1369_CR43","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1108\/OIR-05-2017-0139","volume":"42","author":"M Thelwall","year":"2018","unstructured":"Thelwall M (2018) Gender bias in sentiment analysis. Online Inf Rev 42(1):45\u201357","journal-title":"Online Inf Rev"},{"key":"1369_CR44","doi-asserted-by":"crossref","unstructured":"Ungless EL, Ross B, Belle V (2023) Potential pitfalls with automatic sentiment analysis: The example of queerphobic bias. Soc Sci Comput Rev 08944393231152946","DOI":"10.1177\/08944393231152946"},{"key":"1369_CR45","doi-asserted-by":"crossref","unstructured":"Wallach HM (2006) Topic modeling: Beyond bag-of-words. Proceedings of the 23rd international conference on machine learning (p. 977\u2013984). New York, NY, USA: Association for Computing Machinery","DOI":"10.1145\/1143844.1143967"},{"key":"1369_CR46","doi-asserted-by":"crossref","unstructured":"Wang M, Cao D, Li L, Li S, Ji R (2014) Microblog sentiment analysis based on cross-media bag-of-words model. Proceedings of international conference on internet multimedia computing and service (pp. 76\u201380)","DOI":"10.1145\/2632856.2632912"},{"issue":"2","key":"1369_CR47","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1109\/TCSS.2021.3106003","volume":"9","author":"F Wu","year":"2021","unstructured":"Wu F, Du M, Fan C, Tang R, Yang Y, Mostafavi A, Hu X (2021) Understanding social biases behind location names in contextual word embedding models. IEEE Trans Comput Soc Syst 9(2):458\u2013468","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1369_CR48","doi-asserted-by":"crossref","unstructured":"Yadav A, Vishwakarma DK (2020) A multilingual framework of cnn and bilstm for emotion classification. 2020 11th international conference on computing, communication and networking technologies (icccnt) (pp. 1\u20136)","DOI":"10.1109\/ICCCNT49239.2020.9225614"},{"key":"1369_CR49","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1007\/s41060-020-00231-3","volume":"11","author":"T Yang","year":"2021","unstructured":"Yang T, Yao R, Yin Q, Tian Q, Wu O (2021) Mitigating sentimental bias via a polar attention mechanism. Int J Data Sci Anal 11:27\u201336","journal-title":"Int J Data Sci Anal"},{"key":"1369_CR50","doi-asserted-by":"crossref","unstructured":"Yang Z, Jain H, Shi J, Asyrofi MH, Lo D (2021) Biasheal: On-the-fly black-box healing of bias in sentiment analysis systems. 2021 ieee international conference on software maintenance and evolution (icsme) (pp. 644\u2013648)","DOI":"10.1109\/ICSME52107.2021.00073"},{"key":"1369_CR51","doi-asserted-by":"crossref","unstructured":"Zhao J, Wang T, Yatskar M, Ordonez V, Chang K-W (2018) Gender bias in coreference resolution: Evaluation and debiasing methods. Proceedings of the 2018 conference of the north american chapter of the association for computational linguistics: Human language technologies, volume 2 (short papers) (pp. 15\u201320). Association for Computational Linguistics","DOI":"10.18653\/v1\/N18-2003"},{"key":"1369_CR52","unstructured":"Zhiltsova A, Caton S, Mulway C (2019) Mitigation of unintended biases against non-native english texts in sentiment analysis. Aics (pp. 317\u2013328)"}],"container-title":["Social Network Analysis and Mining"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-024-01369-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13278-024-01369-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13278-024-01369-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,25]],"date-time":"2025-02-25T05:49:25Z","timestamp":1740462565000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13278-024-01369-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["1369"],"URL":"https:\/\/doi.org\/10.1007\/s13278-024-01369-9","relation":{},"ISSN":["1869-5469"],"issn-type":[{"value":"1869-5469","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,24]]},"assertion":[{"value":"8 July 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 September 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 October 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no financial or non-financial interests directly or indirectly related to the work submitted for publication. The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"208"}}