{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:55:48Z","timestamp":1774936548941,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T00:00:00Z","timestamp":1612310400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001501","name":"University Grants Commission","doi-asserted-by":"publisher","award":["F1-17.1\/2016\/RGNF-2015-17-SC-TAM-20541"],"award-info":[{"award-number":["F1-17.1\/2016\/RGNF-2015-17-SC-TAM-20541"]}],"id":[{"id":"10.13039\/501100001501","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Wireless Pers Commun"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1007\/s11277-021-08093-z","type":"journal-article","created":{"date-parts":[[2021,2,3]],"date-time":"2021-02-03T13:03:58Z","timestamp":1612357438000},"page":"1481-1505","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Firefly Optimization Algorithm Based Web Scraping for Web Citation Extraction"],"prefix":"10.1007","volume":"118","author":[{"given":"E.","family":"Suganya","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S.","family":"Vijayarani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,2,3]]},"reference":[{"key":"8093_CR1","first-page":"494","volume":"1","author":"FS Sari","year":"2010","unstructured":"Sari, F. S., & Kurniawan, A. (2010). Implementation of Indonesian electronic citation system based on web. Third International Conference on Knowledge Discovery and Data Mining\u2014IEEE Transaction, 1, 494\u2013497.","journal-title":"Third International Conference on Knowledge Discovery and Data Mining\u2014IEEE Transaction"},{"key":"8093_CR2","volume-title":"Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data","author":"B Liu","year":"2007","unstructured":"Liu, B. (2007). Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data. Berlin: Springer."},{"issue":"2","key":"8093_CR3","first-page":"1227","volume":"13","author":"J Mehra","year":"2018","unstructured":"Mehra, J., & Thakur, R. S. (2018). An Effective method for Web Log 3 preprocessing and page access frequency using web usage mining. International Journal of Applied Engineering Research, 13(2), 1227\u20131232.","journal-title":"International Journal of Applied Engineering Research"},{"key":"8093_CR4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-39314-3","volume-title":"Web information retrieval","author":"S Ceri","year":"2013","unstructured":"Ceri, S., Bozzon, A., Brambilla, M., Della Valle, E., et al. (2013). Web information retrieval. Berlin: Springer."},{"key":"8093_CR5","first-page":"98","volume":"6","author":"S Khalil","year":"2017","unstructured":"Khalil, S., & Fakir, M. (2017). R Crawler: An R package for parallel web crawling and scraping. Software X, 6, 98\u2013106.","journal-title":"Software X"},{"issue":"2","key":"8093_CR6","first-page":"201","volume":"4","author":"K Ammulu","year":"2017","unstructured":"Ammulu, K., & Venugopal, T. (2017). Mining web data using PSO algorithm. International Journal for Innovative Research in Science & Technology, 4(2), 201\u2013207.","journal-title":"International Journal for Innovative Research in Science & Technology"},{"key":"8093_CR7","unstructured":"Li, R. (2013). Web information extraction by using improved hybrid intelligent algorithm and HMM. In Information and computer technologies, computer modelling and new technologies (pp. 251\u2013259)."},{"issue":"4","key":"8093_CR8","doi-asserted-by":"publisher","first-page":"612","DOI":"10.1109\/TKDE.2010.140","volume":"23","author":"C Kim","year":"2011","unstructured":"Kim, C., & Shim, K. (2011). TEXT: Automatic template extraction from heterogeneous web pages. IEEE Transactions on Knowledge and Data Engineering, 23(4), 612\u2013626.