{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T09:38:40Z","timestamp":1769161120901,"version":"3.49.0"},"reference-count":73,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T00:00:00Z","timestamp":1755129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Committee of Science of the Ministry of Science and Higher Education of the Republic of Kazakhstan","award":["BR24992852"],"award-info":[{"award-number":["BR24992852"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Informatics"],"abstract":"<jats:p>Public transport agencies must triage thousands of multilingual complaints every day, yet the cost of training and serving fine-grained sentiment analysis models limits real-time deployment. The proposed \u201cone encoder, any facet\u201d framework therefore offers a reproducible, resource-efficient alternative to heavy fine-tuning for domain-specific sentiment analysis or opinion mining tasks on digital service data. To the best of our knowledge, we are the first to test this paradigm on operational multilingual complaints, where public transport agencies must prioritize thousands of Russian- and Kazakh-language messages each day. A human-labelled corpus of 2400 complaints is embedded with five open-source universal models. Obtained embeddings are matched to semantic \u201canchor\u201d queries that describe three distinct facets: service aspect (eight classes), implicit frustration, and explicit customer request. In the strict zero-shot setting, the best encoder reaches 77% accuracy for aspect detection, 74% for frustration, and 80% for request; taken together, these signals reproduce human four-level priority in 60% of cases. Attaching a single-layer logistic probe on top of the frozen embeddings boosts performance to 89% for aspect, 83\u201387% for the binary facets, and 72% for end-to-end triage. Compared with recent fine-tuned sentiment analysis systems, our pipeline cuts memory demands by two orders of magnitude and eliminates task-specific training yet narrows the accuracy gap to under five percentage points. These findings indicate that a single frozen encoder, guided by handcrafted anchors and an ultra-light head, can deliver near-human triage quality across multiple pragmatic dimensions, opening the door to low-cost, language-agnostic monitoring of digital-service feedback.<\/jats:p>","DOI":"10.3390\/informatics12030082","type":"journal-article","created":{"date-parts":[[2025,8,14]],"date-time":"2025-08-14T15:44:21Z","timestamp":1755186261000},"page":"82","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Global Embeddings, Local Signals: Zero-Shot Sentiment Analysis of Transport Complaints"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5522-4421","authenticated-orcid":false,"given":"Aliya","family":"Nugumanova","sequence":"first","affiliation":[{"name":"Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4294-8485","authenticated-orcid":false,"given":"Daniyar","family":"Rakhimzhanov","sequence":"additional","affiliation":[{"name":"Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9076-0722","authenticated-orcid":false,"given":"Aiganym","family":"Mansurova","sequence":"additional","affiliation":[{"name":"Big Data and Blockchain Technologies Research Innovation Center, Astana IT University, Astana 010000, Kazakhstan"}]}],"member":"1968","published-online":{"date-parts":[[2025,8,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.jik.2021.07.001","article-title":"Social media: Where customers air their troubles\u2014How to respond to them?","volume":"4","author":"Sigurdsson","year":"2021","journal-title":"J. Innov. Knowl."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Moreno, A., and Iglesias, C.A. (2021). Understanding customers\u2019 transport services with topic clustering and sentiment analysis. Appl. Sci., 21.","DOI":"10.3390\/app112110169"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"102530","DOI":"10.1016\/j.scs.2020.102530","article-title":"Social media semantic perceptions on Madrid Metro system: Using Twitter data to link complaints to space","volume":"64","author":"Horak","year":"2021","journal-title":"Sustain. Cities Soc."},{"key":"ref_4","first-page":"101197","article-title":"Framework for evaluating online public opinions on urban rail transit services through social media data classification and mining","volume":"56","author":"Gong","year":"2024","journal-title":"Res. Transp. Bus. Manag."