{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T16:59:08Z","timestamp":1787417948047,"version":"build-2736575974"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007069","name":"Universit\u00e0 della Calabria","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007069","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In today\u2019s digital landscape, user-generated opinions\u2014such as online reviews, user comments, and social media posts\u2014offer valuable insights into people\u2019s experiences, sentiments, and concerns, influencing decisions across businesses, organizations, and public policy. Advanced machine learning techniques, particularly Large Language Models (LLMs) like BERT and GPT, facilitate the automated analysis of this vast, unstructured data to extract actionable information. However, beyond high classification accuracy, there is a growing demand for explainability to ensure transparency and trust in automated systems. Understanding why an opinion is classified in a particular way is critical for informed decision-making. This paper proposes a multidimensional, explainable framework that combines LLM-based classification across latent dimensions (e.g., sentiment, topic, emotion), interpretable AI for identifying influential words, and generative AI for producing human-readable explanations. Unlike standard explanations generated solely by models such as GPT, our method integrates Explainable AI (XAI) techniques to pinpoint influential words for each classification dimension and organizes them into structured, dimension-aware outputs\u2014significantly enhancing interpretability and alignment with model predictions. Experimental results\u2014based on text-level metrics, latent space representations, and qualitative assessments from both automated tools and human experts\u2014demonstrate the effectiveness of our approach in improving transparency, interpretability, and usability in opinion analysis.<\/jats:p>","DOI":"10.1007\/s10994-026-07037-7","type":"journal-article","created":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T10:51:14Z","timestamp":1780051874000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Interpreting User Opinions: A Multidimensional Approach Leveraging Explainable AI and Generative Models"],"prefix":"10.1007","volume":"115","author":[{"given":"Cristian","family":"Cosentino","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Merve","family":"Gunduz Cure","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabrizio","family":"Marozzo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sule","family":"Ozturk Birim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,29]]},"reference":[{"key":"7037_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101805","volume":"99","author":"S Ali","year":"2023","unstructured":"Ali, S., Abuhmed, T., El-Sappagh, S., Muhammad, K., Alonso-Moral, J. M., Confalonieri, R., Guidotti, R., Del Ser, J., D\u00edaz-Rodr\u00edguez, N., & Herrera, F. (2023). Explainable artificial intelligence (XAI): What we know and what is left to attain trustworthy artificial intelligence. Information Fusion, 99, Article 101805.","journal-title":"Information Fusion"},{"issue":"7","key":"7037_CR2","first-page":"3303","volume":"26","author":"I Ameer","year":"2023","unstructured":"Ameer, I., B\u00f6l\u00fcc\u00fc, N., Siddiqui, M. H. F., Can, B., Sidorov, G., & Gelbukh, A. (2023). Multi-label emotion classification in texts using transfer learning. Expert Systems with Applications, 26(7), 3303\u20133311.","journal-title":"Expert Systems with Applications"},{"key":"7037_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.7717\/peerj-cs.479","volume":"7","author":"E Amparore","year":"2021","unstructured":"Amparore, E., Perotti, A., & Bajardi, P. (2021). To trust or not to trust