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"1","key":"8093_CR9","first-page":"01","volume":"16","author":"TV Udapure","year":"2014","unstructured":"Udapure, T. V., Kale, R. D., & Dharmik, R. C. (2014). Study of web crawler and its different types. Journal of Computer Engineering, 16(1), 01\u201305.","journal-title":"Journal of Computer Engineering"},{"issue":"8","key":"8093_CR10","first-page":"176","volume":"3","author":"H Balaji","year":"2014","unstructured":"Balaji, H., & Govardhan, A. (2014). A survey on hidden Markov models for information extraction. International Journal of Application or Innovation in Engineering & Management, 3(8), 176\u2013179.","journal-title":"International Journal of Application or Innovation in Engineering & Management"},{"issue":"5","key":"8093_CR11","first-page":"1","volume":"2","author":"NS Saklani","year":"2016","unstructured":"Saklani, N. S., & Sharma, S. (2016). Extracting news from the web pages by using concept of clustering with neural genetic approach. International Journal of Advance Research, Ideas, and Innovations in Technology, 2(5), 1\u201317.","journal-title":"International Journal of Advance Research, Ideas, and Innovations in Technology"},{"issue":"5","key":"8093_CR12","first-page":"4444","volume":"6","author":"A Bhagat","year":"2015","unstructured":"Bhagat, A., & Raut, V. (2015). Ternary based web crawler for optimized search results. International Journal of Computer Science and Information Technologies, 6(5), 4444\u20134449.","journal-title":"International Journal of Computer Science and Information Technologies"},{"key":"8093_CR13","doi-asserted-by":"crossref","unstructured":"Ge, A., Mao, W., & Zeng, D. (2010). Story extraction from the Web: A case study in security informatics. In IEEE international conference on service operations and logistics, and informatics (pp. 306\u2013310).","DOI":"10.1109\/SOLI.2010.5551561"},{"key":"8093_CR14","unstructured":"Huang J., Liu, Z., Wang, B., et al. (2018). Web data extraction from scientific publishers\u2019 website using hidden Markov model. In Knowledge science, engineering and management (pp. 469\u2013476). Berlin: Springer."},{"key":"8093_CR15","unstructured":"Powley, B., & Dale, R. (2007). High accuracy citation extraction and named entity recognition for a heterogeneous corpus of academic papers. In International conference on natural language processing and knowledge engineering (pp. 119\u2013124). Beijing: IEEE Xplore."},{"issue":"6","key":"8093_CR16","first-page":"132","volume":"7","author":"S Liangtu","year":"2007","unstructured":"Liangtu, S., & Xiaoming, Z. (2007). Web text feature extraction David with particle swarm optimization. International Journal of Computer Science and Network Security, 7(6), 132\u2013136.","journal-title":"International Journal of Computer Science and Network Security"},{"key":"8093_CR17","unstructured":"Seymore, K., McCallum, A., & Rosenfeld, R. (1999). Learning hidden Markov model structure for information extraction. AAAI-99 Workshop on a machine (pp. 37\u201342)."},{"issue":"9","key":"8093_CR18","first-page":"2045","volume":"2","author":"VPA Linnet Hailey","year":"2013","unstructured":"Linnet Hailey, V. P. A., & Sudha, N. (2013). An optimization approach of firefly algorithm to record deduplication. International Journal of Engineering Research & Technology, 2(9), 2045\u20132049.","journal-title":"International Journal of Engineering Research & Technology"},{"key":"8093_CR19","doi-asserted-by":"publisher","first-page":"200","DOI":"10.3390\/info10060200","volume":"10","author":"A Alexandrescu","year":"2019","unstructured":"Alexandrescu, A. (2019). Optimization and security in information retrieval, extraction, processing, and presentation on a cloud platform. Information, 10, 200.","journal-title":"Information"},{"issue":"1","key":"8093_CR20","first-page":"103","volume":"2","author":"A Pal","year":"2009","unstructured":"Pal, A., Tomar, D. S., & Shrivastava, S. C. (2009). Effective focused crawling based on content and link structure analysis. International Journal of Computer Science and Information Security, 2(1), 103\u2013107.","journal-title":"International Journal of Computer Science and Information Security"},{"issue":"5","key":"8093_CR21","first-page":"545","volume":"4","author":"A Pranav","year":"2015","unstructured":"Pranav, A., & Chauhan, S. (2015). Efficient focused web crawling approach for search engine. International Journal of Computer Science and Mobile Computing, 4(5), 545\u2013551.","journal-title":"International Journal of Computer Science and Mobile Computing"},{"issue":"2","key":"8093_CR22","doi-asserted-by":"publisher","first-page":"31","DOI":"10.5120\/10440-5125","volume":"63","author":"MdA Kausar","year":"2013","unstructured":"Kausar, Md. A., Dhaka, V. S., & Singh, S. V. (2013). Web crawler: A review. International Journal of Computer Applications, 63(2), 31\u201336.","journal-title":"International Journal of Computer Applications"},{"key":"8093_CR23","unstructured":"David R. H., & Miller, T. L. (1999). Bbn at trec7: Using hidden markov models for information retrieval. TREC - 7."