{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T17:12:09Z","timestamp":1783789929072,"version":"3.55.0"},"reference-count":56,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T00:00:00Z","timestamp":1746144000000},"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":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Explaining predictions of classifiers is a fundamental problem in eXplainable Artificial Intelligence (XAI). LIME (for Local Interpretable Model-agnostic Explanations) is a popular XAI technique able to explain any classifier by providing an interpretable model which approximates the black box locally to the instance under consideration. In order to build interpretable local models, LIME requires the user to explicitly define a space of interpretable components, also called artefacts, associated with the input instance. To reconstruct local black-box behaviour, the instance neighbourhood is explored by generating instance neighbours as random subsets of the provided artefacts. In this work, we note that the above-depicted strategy has a limitation given by the fact that the local explanation is limited to be expressed only in terms of object artefacts. To overcome this limitation, in this work we propose <jats:inline-formula>\n              <jats:alternatives>\n                <jats:tex-math>$$\\mathcal {S}{\\text {-LIME}}$$<\/jats:tex-math>\n                <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\">\n                  <mml:mrow>\n                    <mml:mi>S<\/mml:mi>\n                    <mml:mtext>-LIME<\/mml:mtext>\n                  <\/mml:mrow>\n                <\/mml:math>\n              <\/jats:alternatives>\n            <\/jats:inline-formula>, a variant of the basic LIME method exploiting unsupervised learning to replace object artefacts with self-generated semantic features in neighbourhood generation. This characteristic enables our approach to sample instance neighbours in a more semantic-driven fashion and greatly reduces the bias associated with explanations. We demonstrate the applicability and effectiveness of our proposal in the text classification domain. We also present a further extension for textual data in which word groups are used to obtain richer explanations. Comparison with the baseline highlights the superior quality of the explanations obtained by adopting our strategy.<\/jats:p>","DOI":"10.1007\/s00521-025-11227-0","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T13:51:07Z","timestamp":1746193867000},"page":"13617-13641","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Improving local interpretable classifier explanations exploiting self-generated semantic features"],"prefix":"10.1007","volume":"37","author":[{"given":"Fabrizio","family":"Angiulli","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Fassetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7386-2512","authenticated-orcid":false,"given":"Simona","family":"Nistic\u00f2","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,5,2]]},"reference":[{"issue":"1","key":"11227_CR1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332","journal-title":"Mach Learn"},{"issue":"7553","key":"11227_CR2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"11227_CR3","unstructured":"Vaswani A (2017) Attention is all you need. In: Advances in Neural Information Processing Systems"},{"key":"11227_CR4","doi-asserted-by":"publisher","unstructured":"Hamon R, Junklewitz H, Malgieri G, Hert PD, Beslay L, Sanchez I (2021) Impossible explanations? beyond explainable AI in the GDPR from a COVID-19 use case scenario. FAccT \u201921. ACM, New York, pp 549\u2013559. https:\/\/doi.org\/10.1145\/3442188.3445917","DOI":"10.1145\/3442188.3445917"},{"key":"11227_CR5","doi-asserted-by":"crossref","unstructured":"Brennen A (2020) What do people really want when they say they want \u201cexplainable AI?