an explanation: using leaf to evaluate local linear xai methods. PeerJ Computer Science, 7, 1\u201326. https:\/\/doi.org\/10.7717\/peerj-cs.479","journal-title":"PeerJ Computer Science"},{"key":"7037_CR4","doi-asserted-by":"publisher","unstructured":"Andreou, C., Tsapatsoulis, N., & Anastasopoulou, V. (2023). A dataset of hotel reviews for aspect-based sentiment analysis and topic modeling. In 2023 18th International workshop on semantic and social media adaptation and personalization, SMAP 2023 (pp. 1\u20135). https:\/\/doi.org\/10.1109\/SMAP59435.2023.10255219","DOI":"10.1109\/SMAP59435.2023.10255219"},{"key":"7037_CR5","doi-asserted-by":"crossref","unstructured":"Angiulli, F., De\u00a0Luca, F., Fassetti, F., & Nistic\u00f3, S. (2024). Large language models-based local explanations of text classifiers. In International conference on discovery science (pp. 19\u201335). Springer.","DOI":"10.1007\/978-3-031-78977-9_2"},{"key":"7037_CR6","doi-asserted-by":"crossref","unstructured":"Ayanouz, S.e.a. (2020). A smart chatbot architecture based NLP and machine learning for health care assistance. In 3rd International conference on networking, information systems & security.","DOI":"10.1145\/3386723.3387897"},{"key":"7037_CR7","doi-asserted-by":"crossref","unstructured":"Belcastro, L., Cantini, R., Marozzo, F., Talia, D., & Trunfio, P. (2024). Detecting mental disorder on social media: A ChatGPT-augmented explainable approach. arXiv preprint. arXiv:2401.17477","DOI":"10.1016\/j.osnem.2025.100321"},{"issue":"1","key":"7037_CR8","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1007\/s13278-022-00913-9","volume":"12","author":"L Belcastro","year":"2022","unstructured":"Belcastro, L., Branda, F., Cantini, R., Marozzo, F., Talia, D., & Trunfio, P. (2022). Analyzing voter behavior on social media during the 2020 US Presidential Election campaign. Social Network Analysis and Mining, 12(1), 83.","journal-title":"Social Network Analysis and Mining"},{"issue":"12","key":"7037_CR9","doi-asserted-by":"publisher","first-page":"542","DOI":"10.3390\/a16120542","volume":"16","author":"L Belcastro","year":"2023","unstructured":"Belcastro, L., Carbone, D., Cosentino, C., Marozzo, F., & Trunfio, P. (2023). Enhancing cryptocurrency price forecasting by integrating machine learning with social media and market data. Algorithms, 16(12), 542.","journal-title":"Algorithms"},{"key":"7037_CR10","doi-asserted-by":"crossref","unstructured":"Cantini, R., Cosentino, C., & Marozzo, F. (2024). Multi-dimensional classification on social media data for detailed reporting with large language models. In IFIP Int. conference on artificial intelligence applications and innovations (pp. 100\u2013114). Springer.","DOI":"10.1007\/978-3-031-63215-0_8"},{"key":"7037_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.osnem.2024.100295","volume":"45","author":"R Cantini","year":"2025","unstructured":"Cantini, R., Cosentino, C., Marozzo, F., Talia, D., & Trunfio, P. (2025). Harnessing prompt-based large language models for disaster monitoring and automated reporting from social media feedback. Online Social Networks and Media, 45, Article 100295.","journal-title":"Online Social Networks and Media"},{"key":"7037_CR12","unstructured":"Chang, J., Gerrish, S., Wang, C., Boyd-Graber, J., & Blei, D. (2009). Reading tea leaves: How humans interpret topic models. In Advances in neural information processing systems (Vol. 22)."