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Das, R.D. (2021). Understanding users\u2019 satisfaction towards public transit system in India: A case-study of Mumbai. ISPRS Int. J. Geo-Inf., 3.","DOI":"10.3390\/ijgi10030155"},{"key":"ref_6","unstructured":"Sahil, P.S., and Jamatia, A. (2025). Team A at SemEval-2025 Task 11: Breaking Language Barriers in Emotion Detection with Multilingual Models. arXiv."},{"key":"ref_7","unstructured":"Zhou, Y., Muresanu, A.I., Han, Z., Paster, K., Pitis, S., Chan, H., and Ba, J. (2022, January 25). Large language models are human-level prompt engineers. Proceedings of the Eleventh International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Lan, Y., Wu, Y., Xu, W., Feng, W., and Zhang, Y. (2024). Chinese fine-grained financial sentiment analysis with large language models. Neural Comput. Appl., 1\u201310.","DOI":"10.1007\/s00521-024-10603-6"},{"key":"ref_9","unstructured":"Shah, F.A., Sabir, A., and Sharma, R. (2024). A Fine-grained Sentiment Analysis of App Reviews using Large Language Models: An Evaluation Study. arXiv."},{"key":"ref_10","first-page":"11","article-title":"A fine-grained sentiment recognition method for online Government-Public interaction texts based on large language models","volume":"Volume 13635","author":"Teng","year":"2025","journal-title":"Proceedings of the International Conference on Artificial Intelligence and Machine Learning Research (CAIMLR 2024)"},{"key":"ref_11","unstructured":"Wang, L., Yang, N., Huang, X., Yang, L., Majumder, R., and Wei, F. (2024). Multilingual e5 text embeddings: A technical report. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, J., Xiao, S., Zhang, P., Luo, K., Lian, D., and Liu, Z. (2024). BGE M3-embedding: Multi-lingual, multi-functionality, multi-granularity text embeddings through self-knowledge distillation. arXiv.","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"ref_13","unstructured":"Li, Z., Zhang, X., Zhang, Y., Long, D., Xie, P., and Zhang, M. (2023). Towards general text embeddings with multi-stage contrastive learning. arXiv."},{"key":"ref_14","unstructured":"Solatorio, A.V. (2024). Gistembed: Guided in-sample selection of training negatives for text embedding fine-tuning. arXiv."},{"key":"ref_15","unstructured":"Cao, H. (2024). Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Gan, D., and Li, J. (2025). Small, Open-Source Text-Embedding Models as Substitutes to OpenAI Models for Gene Analysis. bioRxiv.","DOI":"10.1101\/2025.02.15.638462"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Muennighoff, N., Tazi, N., Magne, L., and Reimers, N. (2022). MTEB: Massive text embedding benchmark. arXiv.","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref_18","unstructured":"(2025, June 26). BGE-M3 Model Card and Documentation, Available online: https:\/\/huggingface.co\/BAAI\/bge-m3."},{"key":"ref_19","unstructured":"Goffman, E. (1981). Forms of Talk, University of Pennsylvania Press."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Su, H., Shi, W., Kasai, J., Wang, Y., Hu, Y., Ostendorf, M., Yih, W.-t., Smith, N.A., Zettlemoyer, L., and Yu, T. (2022). One embedder, any task: Instruction-finetuned text embeddings. arXiv.","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wu, C., Wu, F., Liu, J., Yuan, Z., Wu, S., and Huang, Y. (2018, January 5\u20136). Thu_ngn at semeval-2018 task 1: Fine-grained tweet sentiment intensity analysis with attention Cnn-LSTM. Proceedings of the 12th International Workshop on Semantic Evaluation, New Orleans, LA, USA.","DOI":"10.18653\/v1\/S18-1028"},{"key":"ref_22","unstructured":"(2023, January 24). What is sentiment analysis?. Proceedings of the IBM Think,  Boston, MA, USA. Available online: https:\/\/www.ibm.com\/think\/topics\/sentiment-analysis."},{"key":"ref_23","unstructured":"Amazon Web Services (2025, June 22). What Is Sentiment Analysis?. Available online: https:\/\/aws.amazon.com\/what-is\/sentiment-analysis\/."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3594","DOI":"10.1109\/ACCESS.2019.2963020","article-title":"A sentiment polarity categorization technique for online product reviews","volume":"8","author":"Kausar","year":"2019","journal-title":"IEEE Access"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Tirpude, S., Thakre, Y., Sudan, S., Agrawal, S., and Ganorkar, A. (2023, January 23\u201325). Mining Comments and Sentiments in YouTube Live Chat Data. Proceedings of the 2023 4th International Conference on Intelligent Technologies (CONIT), Hubballi, India.","DOI":"10.1109\/CONIT61985.2024.10626352"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"152","DOI":"10.54254\/2977-3903\/2025.23585","article-title":"Fine-grained sentiment analysis for social media: From multi-model collaboration to cross-language multimodal analysis","volume":"5","author":"Dong","year":"2025","journal-title":"Adv. Eng. Innov."