\" we asked 60 stakeholders. In: Extended abstracts of the 2020 CHI conference on human factors in computing systems, pp 1\u20137","DOI":"10.1145\/3334480.3383047"},{"issue":"3","key":"11227_CR6","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1145\/3313096","volume":"25","author":"M Hind","year":"2019","unstructured":"Hind M (2019) Explaining explainable AI. XRDS: Crossroads ACM Mag Stud 25(3):16\u201319","journal-title":"XRDS: Crossroads ACM Mag Stud"},{"key":"11227_CR7","unstructured":"Preece A, Harborne D, Braines D, Tomsett R, Chakraborty S (2018) Stakeholders in explainable AI. arXiv preprint arXiv:1810.00184"},{"key":"11227_CR8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.inffus.2019.12.012","volume":"58","author":"AB Arrieta","year":"2020","unstructured":"Arrieta AB, D\u00edaz-Rodr\u00edguez N, Del Ser J, Bennetot A, Tabik S, Barbado A, Garc\u00eda S, Gil-L\u00f3pez S, Molina D, Benjamins R (2020) Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Inf Fusion 58:82\u2013115","journal-title":"Inf Fusion"},{"key":"11227_CR9","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2016) \u201cwhy should i trust you?\" explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD KDD, pp 1135\u20131144","DOI":"10.1145\/2939672.2939778"},{"key":"11227_CR10","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1016\/j.patrec.2021.06.030","volume":"150","author":"M Ivanovs","year":"2021","unstructured":"Ivanovs M, Kadikis R, Ozols K (2021) Perturbation-based methods for explaining deep neural networks: a survey. Pattern Recogn Lett 150:228\u2013234","journal-title":"Pattern Recogn Lett"},{"key":"11227_CR11","unstructured":"Petsiuk V, Das A, Saenko K (2018) Rise: randomized input sampling for explanation of black-box models. arXiv preprint arXiv:1806.07421"},{"key":"11227_CR12","doi-asserted-by":"crossref","unstructured":"Fong RC, Vedaldi A (2017) Interpretable explanations of black boxes by meaningful perturbation. In: Proceedings of the IEEE ICCV, pp 3429\u20133437","DOI":"10.1109\/ICCV.2017.371"},{"key":"11227_CR13","unstructured":"Dabkowski P, Gal Y (2017) Real time image saliency for black box classifiers. In: Advances in neural information processing systems, vol 30"},{"key":"11227_CR14","doi-asserted-by":"crossref","unstructured":"Angiulli F, Fassetti F, Nistic\u00f2 S (2021) Finding local explanations through masking models. In: IDEAL 2021. Springer, pp 467\u2013475","DOI":"10.1007\/978-3-030-91608-4_46"},{"key":"11227_CR15","doi-asserted-by":"publisher","unstructured":"Fong R, Patrick M, Vedaldi A (2019) Understanding deep networks via extremal perturbations and smooth masks. In: 2019 IEEE\/CVF ICCV (ICCV), pp 2950\u20132958. https:\/\/doi.org\/10.1109\/ICCV.2019.00304","DOI":"10.1109\/ICCV.2019.00304"},{"key":"11227_CR16","doi-asserted-by":"crossref","unstructured":"Yang Q, Zhu X, Fwu J-K, Ye Y, You G, Zhu Y (2021) MFPP: morphological fragmental perturbation pyramid for black-box model explanations. In: 2020 25th ICPR, IEEE, pp 1376\u20131383","DOI":"10.1109\/ICPR48806.2021.9413046"},{"key":"11227_CR17","unstructured":"Greydanus S, Koul A, Dodge J, Fern A (2018) Visualizing and understanding Atari agents. In: ICML. PMLR, pp 1792\u20131801"},{"key":"11227_CR18","unstructured":"Puri N, Verma S, Gupta P, Kayastha D, Deshmukh S, Krishnamurthy B, Singh S (2019) Explain your move: Understanding agent actions using specific and relevant feature attribution. arXiv preprint arXiv:1912.12191"},{"key":"11227_CR19","unstructured":"Lundberg S, Lee S-I (2017) A unified approach to interpreting model predictions. arXiv preprint arXiv:1705.07874"},{"key":"11227_CR20","unstructured":"Karimi A-H, Barthe G, Balle B, Valera I (2020) Model-agnostic counterfactual explanations for consequential decisions. In: AISTATS. PMLR, pp 895\u2013905"},{"key":"11227_CR21","doi-asserted-by":"crossref","unstructured":"Mothilal RK, Sharma A, Tan C (2020) Explaining machine learning classifiers through diverse counterfactual explanations. In: Proceedings of the 2020 conference on fairness, accountability, and transparency, pp 607\u2013617","DOI":"10.1145\/3351095.3372850"},{"key":"11227_CR22","doi-asserted-by":"crossref","unstructured":"Laugel T, Lesot M-J, Marsala C, Renard X, Detyniecki M (2017) Inverse classification for comparison-based interpretability in machine learning. arXiv preprint arXiv:1712.08443","DOI":"10.1007\/978-3-319-91473-2_9"},{"issue":"6","key":"11227_CR23","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/MIS.2019.2957223","volume":"34","author":"R Guidotti","year":"2019","unstructured":"Guidotti R, Monreale A, Giannotti F, Pedreschi D, Ruggieri S, Turini F (2019) Factual and counterfactual explanations for black box decision making. IEEE Intell Syst 34(6):14\u201323","journal-title":"IEEE Intell Syst"},{"key":"11227_CR24","unstructured":"Goyal