},{"key":"7037_CR13","doi-asserted-by":"publisher","unstructured":"Chochlakis, G., Mahajan, G., Baruah, S., Burghardt, K., Lerman, K., & Narayanan, S. (2023). Leveraging label correlations in a multi-label setting: A case study in emotion. In ICASSP 2023\u20142023 IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ICASSP49357.2023.10096864","DOI":"10.1109\/ICASSP49357.2023.10096864"},{"key":"7037_CR14","doi-asserted-by":"crossref","unstructured":"Cosentino, C., G\u00fcnd\u00fcz-C\u00fcre, M., Marozzo, F., & \u00d6zt\u00fcrk-Birim, \u015e. (2025). Exploiting large language models for enhanced review classification explanations through interpretable and multidimensional analysis. In Int. conference on discovery science (pp. 3\u201318). Springer.","DOI":"10.1007\/978-3-031-78977-9_1"},{"key":"7037_CR15","doi-asserted-by":"crossref","unstructured":"Crisan, A., Butters, N., Butters, N., Zoe. (2024). Exploring subjective notions of explainability through counterfactual visualization of sentiment analysis. In 2024 IEEE evaluation and beyond-methodological approaches for visualization (BELIV) (pp. 15\u201324). IEEE.","DOI":"10.1109\/BELIV64461.2024.00007"},{"key":"7037_CR16","doi-asserted-by":"publisher","DOI":"10.2196\/53559","volume":"11","author":"J Davis","year":"2024","unstructured":"Davis, J., Van Bulck, L., Durieux, B. N., & Lindvall, C. (2024). The temperature feature of ChatGPT: Modifying creativity for clinical research. JMIR Human Factors, 11, Article e53559.","journal-title":"JMIR Human Factors"},{"key":"7037_CR17","unstructured":"Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint. arXiv:1810.04805"},{"key":"7037_CR18","doi-asserted-by":"crossref","unstructured":"Dong, Y. R., Hu, T., & Collier, N. (2024). Can LLM be a personalized judge? arXiv preprint. arXiv:2406.11657","DOI":"10.18653\/v1\/2024.findings-emnlp.592"},{"key":"7037_CR19","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1007\/978-3-031-46781-3_14","volume-title":"Integrated uncertainty in knowledge modelling and decision making","author":"H Duong","year":"2023","unstructured":"Duong, H., Hoang, L., & Le, B. (2023). Controlling lime kernel width to achieve comprehensible explanations on tabular data. In K. Honda, B. Le, V.-N. Huynh, M. Inuiguchi, & Y. Kohda (Eds.), Integrated uncertainty in knowledge modelling and decision making (pp. 153\u2013164). Springer."},{"key":"7037_CR20","doi-asserted-by":"publisher","DOI":"10.3389\/fsoc.2022.886498","volume":"7","author":"R Egger","year":"2022","unstructured":"Egger, R., & Yu, J. (2022). A topic modeling comparison between LDA, NMF, Top2Vec, and BERTopic to demystify twitter posts. Frontiers in Sociology, 7, Article 886498.","journal-title":"Frontiers in Sociology"},{"key":"7037_CR21","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1007\/978-981-99-9109-9_37","volume-title":"Artificial intelligence and robotics","author":"L Gan","year":"2024","unstructured":"Gan, L., Yang, T., Huang, Y., Yang, B., Luo, Y. Y., Richard, L. W. C., & Guo, D. (2024). Experimental comparison of three topic modeling methods with LDA, Top2Vec and BERTopic. In H. Lu & J. Cai (Eds.), Artificial intelligence and robotics (pp. 376\u2013391). Springer."},{"key":"7037_CR22","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1186\/1472-6823-13-47","volume":"13","author":"P Gayoso-Diz","year":"2013","unstructured":"Gayoso-Diz, P., Otero-Gonz\u00e1lez, A., Rodriguez-Alvarez, M. X., Gude, F., Garc\u00eda, F., De Francisco, A., & Quintela, A. G. (2013). Insulin resistance (HOMA-IR) cut-off values and the metabolic syndrome in a general adult population: Effect of gender and age: Epirce cross-sectional study. BMC Endocrine Disorders, 13, 47.","journal-title":"BMC Endocrine Disorders"},{"issue":"30","key":"7037_CR23","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2305016120","volume":"120","author":"F Gilardi","year":"2023","unstructured":"Gilardi, F., Alizadeh, M., & Kubli, M. (2023). ChatGPT outperforms crowd workers for text-annotation tasks. Proceedings of the National Academy of Sciences of United States of America, 120(30), Article e2305016120.","journal-title":"Proceedings of the National Academy of Sciences of United States of