{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:56:50Z","timestamp":1773482210560,"version":"3.50.1"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s41060-025-00955-0","type":"journal-article","created":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T07:00:44Z","timestamp":1764313244000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Statistical interpretation for word embeddings in natural language processing"],"prefix":"10.1007","volume":"21","author":[{"given":"Zitong","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Ashraf","family":"Yaseen","sequence":"additional","affiliation":[]},{"given":"Hulin","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"key":"955_CR1","unstructured":"Levy, O., Yoav, G.: Neural word embedding as implicit matrix factorization. Adv. Neural Inf. Process. Syst. 27 (2014)."},{"key":"955_CR2","doi-asserted-by":"crossref","unstructured":"Armand, J., Edouard, G., Piotr, B.T.M.: Bag of tricks for efficient text classification. European Association for Computational Linguistics 2017, 427 (2017).","DOI":"10.18653\/v1\/E17-2068"},{"key":"955_CR3","unstructured":"Mikolov, T. et al.: Distributed representations of words and phrases and their compositionality. Adv. Neural Inf. Process. Syst. 26 (2013)."},{"key":"955_CR4","doi-asserted-by":"crossref","unstructured":"Terra, E.L., Charles L.A.C. Frequency estimates for statistical word similarity measures. In Proceedings of the 2003 human language technology conference of the North American Chapter of the Association for Computational Linguistics. (2003).","DOI":"10.3115\/1073445.1073477"},{"key":"955_CR5","unstructured":"Mai, F., Lukas, G., Ansgar, S.: CBOW is not all you need: combining CBOW with the compositional matrix space model (2019)."},{"key":"955_CR6","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1162\/tacl_a_00134","volume":"3","author":"O Levy","year":"2015","unstructured":"Levy, O., Goldberg, Y., Dagan, I.: Improving distributional similarity with lessons learned from word embeddings. Trans. Assoc. Comput. Linguist. 3, 211\u2013225 (2015)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"955_CR7","unstructured":"\u0158eh\u016f\u0159ek, R., Petr, S.: Software framework for topic modelling with large corpora. In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. (2010)."},{"key":"955_CR8","unstructured":"Mikolov, T. et al.: Efficient estimation of word representations in vector space. (2013)."},{"key":"955_CR9","unstructured":"Lim, Y.J., Yee, W.T.: Variational Bayesian approach to movie rating prediction. Proceedings of KDD cup and workshop. 7 (2007)."},{"issue":"3","key":"955_CR10","doi-asserted-by":"publisher","first-page":"510","DOI":"10.3758\/BF03193020","volume":"39","author":"JA Bullinaria","year":"2007","unstructured":"Bullinaria, J.A., Levy, J.P.: Extracting semantic representations from word co-occurrence statistics: a computational study. Behav. Res. Methods 39(3), 510\u2013526 (2007)","journal-title":"Behav. Res. Methods"},{"key":"955_CR11","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/BF02288367","volume":"1","author":"C Eckart","year":"1936","unstructured":"Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1, 211\u2013218 (1936)","journal-title":"Psychometrika"},{"key":"955_CR12","unstructured":"Srebro, N., Jaakkola, T.: Weighted low-rank approximations. In T. Fawcett and N. Mishra, editors, ICML, pages 720\u2013727. AAAI Press, (2003)."},{"key":"955_CR13","unstructured":"Besbes, A.: Sentiment analysis on Twitter using Word2vec and Keras. (2017). https:\/\/www.ahmedbesbes.com\/blog\/sentiment-analysis-with-keras-and-word-2-vec"},{"key":"955_CR14","unstructured":"Rehurek, R., Sojka, P.: Gensim\u2013python framework for vector space modelling. NLP Centre, Faculty of Informatics, Masaryk University, Brno, Czech Republic. 3(2) (2011)"},{"key":"955_CR15","unstructured":"Honnibal, M., Montani, I.: spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. (2017)."},{"key":"955_CR16","doi-asserted-by":"crossref","unstructured":"Babaei, G., Oliver, G., Paolo, G., Alessandro, M.: SAFE-NLP: How accurate and robust is a text classification model?. Available at SSRN 5057253 (2024).","DOI":"10.2139\/ssrn.5537980"},{"issue":"3","key":"955_CR17","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1080\/02331888.2024.2361481","volume":"58","author":"P Giudici","year":"2024","unstructured":"Giudici, P.: Safe machine learning. Statistics 58(3), 473\u2013477 (2024). https:\/\/doi.org\/10.1080\/02331888.2024.2361481","journal-title":"Statistics"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00955-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s41060-025-00955-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-025-00955-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:35:27Z","timestamp":1773480927000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s41060-025-00955-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":17,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["955"],"URL":"https:\/\/doi.org\/10.1007\/s41060-025-00955-0","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"value":"2364-415X","type":"print"},{"value":"2364-4168","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,28]]},"assertion":[{"value":"12 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 November 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":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"17"}}