Y, Wu Z, Ernst J, Batra D, Parikh D, Lee S (2019) Counterfactual visual explanations. In: ICML. PMLR, pp. 2376\u20132384"},{"key":"11227_CR25","unstructured":"Agarwal S, Jabbari S, Agarwal C, Upadhyay S, Wu S, Lakkaraju H (2021) Towards the unification and robustness of perturbation and gradient based explanations. In: ICML. PMLR, pp 110\u2013119"},{"key":"11227_CR26","unstructured":"Shrikumar A, Greenside P, Kundaje A (2017) Learning important features through propagating activation differences. In: ICML, PMLR, pp 3145\u20133153"},{"key":"11227_CR27","unstructured":"Smilkov D, Thorat N, Kim B, Vi\u00e9gas F, Wattenberg M (2017) SmoothGrad: removing noise by adding noise. arXiv preprint arXiv:1706.03825"},{"key":"11227_CR28","unstructured":"Simonyan K, Vedaldi A, Zisserman A (2014) Visualising image classification models and saliency maps. Deep Inside Convolutional Networks"},{"key":"11227_CR29","unstructured":"Sundararajan M, Taly A, Yan Q (2017) Axiomatic attribution for deep networks. In: ICML, PMLR, pp 3319\u20133328"},{"key":"11227_CR30","doi-asserted-by":"crossref","unstructured":"Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D (2017) Grad-CAM: visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE ICCV, pp 618\u2013626","DOI":"10.1109\/ICCV.2017.74"},{"key":"11227_CR31","doi-asserted-by":"crossref","unstructured":"Montavon G, Binder A, Lapuschkin S, Samek W, M\u00fcller K-R (2019) Layer-wise relevance propagation: an overview. Explainable AI: interpreting, explaining and visualizing deep learning, 193\u2013209","DOI":"10.1007\/978-3-030-28954-6_10"},{"key":"11227_CR32","doi-asserted-by":"crossref","unstructured":"Ribeiro MT, Singh S, Guestrin C (2018) Anchors: high-precision model-agnostic explanations. In: Proceedings of the AAAI conference on artificial intelligence, vol 32","DOI":"10.1609\/aaai.v32i1.11491"},{"key":"11227_CR33","unstructured":"Guidotti R, Monreale A, Ruggieri S, Pedreschi D, Turini F, Giannotti F (2018) Local rule-based explanations of black box decision systems. arXiv preprint arXiv:1805.10820"},{"key":"11227_CR34","unstructured":"Zafar MR, Khan NM (2019) DLIME: a deterministic local interpretable model-agnostic explanations approach for computer-aided diagnosis systems. arXiv preprint arXiv:1906.10263"},{"key":"11227_CR35","unstructured":"Visani G, Bagli E, Chesani F (2020) OptiLIME: optimized lime explanations for diagnostic computer algorithms. arXiv preprint arXiv:2006.05714"},{"key":"11227_CR36","unstructured":"Sokol K, Hepburn A, Santos-Rodriguez R, Flach P (2019) bLIMEy: surrogate prediction explanations beyond LIME. arXiv preprint arXiv:1910.13016"},{"key":"11227_CR37","unstructured":"Schockaert C, Macher V, Schmitz A (2020) VAE-LIME: deep generative model based approach for local data-driven model interpretability applied to the ironmaking industry. arXiv preprint arXiv:2007.10256"},{"key":"11227_CR38","doi-asserted-by":"publisher","unstructured":"Zhou Z, Hooker G, Wang F (2021) S-LIME: stabilized-lime for model explanation. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. KDD \u201921. Association for Computing Machinery, New York, pp 2429\u20132438. https:\/\/doi.org\/10.1145\/3447548.3467274","DOI":"10.1145\/3447548.3467274"},{"key":"11227_CR39","unstructured":"Zhao X, Huang X, Robu V, Flynn D (2021) BayLIME: Bayesian local interpretable model-agnostic explanations. In: Conference on uncertainty in artificial intelligence. https:\/\/api.semanticscholar.org\/CorpusID:227334656"},{"key":"11227_CR40","unstructured":"Tan Z, Tian Y, Li J (2023) GLIME: general, stable and local LIME explanation. In: Thirty-seventh conference on neural information processing systems. https:\/\/openreview.net\/forum?id=3FJaFElIVN"},{"key":"11227_CR41","doi-asserted-by":"publisher","first-page":"1369","DOI":"10.1109\/LSP.2024.3398358","volume":"31","author":"X Li","year":"2024","unstructured":"Li X, Xu F, Gao H, Liu F, Lyu X (2024) A frequency domain feature-guided network for semantic segmentation of remote sensing images. IEEE Signal Process Lett 31:1369\u20131373. https:\/\/doi.org\/10.1109\/LSP.2024.3398358","journal-title":"IEEE Signal Process Lett"},{"key":"11227_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3243954","volume":"61","author":"X Li","year":"2023","unstructured":"Li X, Xu F, Liu F, Lyu X, Tong Y, Xu Z, Zhou J (2023) A synergistical