America"},{"key":"7037_CR24","doi-asserted-by":"publisher","unstructured":"Grootendorst, M. (2022). BERTopic: Neural topic modeling with a class-based TF-IDF procedure. arXiv Preprint. https:\/\/doi.org\/10.48550\/arXiv.2203.05794","DOI":"10.48550\/arXiv.2203.05794"},{"issue":"5","key":"7037_CR25","doi-asserted-by":"publisher","first-page":"2770","DOI":"10.1007\/s10618-024-01087-1","volume":"38","author":"R Guidotti","year":"2024","unstructured":"Guidotti, R. (2024). Counterfactual explanations and how to find them: literature review and benchmarking. Data Mining and Knowledge Discovery, 38(5), 2770\u20132824. https:\/\/doi.org\/10.1007\/s10618-024-01087-1","journal-title":"Data Mining and Knowledge Discovery"},{"key":"7037_CR26","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-030-76409-8_2","volume-title":"Explainable AI within the digital transformation and cyber physical systems: XAI methods and applications","author":"R Guidotti","year":"2021","unstructured":"Guidotti, R., Monreale, A., Pedreschi, D., & Giannotti, F. (2021). Principles of explainable artificial intelligence. In M. Sayed-Mouchaweh (Ed.), Explainable AI within the digital transformation and cyber physical systems: XAI methods and applications (pp. 9\u201331). Springer."},{"issue":"84","key":"7037_CR27","doi-asserted-by":"publisher","first-page":"5153","DOI":"10.21105\/joss.05153","volume":"8","author":"L Hansen","year":"2023","unstructured":"Hansen, L., et al. (2023). Textdescriptives: A python package for calculating a large variety of metrics from text. Journal of Open Source Software, 8(84), 5153.","journal-title":"Journal of Open Source Software"},{"key":"7037_CR28","doi-asserted-by":"publisher","first-page":"77132","DOI":"10.1109\/ACCESS.2023.3298445","volume":"11","author":"AT Haryono","year":"2023","unstructured":"Haryono, A. T., Sarno, R., & Sungkono, K. R. (2023). Transformer-gated recurrent unit method for predicting stock price based on news sentiments and technical indicators. IEEE Access, 11, 77132\u201377146. https:\/\/doi.org\/10.1109\/ACCESS.2023.3298445","journal-title":"IEEE Access"},{"key":"7037_CR29","doi-asserted-by":"crossref","unstructured":"Hossain, M., Habib, M., Hassan, M., Soroni, F., & Khan, M. M. (2022). Research and development of an e-commerce with sales chatbot. In 2022 IEEE World AI IoT Congress (AIIoT) (pp. 557\u2013564).","DOI":"10.1109\/AIIoT54504.2022.9817272"},{"key":"7037_CR30","doi-asserted-by":"crossref","unstructured":"Hsu, C.-C., Wu, I.-Z., & Liu, S.-M. (2024). Decoding AI complexity: SHAP textual explanations via LLM for improved model transparency. In 2024 International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan) (pp. 197\u2013198). IEEE.","DOI":"10.1109\/ICCE-Taiwan62264.2024.10674465"},{"key":"7037_CR31","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.3390\/app9061123","volume":"9","author":"M Jabreel","year":"2019","unstructured":"Jabreel, M., & Moreno, A. (2019). A deep learning-based approach for multi-label emotion classification in tweets. Applied Sciences, 9, 1123.","journal-title":"Applied Sciences"},{"key":"7037_CR32","first-page":"209","volume-title":"Emerging research challenges and opportunities in computational social network analysis and mining","author":"S Jaradat","year":"2019","unstructured":"Jaradat, S., & Matskin, M. (2019). On dynamic topic models for mining social media. In N. Agarwal, N. Dokoohaki, & S. Tokdemir (Eds.), Emerging research challenges and opportunities in computational social network analysis and mining (pp. 209\u2013230). Springer."