},{"key":"8093_CR24","doi-asserted-by":"crossref","unstructured":"Shekhar, S., Agrawal, R., & Arya, K. V. (2010). An architectural framework of a crawler for retrieving highly relevant web documents by filtering replicated web collections. In International conference on advances in computer engineering (pp. 29\u201333). IEEE Conference Publications.","DOI":"10.1109\/ACE.2010.64"},{"key":"8093_CR25","unstructured":"Slamet, C., Andrian, R., Maylawati, D.S., et al. (2018). Web scraping and na\u00efve Bayes classification for job search engine. In IOP conference series: Materials science and engineering. Indonesia: IOP Science.1\u20137."},{"key":"8093_CR26","first-page":"1","volume":"68","author":"S Munzert","year":"2015","unstructured":"Munzert, S., Rubba, C., Meissner, P., & Nyhuis, D. (2015). Automated data collection with R: A practical guide to web scraping and text mining. Journal of Statistical Software, 68, 1\u20133.","journal-title":"Journal of Statistical Software"},{"key":"8093_CR27","doi-asserted-by":"crossref","unstructured":"Malik, S. K., & Rizvi, S. (2011). Information extraction using web usage mining, web scrapping and semantic annotation. In International conference on computational intelligence and communication networks (pp. 465\u2013469).","DOI":"10.1109\/CICN.2011.97"},{"key":"8093_CR28","unstructured":"Andrew Cantino, K.M. (2013). SelectorGadget. Retrieved from Chrome Web store: https:\/\/chrome.google.com\/webstore\/detail\/selectorgadget\/mhjhnkcfbdhnjickkkdbjoemdmbfginb?hl=en"},{"key":"8093_CR29","doi-asserted-by":"crossref","unstructured":"Kennedy, J., & Eberhart, R, (1995). Particle swarm optimization. In International conference on neural networks-Australia (pp. 1942\u20131948). IEEE.","DOI":"10.1109\/ICNN.1995.488968"},{"issue":"8","key":"8093_CR30","doi-asserted-by":"publisher","first-page":"6211","DOI":"10.1007\/s12517-014-1584-7","volume":"8","author":"ZS Younus","year":"2014","unstructured":"Younus, Z. S., Mohamad, D., Saba, T., Alkawaz, M. H., et al. (2014). Content-based image retrieval using PSO and k-means clustering algorithm. Arabian Journal of Geosciences, 8(8), 6211\u20136224.","journal-title":"Arabian Journal of Geosciences"},{"key":"8093_CR31","doi-asserted-by":"crossref","unstructured":"Lai, J., Liu, Q., & Liu, Y. (2010). Web information extraction based on hidden Markov model. In International conference on computer supported cooperative work in design (pp. 234\u2013238). IEEE Explore.","DOI":"10.1109\/CSCWD.2010.5471969"},{"issue":"3","key":"8093_CR32","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.jksuci.2018.06.004","volume":"32","author":"S Larabi Marie-Sainte","year":"2018","unstructured":"Larabi Marie-Sainte, S., & Alalyani, A. (2018). Firefly algorithm based feature selection for Arabic text classification. Journal of King Saud University \u2013 Computer and Information Sciences, 32(3), 320\u2013328.","journal-title":"Journal of King Saud University \u2013 Computer and Information Sciences"}],"container-title":["Wireless Personal Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-021-08093-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11277-021-08093-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11277-021-08093-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,21]],"date-time":"2021-04-21T19:35:03Z","timestamp":1619033703000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11277-021-08093-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,3]]},"references-count":32,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2021,5]]}},"alternative-id":["8093"],"URL":"https:\/\/doi.org\/10.1007\/s11277-021-08093-z","relation":{},"ISSN":["0929-6212","1572-834X"],"issn-type":[{"value":"0929-6212","type":"print"},{"value":"1572-834X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,3]]},"assertion":[{"value":"10 January 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2021","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}