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Fang, J., and Jin, S. (2025). Fine-Grained Sentiment Analysis Based on SSFF-GCN Model. Systems, 2.","DOI":"10.3390\/systems13020111"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kaminska, O., Cornelis, C., and Hoste, V. (2023). Fuzzy rough nearest neighbour methods for aspect-based sentiment analysis. Electronics, 5.","DOI":"10.3390\/electronics12051088"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"107134","DOI":"10.1016\/j.knosys.2021.107134","article-title":"A comprehensive survey on sentiment analysis: Approaches, challenges and trends","volume":"226","author":"Birjali","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_30","first-page":"1855","article-title":"Integrating Ontology-Based Approaches with Deep Learning Models for Fine-Grained Sentiment Analysis","volume":"81","author":"Zhao","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"2313","DOI":"10.1007\/s40747-021-00306-z","article-title":"Product-harm crisis intelligent warning system design based on fine-grained sentiment analysis of automobile complaints","volume":"3","author":"Hu","year":"2023","journal-title":"Complex Intell. Syst."},{"key":"ref_32","first-page":"48","article-title":"Fine Grained Analysis of Intention for Social Media Reviews Using Distance Measure and Deep Learning Technique","volume":"2","author":"Akila","year":"2023","journal-title":"J. Internet Serv. Inf. Secur."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Torres, E.C.M., and de Picado-Santos, L.G. (2025). Sentiment Analysis and Topic Modeling in Transportation: A Literature Review. Appl. Sci., 12.","DOI":"10.3390\/app15126576"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1007\/s13278-024-01278-x","article-title":"Utilizing the Twitter social media to identify transportation-related grievances in Indian cities","volume":"1","author":"Pullanikkat","year":"2024","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1177\/03611981231225655","article-title":"Metroberta: Leveraging traditional customer relationship management data to develop a transit-topic-aware language model","volume":"9","author":"Leong","year":"2024","journal-title":"Transp. Res. Rec."},{"key":"ref_36","unstructured":"R\u00f8nningstad, E., Storset, L.C., M\u00e6hlum, P., \u00d8vrelid, L., and Velldal, E. (2025, January 3\u20135). Mixed Feelings: Cross-Domain Sentiment Classification of Patient Feedback. Proceedings of the Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa\/Baltic-HLT 2025), Tallinn, Estonia."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Pullanikkat, R., Basu, M., and Ghosh, S. (2025). Hear the Commute: A Generative AI-Based Framework to Summarize Transport Grievances from Social Media. Int. J. Intell. Transp. Syst. Res., 1\u201317.","DOI":"10.1007\/s13177-025-00502-y"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Li, J., Yang, Y., Chen, R., Zheng, D., Pang, P.C.I., Lam, C.K., Wong, D., and Wang, Y. (2025). Identifying healthcare needs with patient experience reviews using ChatGPT. PLoS ONE, 3.","DOI":"10.1371\/journal.pone.0313442"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e66344","DOI":"10.2196\/66344","article-title":"Revealing patient dissatisfaction with health care resource allocation in multiple dimensions using large language models and the international classification of diseases 11th revision: Aspect-based sentiment analysis","volume":"27","author":"Li","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ruan, K., Wang, X., and Di, X. (2024, January 24\u201327). From Twitter to Reasoner: Understand mobility travel modes and sentiment using large language models. Proceedings of the 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), Edmonton, AB, Canada.","DOI":"10.1109\/ITSC58415.2024.10919612"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Esperan\u00e7a, M., Freitas, D., Paix\u00e3o, P.V., Marcos, T.A., Martins, R.A., and Ferreira, J.C. (2025). Proactive Complaint Management in Public Sector Informatics Using AI: A Semantic Pattern Recognition Framework. Appl. Sci., 12.","DOI":"10.3390\/app15126673"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"362","DOI":"10.64252\/485k6s11","article-title":"A Unified Platform for Resolving Citizens\u2019 Queries on Beneficiary Services by Using AI-Powered Chatbots","volume":"11","author":"Mehta","year":"2025","journal-title":"Int. J. Environ. Sci."