},{"key":"7037_CR33","doi-asserted-by":"crossref","unstructured":"Kirchner, K., Opuszko, M., & Gehrke, S. (2021). In J. Papathanasiou, P. Zarat\u00e9, & J. Sousa (Eds.), Decision support in the era of social media and user-generated content (pp. 79\u201395). Springer.","DOI":"10.1007\/978-3-030-70377-6_5"},{"key":"7037_CR34","doi-asserted-by":"crossref","unstructured":"Knab, P., Marton, S., Schlegel, U., & Bartelt, C. (2025). Which LIME should I trust? concepts, challenges, and solutions. In R. Guidotti, U. Schmid, & L. Longo (Eds.), Explainable artificial intelligence, xAI 2025. Communications in computer and information science (Vol. 2577). Springer.","DOI":"10.1007\/978-3-032-08324-1_2"},{"issue":"1","key":"7037_CR35","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s40547-024-00143-4","volume":"11","author":"JO Krugmann","year":"2024","unstructured":"Krugmann, J. O., & Hartmann, J. (2024). Sentiment analysis in the age of generative AI. Customer Needs and Solutions, 11(1), 3.","journal-title":"Customer Needs and Solutions"},{"key":"7037_CR36","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1016\/j.neunet.2022.03.017","volume":"150","author":"P Kumar","year":"2022","unstructured":"Kumar, P., & Raman, B. (2022). A bert based dual-channel explainable text emotion recognition system. Neural Networks, 150, 392\u2013407.","journal-title":"Neural Networks"},{"key":"7037_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1108\/INTR-08-2021-0600","volume":"32","author":"S Laato","year":"2022","unstructured":"Laato, S., Tiainen, M., NajmulIslam, A. K. M., & M\u00e4ntym\u00e4ki, M. (2022). How to explain ai systems to end users: A systematic literature review and research agenda. Internet Research, 32, 1\u201331.","journal-title":"Internet Research"},{"issue":"1","key":"7037_CR38","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","volume":"33","author":"JR Landis","year":"1977","unstructured":"Landis, J. R., & Koch, G. G. (1977). The measurement of observer agreement for categorical data. Biometrics, 33(1), 159\u2013174.","journal-title":"Biometrics"},{"key":"7037_CR39","doi-asserted-by":"crossref","unstructured":"Lau, J. H., Newman, D., & Baldwin, T. (2014). Machine reading tea leaves: Automatically evaluating topic coherence and topic model quality. In Proceedings of the 14th conference of the European chapter of the Association for Computational Linguistics (pp. 530\u2013539).","DOI":"10.3115\/v1\/E14-1056"},{"key":"7037_CR40","unstructured":"Lis, M., & Kowalski, A. (2023). A comparative study of sentence embedding models for semantic clustering. In Proceedings of EMNLP, 2023."},{"key":"7037_CR41","volume":"170","author":"D Lottridge","year":"2023","unstructured":"Lottridge, D., & Woolf, B. (2023). User-centered evaluation of explanation methods for natural language models. International Journal of Human-Computer Studies, 170, Article 103097.","journal-title":"International Journal of Human-Computer Studies"},{"key":"7037_CR42","doi-asserted-by":"publisher","DOI":"10.1016\/j.dss.2025.114402","volume":"191","author":"D Martens","year":"2025","unstructured":"Martens, D., Hinns, J., Dams, C., Vergouwen, M., & Evgeniou, T. (2025). Tell me a story! narrative-driven XAI with large language models. Decision Support Systems, 191, Article 114402.","journal-title":"Decision Support Systems"},{"issue":"3","key":"7037_CR43","doi-asserted-by":"publisher","first-page":"3803","DOI":"10.1109\/TNSM.2023.3236994","volume":"20","author":"W Meng","year":"2023","unstructured":"Meng, W., Zaiter, F., Zhang, Y., Liu, Y., Zhang, S., Tao, S., Zhu, Y., Han, T., Zhao, Y., Wang, E., et al. (2023). Logsummary: Unstructured log summarization for software systems. IEEE Transactions on Network and Service Management, 20(3), 3803\u20133815.","journal-title":"IEEE Transactions on Network and Service Management"},{"key":"7037_CR44","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2025.113042","volume":"310","author":"MA Mersha","year":"2025","unstructured":"Mersha, M. A., Yigezu, M. G., & Kalita, J. (2025). Evaluating the