attention model for semantic segmentation of remote sensing images. IEEE Trans Geosci Remote Sens 61:1\u201316. https:\/\/doi.org\/10.1109\/TGRS.2023.3243954","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11227_CR43","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TGRS.2023.3339291","volume":"62","author":"X Li","year":"2024","unstructured":"Li X, Xu F, Liu F, Tong Y, Lyu X, Zhou J (2024) Semantic segmentation of remote sensing images by interactive representation refinement and geometric prior-guided inference. IEEE Trans Geosci Remote Sens 62:1\u201318. https:\/\/doi.org\/10.1109\/TGRS.2023.3339291","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"11227_CR44","doi-asserted-by":"publisher","unstructured":"Ou J, Lin\u2019 H, Qiang Z, Chen Z (2022) Survey of images semantic segmentation based on deep learning. In: 2022 IEEE 8th international conference on cloud computing and intelligent systems (CCIS), pp 456\u2013463. https:\/\/doi.org\/10.1109\/CCIS57298.2022.10016328","DOI":"10.1109\/CCIS57298.2022.10016328"},{"key":"11227_CR45","unstructured":"Shen T, Mueller J, Barzilay R, Jaakkola T (2020) Educating text autoencoders: latent representation guidance via denoising. In: ICML, PMLR, pp 8719\u20138729"},{"key":"11227_CR46","unstructured":"Makhzani A, Shlens J, Jaitly N, Goodfellow I, Frey B (2015) Adversarial autoencoders. arXiv preprint arXiv:1511.05644"},{"key":"11227_CR47","unstructured":"Kingma DP, Welling M (2013) Auto-Encoding Variational Bayes"},{"issue":"1","key":"11227_CR48","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"R Tibshirani","year":"1996","unstructured":"Tibshirani R (1996) Regression shrinkage and selection via the lasso. J Roy Stat Soc: Ser B (Methodol) 58(1):267\u2013288","journal-title":"J Roy Stat Soc: Ser B (Methodol)"},{"key":"11227_CR49","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":"11227_CR50","unstructured":"Liu Y, Ott M, Goyal N, Du J, Joshi M, Chen D, Levy O, Lewis M, Zettlemoyer L, Stoyanov V (2019) Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692"},{"issue":"4","key":"11227_CR51","first-page":"35","volume":"24","author":"A Singhal","year":"2001","unstructured":"Singhal A (2001) Modern information retrieval: a brief overview. IEEE Data Eng Bull 24(4):35\u201343","journal-title":"IEEE Data Eng Bull"},{"key":"11227_CR52","unstructured":"Shen T, Lei T, Barzilay R, Jaakkola T (2017) Style transfer from non-parallel text by cross-alignment. arXiv preprint arXiv:1705.09655"},{"key":"11227_CR53","first-page":"3881","volume-title":"Proceedings of the 34th ICML. Proceedings of Machine Learning Research","author":"Z Yang","year":"2017","unstructured":"Yang Z, Hu Z, Salakhutdinov R, Berg-Kirkpatrick T (2017) Improved variational autoencoders for text modeling using dilated convolutions. In: Precup D, Teh YW (eds) Proceedings of the 34th ICML. Proceedings of Machine Learning Research, vol 70. PMLR, New York, pp 3881\u20133890"},{"key":"11227_CR54","unstructured":"Rish I (2001) An empirical study of the naive bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, vol 3, pp 41\u201346"},{"issue":"3731","key":"11227_CR55","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1126\/science.153.3731.34","volume":"153","author":"R Bellman","year":"1966","unstructured":"Bellman R (1966) Dynamic programming. Science 153(3731):34\u201337","journal-title":"Science"},{"key":"11227_CR56","unstructured":"Lutz M. Programming python 4th Edition Trainingdata.zip. Available at: http:\/\/help.sentiment140.com\/for-students"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11227-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11227-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11227-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,27]],"date-time":"2025-06-27T08:29:21Z","timestamp":1751012961000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11227-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,2]]},"references-count":56,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11227"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11227-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,2]]},"assertion":[{"value":"24 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 May 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"No conflicts to declare.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}]}}