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Chen, G., and Cao, J. (2024). Research on Public Service Request Text Classification Based on BERT-BiLSTM-CNN Feature Fusion. Appl. Sci., 14.","DOI":"10.3390\/app14146282"},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"105887","DOI":"10.1016\/j.clsr.2023.105887","article-title":"Public tenders, complaints, machine learning and recommender systems: A case study in public administration","volume":"51","author":"Nai","year":"2023","journal-title":"Comput. Law Secur. Rev."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Agustina, N., Naseer, M., Gusdevi, H., and Rismayadi, D.A. (2024, January 29\u201330). Development of a Public Complaint Classification Model to Support E-Government Using IndoBERT. Proceedings of the 2024 6th International Conference on Cybernetics and Intelligent System (ICORIS), Central Java, Indonesia.","DOI":"10.1109\/ICORIS63540.2024.10903819"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Jin, M., and Aletras, N. (2021, January 6\u201311). Modeling the Severity of Complaints in Social Media. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico.","DOI":"10.18653\/v1\/2021.naacl-main.180"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"123112","DOI":"10.1016\/j.jenvman.2024.123112","article-title":"Topic-sentiment analysis of citizen environmental complaints in China: Using a Stacking-BERT model","volume":"371","author":"Liu","year":"2024","journal-title":"J. Environ. Manag."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Singh, A., and Saha, S. (2021, January 5\u201310). Are you really complaining? A multi-task framework for complaint identification, emotion, and sentiment classification. Proceedings of the International Conference on Document Analysis and Recognition, Lausanne, Switzerland.","DOI":"10.1007\/978-3-030-86331-9_46"},{"key":"ref_49","first-page":"660","article-title":"Complaint and severity identification from online financial content","volume":"1","author":"Singh","year":"2023","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Joshi, A., Kumar, A., and Patel, N. (2024). Leveraging Natural Language Processing for Real-Time Financial Complaint Analysis on Social Media: A Multitasking Approach. SSRN, SSRN 5059673.","DOI":"10.2139\/ssrn.5059673"},{"key":"ref_51","unstructured":"Caralt, M.H., Sekuli\u0107, I., Carevi\u0107, F., Khau, N., Popa, D.N., Guedes, B., Guimar\u00e3esMathis, V., Yang, Z., Manso, A., and Reddy, M. (2024). \u201cStupid robot, I want to speak to a human!\u201d User Frustration Detection in Task-Oriented Dialog Systems. arXiv."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1037\/0033-2909.106.1.59","article-title":"Frustration-aggression hypothesis: Examination and reformulation","volume":"106","author":"Berkowitz","year":"1989","journal-title":"Psychol. Bull."},{"key":"ref_53","doi-asserted-by":"crossref","unstructured":"Searle, J.R. (1979). Expression and Meaning: Studies in the Theory of Speech Acts, Cambridge University Press.","DOI":"10.1017\/CBO9780511609213"},{"key":"ref_54","doi-asserted-by":"crossref","unstructured":"Wang, L., Li, L., Dai, D., Chen, D., Zhou, H., Meng, F., Zhou, J., and Sun, X. (2023, January 6\u201310). Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore.","DOI":"10.18653\/v1\/2023.emnlp-main.609"},{"key":"ref_55","first-page":"4077","article-title":"Prototypical networks for few-shot learning","volume":"30","author":"Snell","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_56","doi-asserted-by":"crossref","unstructured":"Liu, H., Zhao, S., Zhang, X., Zhang, F., Wang, W., Ma, F., Chen, H., Yu, H., and Zhang, X. (2024, January 20\u201327). Liberating seen classes: Boosting few-shot and zero-shot text classification via anchor generation and classification reframing. Proceedings of the AAAI Conference on Artificial Intelligence, Vancouver, BC, Canada.","DOI":"10.1609\/aaai.v38i17.29827"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Paletto, L., Basile, V., and Esposito, R. (2024, January 11\u201316). Label Augmentation for Zero-Shot Hierarchical Text Classification. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics, Bangkok, Thailand.","DOI":"10.18653\/v1\/2024.acl-long.416"},{"key":"ref_58","unstructured":"Hugging Face (2025, July 01). Intfloat\/Multilingual-e5-large-instruct. Available online: https:\/\/huggingface.co\/intfloat\/multilingual-e5-large-instruct."