effectiveness of XAI techniques for encoder-based language models. Knowledge-Based Systems, 310, Article 113042.","journal-title":"Knowledge-Based Systems"},{"key":"7037_CR45","doi-asserted-by":"crossref","unstructured":"Mohammad, S. M., Bravo-Marquez, F., Salameh, M., & Kiritchenko, S. SemEval-2018 Task 1: Affect in Tweets. In Proceedings of the 12th international workshop on semantic evaluation. Association for Computational Linguistics.","DOI":"10.18653\/v1\/S18-1001"},{"key":"7037_CR46","doi-asserted-by":"publisher","first-page":"287","DOI":"10.3758\/s13428-025-02746-8","volume":"57","author":"F Moons","year":"2025","unstructured":"Moons, F., & Vandervieren, E. (2025). Measuring agreement among several raters classifying subjects into one or more (hierarchical) categories: A generalization of Fleiss\u2019 kappa. Behavior Research Methods, 57, 287. https:\/\/doi.org\/10.3758\/s13428-025-02746-8","journal-title":"Behavior Research Methods"},{"key":"7037_CR47","doi-asserted-by":"crossref","unstructured":"Morichetta, A., Casas, P., & Mellia, M. (2019). Explain-it: Towards explainable AI for unsupervised network traffic analysis. In Proceedings of the 3rd ACM CoNEXT workshop on Big DAta, machine learning and artificial intelligence for data communication networks (pp. 22\u201328).","DOI":"10.1145\/3359992.3366639"},{"issue":"1","key":"7037_CR48","doi-asserted-by":"publisher","first-page":"185","DOI":"10.2307\/20721420","volume":"34","author":"SM Mudambi","year":"2010","unstructured":"Mudambi, S. M., & Schuff, D. (2010). Research note: What makes a helpful online review? A study of customer reviews on Amazon.Com1. MIS Quarterly, 34(1), 185\u2013200.","journal-title":"MIS Quarterly"},{"issue":"1","key":"7037_CR49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10586-023-04203-7","volume":"27","author":"D Myers","year":"2024","unstructured":"Myers, D., Mohawesh, R., Chellaboina, V. I., et al. (2024). Foundation and large language models: Fundamentals, challenges, opportunities, and social impacts. Cluster Computing, 27(1), 1\u201326.","journal-title":"Cluster Computing"},{"key":"7037_CR50","unstructured":"Nasiri Lahmer, S., Haddoud, M., & Smaili, K. (2024). Semantic representation learning with transformer models: A comparative study for clustering. Knowledge-Based Systems."},{"issue":"3","key":"7037_CR51","volume":"59","author":"T Nguyen","year":"2022","unstructured":"Nguyen, T. (2022). On the faithfulness of lime explanations for text classification. Information Processing & Management, 59(3), Article 102922.","journal-title":"Information Processing & Management"},{"key":"7037_CR52","doi-asserted-by":"crossref","unstructured":"Plutchik, R. (1980). A general psychoevolutionary theory of emotion. In Emotion: Theory, research, and experience (Vol. 1). Academic Press.","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"7037_CR53","doi-asserted-by":"crossref","unstructured":"Po\u015bwiata, R., & Pere\u0142kiewicz, M. (2022). OPI@LT-EDI-ACL2022: Detecting signs of depression from social media text using RoBERTa pre-trained language models. In The Second workshop on language technology for equality, diversity and inclusion (pp. 276\u2013282).","DOI":"10.18653\/v1\/2022.ltedi-1.40"},{"key":"7037_CR54","doi-asserted-by":"crossref","unstructured":"Qu, J., Arguello, J., & Wang, Y. (2025). Understanding the effects of explaining predictive but unintuitive features in human\u2013XAI interaction. In Proceedings of the 2025 ACM conference on fairness, accountability, and transparency (pp. 296\u2013311).","DOI":"10.1145\/3715275.3732021"},{"key":"7037_CR55","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). why should I trust you? Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 1135\u20131144).","DOI":"10.1145\/2939672.2939778"},{"issue":"2","key":"7037_CR56","doi-asserted-by":"publisher","first-page":"297","DOI":"10.15294\/sji.v8i2.29992","volume":"8","author":"N Ririanti","year":"2021","unstructured":"Ririanti, N., & Purwinarko, A. (2021). Implementation of support vector machine algorithm with correlation-based feature selection and term frequency inverse document frequency for sentiment analysis review hotel. Scientific Journal of Informatics, 8(2), 297\u2013303. https:\/\/doi.org\/10.15294\/sji.v8i2.29992","journal-title":"Scientific Journal of Informatics"},{"key":"7037_CR57","unstructured":"Sundararajan, M., Taly, A., & Yan, Q. (2017). Axiomatic attribution for deep networks. In Proceedings of the 34th international conference on machine learning (pp. 3319\u20133328)."},{"key":"7037_CR59","doi-asserted-by":"crossref","unstructured":"Visani, G., Bagli, E., Chesani, F., Poluzzi, A., & Capuzzo, D. (2022). Statistical stability indices for lime: Obtaining reliable explanations for machine learning models. Journal of the Operational Research Society,73(1), 91\u2013101. Proposes VSI and CSI metrics for LIME stability across repeated runs.","DOI":"10.1080\/01605682.2020.1865846"},{"key":"7037_CR60","doi-asserted-by":"crossref","unstructured":"Wang, F., Xu, Z., Szekely, P., & Chen, M. (2022). Robust (controlled) table-to-text generation with structure-aware equivariance learning. arXiv:2205.03972","DOI":"10.18653\/v1\/2022.naacl-main.371"},{"issue":"3","key":"7037_CR61","doi-asserted-by":"publisher","first-page":"1390","DOI":"10.1109\/TCSS.2025.3531718","volume":"12","author":"X Wang","year":"2025","unstructured":"Wang, X., Lyu, J., Peter, J. D., Kim, B.-G., Parameshachari, B., Li, K., & Wei, W. (2025). Explaining sentiments: Improving explainability in sentiment analysis using local interpretable model-agnostic explanations and counterfactual explanations. IEEE Transactions on Computational Social Systems, 12(3), 1390\u20131403.","journal-title":"IEEE Transactions on Computational Social Systems"},{"issue":"1","key":"7037_CR62","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1186\/s40537-023-00842-0","volume":"11","author":"H Zhang","year":"2024","unstructured":"Zhang, H., & Shafiq, M. O. (2024). Survey of transformers and towards ensemble learning using transformers for natural language processing. Journal of Big Data, 11(1), 25.","journal-title":"Journal of Big Data"},{"key":"7037_CR63","doi-asserted-by":"crossref","unstructured":"Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al. (2023). Judging LLM-as-a-judge with mt-bench and chatbot arena. In Advances in neural information processing systems (Vol. 36, pp. 46595\u201346623).","DOI":"10.52202\/075280-2020"},{"key":"7037_CR64","volume":"21","author":"W Zhou","year":"2025","unstructured":"Zhou, W., Li, C., & Xu, Y. (2025). A benchmark of transformer embedding models for clustering tasks. Information Processing & Management, 21, Article 100683.","journal-title":"Information Processing & Management"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-026-07037-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-026-07037-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-026-07037-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T07:13:00Z","timestamp":1783753980000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-026-07037-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,29]]},"references-count":63,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["7037"],"URL":"https:\/\/doi.org\/10.1007\/s10994-026-07037-7","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,29]]},"assertion":[{"value":"3 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 January 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 May 2026","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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"140"}}