{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T10:07:02Z","timestamp":1784196422743,"version":"3.55.0"},"reference-count":39,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T00:00:00Z","timestamp":1783987200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Measuring semantic similarity between words or phrases is central to natural language processing, information retrieval and computational linguistics. Despite their importance, similarity and distance measures are typically chosen by default (e.g., cosine similarity) or in an ad hoc fashion, with little empirical justification. This lack of systematic evaluation creates two gaps: first, the absence of a comprehensive taxonomy of measures that spans set\u2010based, vector\u2010based and information\u2010theoretic approaches; second, the lack of task\u2010aware benchmarking that quantifies how these measures perform across different models and applications. In this paper, we address these gaps by comparing 15 similarity and distance measures on four NLP tasks (sentence similarity, kNN classification, correlation analysis and visualisation) using multiple benchmark datasets and embedding models. Our results reveal that the effectiveness of similarity measures varies substantially depending on the task and model, challenging the assumption that cosine similarity is universally optimal. These findings highlight the practical risk of relying on default measures and provide a principled basis for selecting similarity functions in NLP, information retrieval and related fields.<\/jats:p>","DOI":"10.1111\/exsy.70354","type":"journal-article","created":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T07:40:46Z","timestamp":1784014846000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Benchmarking Distributional Vector Similarity Measures: A Survey"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3030-1280","authenticated-orcid":false,"given":"Erik","family":"Cambria","sequence":"first","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University  Singapore Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9964-097X","authenticated-orcid":false,"given":"Navid","family":"Nobani","sequence":"additional","affiliation":[{"name":"Department of Statistics and Quantitative Methods University of Milan\u2010Bicocca  Milan Italy"},{"name":"CRISP Research Centre, University of Milan\u2010Bicocca  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0190-2833","authenticated-orcid":false,"given":"Filippo","family":"Pallucchini","sequence":"additional","affiliation":[{"name":"Department of Statistics and Quantitative Methods University of Milan\u2010Bicocca  Milan Italy"},{"name":"CRISP Research Centre, University of Milan\u2010Bicocca  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6864-2702","authenticated-orcid":false,"given":"Fabio","family":"Mercorio","sequence":"additional","affiliation":[{"name":"Department of Statistics and Quantitative Methods University of Milan\u2010Bicocca  Milan Italy"},{"name":"CRISP Research Centre, University of Milan\u2010Bicocca  Milan Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,14]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1089\/big.2018.0175"},{"key":"e_1_2_9_3_1","first-page":"2476","volume-title":"International Joint Conference on Neural Networks (IJCNN)","author":"Bisio F.","year":"2015"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-024-10373-2"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.2307\/1942268"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.63317\/5gome7j43yse"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2023.3329745"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2026.3677113"},{"key":"e_1_2_9_9_1","volume-title":"SemEval\u20102017","author":"Cer D.","year":"2017"},{"issue":"1","key":"e_1_2_9_10_1","first-page":"43","article-title":"A Survey of Binary Similarity and Distance Measures","volume":"8","author":"Choi S. S.","year":"2010","journal-title":"Journal of Systemics, Cybernetics and Informatics"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191745"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3295776"},{"key":"e_1_2_9_14_1","article-title":"Supervised Word Mover's Distance","volume":"29","author":"Huang G.","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2505665"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/9.1.60"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.104.2.211"},{"key":"e_1_2_9_19_1","volume-title":"Newsweeder: Learning to Filter Netnews","author":"Lang K.","year":"1995"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1017\/9780511783692"},{"key":"e_1_2_9_21_1","unstructured":"Lewis D. D.1997.<img578 Text Categorization Test Collection."},{"key":"e_1_2_9_22_1","volume-title":"Automatic Retrieval and Clustering of Similar Words","author":"Lin D.","year":"1998"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/18.61115"},{"key":"e_1_2_9_24_1","unstructured":"Maas A. L. R. E.Daly P. T.Pham D.Huang A. Y.Ng andC.Potts.2011.Learning Word Vectors for Sentiment AnalysisProceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies."},{"issue":"2008","key":"e_1_2_9_25_1","first-page":"1","article-title":"On the Generalized Distance in Statistics","volume":"80","author":"Mahalanobis P. C.","year":"2018","journal-title":"Sankhy\u0101: The Indian Journal of Statistics, Series A"},{"key":"e_1_2_9_26_1","volume-title":"COLING","author":"Malandri L.","year":"2025"},{"key":"e_1_2_9_27_1","volume-title":"NeurIPS 26","author":"Mikolov T.","year":"2013"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.07.013"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.63317\/4h8o6w5g92ei"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672608.3707894"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-018-9590-9"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.998"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2024.101216"},{"key":"e_1_2_9_35_1","unstructured":"Tanimoto T. T.1958.Elementary Mathematical Theory of Classification and Prediction."},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.2934"},{"key":"e_1_2_9_37_1","first-page":"2579","article-title":"Visualizing Data Using T\u2010sne","volume":"9","author":"Van der Maaten L.","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_38_1","first-page":"8772","volume-title":"Proceedings of EMNLP","author":"Zhang X.","year":"2023"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1100"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2932334"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70354","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70354","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70354","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T09:32:19Z","timestamp":1784194339000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70354"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,14]]},"references-count":39,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1111\/exsy.70354"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70354","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,14]]},"assertion":[{"value":"2025-11-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70354"}}