},{"key":"ref_59","doi-asserted-by":"crossref","unstructured":"Asai, A., Schick, T., Lewis, P., Chen, X., Izacard, G., Riedel, S., and Yih, W.T. (2023). Task-aware Retrieval with Instructions. Findings of the Association for Computational Linguistics: ACL, ACL.","DOI":"10.18653\/v1\/2023.findings-acl.225"},{"key":"ref_60","doi-asserted-by":"crossref","first-page":"1201","DOI":"10.1162\/tacl_a_00597","article-title":"Improving multitask retrieval by promoting task specialization","volume":"11","author":"Zhang","year":"2023","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"ref_61","first-page":"1263","article-title":"Learning from imbalanced data","volume":"9","author":"He","year":"2009","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_62","doi-asserted-by":"crossref","unstructured":"Tang, Y., and Yang, Y. (2024). Pooling and attention: What are effective designs for llm-based embedding models?. arXiv.","DOI":"10.1186\/s13662-024-03844-1"},{"key":"ref_63","unstructured":"Wang, L., Yang, N., Huang, X., Jiao, B., Yang, L., Jiang, D., Majumder, R., and Wei, F. (2022). Text embeddings by weakly-supervised contrastive pre-training. arXiv."},{"key":"ref_64","first-page":"530","article-title":"A fast attention network for joint intent detection and slot filling on edge devices","volume":"2","author":"Huang","year":"2023","journal-title":"IEEE Trans. Artif. Intell."},{"key":"ref_65","doi-asserted-by":"crossref","unstructured":"Senge, R., Del Coz, J.J., and H\u00fcllermeier, E. (2013). On the problem of error propagation in classifier chains for multi-label classification. Data Analysis, Machine Learning and Knowledge Discovery, Springer International Publishing.","DOI":"10.1007\/978-3-319-01595-8_18"},{"key":"ref_66","doi-asserted-by":"crossref","unstructured":"Bell, S.J., Meglioli, M.C., Richards, M., S\u00e1nchez, E., Ropers, C., Wang, S., Williams, A., Sagun, L., and Costa-juss\u00e0, M.R. (2024). On the role of speech data in reducing toxicity detection bias. arXiv.","DOI":"10.18653\/v1\/2025.naacl-long.67"},{"key":"ref_67","doi-asserted-by":"crossref","unstructured":"Rakhimzhanov, D., Belginova, S., and Yedilkhan, D. (2025). Automated Classification of Public Transport Complaints via Text Mining Using LLMs and Embeddings. Information, 8.","DOI":"10.3390\/info16080644"},{"key":"ref_68","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume":"Volume 1 (Long and Short Papers)","author":"Devlin","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies"},{"key":"ref_69","unstructured":"Mosbach, M., Andriushchenko, M., and Klakow, D. (2020). On the stability of fine-tuning bert: Misconceptions, explanations, and strong baselines. arXiv."},{"key":"ref_70","doi-asserted-by":"crossref","unstructured":"Du, Y., and Nguyen, D. (2023, January 9\u201314). Measuring the Instability of Fine-Tuning. Proceedings of the 61st Annual Meeting Of The Association For Computational Linguistics, Toronto, Canada.","DOI":"10.18653\/v1\/2023.acl-long.342"},{"key":"ref_71","doi-asserted-by":"crossref","unstructured":"Hua, H., Li, X., Dou, D., Xu, C., and Luo, J. (2021, January 6\u201311). Noise Stability Regularization for Improving BERT Fine-tuning. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Mexico City, Mexico.","DOI":"10.18653\/v1\/2021.naacl-main.258"},{"key":"ref_72","doi-asserted-by":"crossref","first-page":"21415","DOI":"10.1007\/s00521-023-08629-3","article-title":"Multilingual text categorization and sentiment analysis: A comparative analysis of the utilization of multilingual approaches for classifying twitter data","volume":"29","author":"Manias","year":"2023","journal-title":"Neural Comput. Appl."},{"key":"ref_73","first-page":"249","article-title":"Sentiment analysis of Lithuanian online reviews using large language models","volume":"Volume 3885","year":"2024","journal-title":"Proceedings of the CEUR Workshop Proceedings: IVUS 2024: Information Society and University Studies 2024, Proceedings of the 29th International Conference on Information Society and University Studies (IVUS 2023)"}],"container-title":["Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/3\/82\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T18:27:52Z","timestamp":1760034472000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2227-9709\/12\/3\/82"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,14]]},"references-count":73,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,9]]}},"alternative-id":["informatics12030082"],"URL":"https:\/\/doi.org\/10.3390\/informatics12030082","relation":{},"ISSN":["2227-9709"],"issn-type":[{"value":"2227-9709","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,14]]}}}