{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T18:33:38Z","timestamp":1783362818284,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":29,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T00:00:00Z","timestamp":1716249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,21]]},"DOI":"10.1145\/3614419.3644018","type":"proceedings-article","created":{"date-parts":[[2024,4,17]],"date-time":"2024-04-17T08:41:58Z","timestamp":1713343318000},"page":"59-69","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Improved methodology for longitudinal Web analytics using Common Crawl"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5490-1347","authenticated-orcid":false,"given":"Henry S","family":"Thompson","sequence":"first","affiliation":[{"name":"School of Informatics, University of Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,21]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"d.]. Amazon Web Services (AWS) Open Data Sponsorship Program. Web document. https:\/\/aws.amazon.com\/opendata\/open-data-sponsorship-program\/ Retrieved","year":"2023","unstructured":"Amazon. [n. d.]. Amazon Web Services (AWS) Open Data Sponsorship Program. Web document. https:\/\/aws.amazon.com\/opendata\/open-data-sponsorship-program\/ Retrieved: 22 November 2023."},{"key":"e_1_3_2_2_2_1","volume-title":"d.]. Content analysis toolkit. Web document. https:\/\/tika.apache.org\/ Retrieved","author":"Foundation Apache Software","year":"2023","unstructured":"Apache Software Foundation. [n. d.]. Content analysis toolkit. Web document. https:\/\/tika.apache.org\/ Retrieved 7 December 2023."},{"key":"e_1_3_2_2_3_1","unstructured":"Internet Archive. [n. d.]. Sort-friendly URI Reordering Transform. Web document. http:\/\/crawler.archive.org\/articles\/user_manual\/glossary.html#surt Retrieved: 29 November 2022."},{"key":"e_1_3_2_2_4_1","volume-title":"Training Data for the Price of a Sandwich. Web document. https:\/\/foundation.mozilla.org\/en\/research\/library\/generative-ai-training-data\/common-crawl\/ Retrieved","author":"Baack Stefan","year":"2024","unstructured":"Stefan Baack and Mozilla Insights. 2024. Training Data for the Price of a Sandwich. Web document. https:\/\/foundation.mozilla.org\/en\/research\/library\/generative-ai-training-data\/common-crawl\/ Retrieved: 25 February 2024."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380092"},{"key":"e_1_3_2_2_6_1","unstructured":"Jingrui Chen. 2021. A Survey on HTTP cookies: Do large Internet companies collect more information from users?MSc dissertation. University of Edinburgh."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/NEXTCOMP.2019.8883665"},{"key":"e_1_3_2_2_8_1","volume-title":"Common Crawl - Get Started. Web document. https:\/\/commoncrawl.org\/get-started Retrieved","author":"Crawl Common","year":"2023","unstructured":"Common Crawl. 2022. Common Crawl - Get Started. Web document. https:\/\/commoncrawl.org\/get-started Retrieved: 22 November 2023."},{"key":"e_1_3_2_2_9_1","volume-title":"Common Crawl - Open Repository of Web Crawl Data. Web document. https:\/\/commoncrawl.org Retrieved","author":"Crawl Common","year":"2023","unstructured":"Common Crawl. 2023. Common Crawl - Open Repository of Web Crawl Data. Web document. https:\/\/commoncrawl.org Retrieved: 22 November 2023."},{"key":"e_1_3_2_2_10_1","volume-title":"Common Crawl - Terms of Use. Web document. https:\/\/commoncrawl.org\/terms-of-use Retrieved","author":"Crawl Common","year":"2024","unstructured":"Common Crawl. 2024. Common Crawl - Terms of Use. Web document. https:\/\/commoncrawl.org\/terms-of-use Retrieved: 24 February 2024."},{"key":"e_1_3_2_2_11_1","first-page":"2023","year":"2011","unstructured":"Nick Cox. 2011,2023. How to calculate a confidence interval for Spearman\u2019s rank correlation. Web document. https:\/\/stats.stackexchange.com\/a\/18904 Retrieved: 6 December 2023.","journal-title":"Nick Cox"},{"key":"e_1_3_2_2_12_1","volume-title":"GZIP file format specification version 4.3. Internet RFC. IETF. https:\/\/www.ietf.org\/rfc\/rfc1952.html Retrieved","author":"Deutsch Peter","year":"2023","unstructured":"Peter Deutsch. 1996. GZIP file format specification version 4.3. Internet RFC. IETF. https:\/\/www.ietf.org\/rfc\/rfc1952.html Retrieved: 22 November 2023."},{"key":"e_1_3_2_2_13_1","unstructured":"Lukasz Domanski. 2020. Analysing Common Crawl - Efficient and Cost-Effective Processing of Large-Scale Data. MSc dissertation. University of Edinburgh."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2017.8258075"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/BDC.2015.30"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.17487\/RFC7232"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561437"},{"key":"e_1_3_2_2_18_1","volume-title":"The Open Group Base Specifications Issue 7","author":"IEEE.","year":"2018","unstructured":"IEEE. 2017. The Open Group Base Specifications Issue 7, 2018 edition IEEE Std 1003.1-2017: POSIX.1a. Web document. https:\/\/pubs.opengroup.org\/onlinepubs\/9699919799\/basedefs\/V1_chap04.html#tag_04_16 Retrieved: 25 November 2023."},{"key":"e_1_3_2_2_19_1","volume-title":"Web document. https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/Retrieved","author":"International Internet Preservation Consortium","year":"2022","unstructured":"[19] International Internet Preservation Consortium. 2017. Web document. https:\/\/iipc.github.io\/warc-specifications\/specifications\/warc-format\/warc-1.1\/Retrieved: 29 November 2022."},{"key":"e_1_3_2_2_20_1","volume-title":"Web document. https:\/\/github.com\/ikreymer\/pywb\/wiki\/CDX-Index-Format#zipnum-sharded-cdxRetrieved","author":"Kreymer Ilya","year":"2023","unstructured":"[20] Ilya Kreymer. 2015. Web document. https:\/\/github.com\/ikreymer\/pywb\/wiki\/CDX-Index-Format#zipnum-sharded-cdxRetrieved: 22 November 2023."},{"key":"e_1_3_2_2_21_1","volume-title":"Announcing the Common Crawl Index. Web document. https:\/\/commoncrawl.org\/blog\/announcing-the-common-crawl-index Retrieved","author":"Kreymer Ilya","year":"2023","unstructured":"Ilya Kreymer. 2015. Announcing the Common Crawl Index. Web document. https:\/\/commoncrawl.org\/blog\/announcing-the-common-crawl-index Retrieved: 22 November 2023."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.24"},{"key":"e_1_3_2_2_23_1","volume-title":"Extensible Markup Language (XML) 1.0","author":"Maler Eve","year":"2022","unstructured":"Eve Maler, Jean Paoli, 2008. Extensible Markup Language (XML) 1.0 (Fifth Edition). Fifth Edition of a W3C Recommendation. W3C. http:\/\/www.w3.org\/TR\/xml\/ Retrieved: 29 November 2022."},{"key":"e_1_3_2_2_24_1","volume-title":"Web document. https:\/\/commoncrawl.org\/the-data\/get-started\/ Retrieved","author":"Nagel Sebastian","year":"2022","unstructured":"Sebastian Nagel. 2022. Common Crawl (Getting Started). Web document. https:\/\/commoncrawl.org\/the-data\/get-started\/ Retrieved: 29 November 2022."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC","author":"Panchenko Alexander","year":"2018","unstructured":"Alexander Panchenko 2018. Building a Web-Scale Dependency-Parsed Corpus from CommonCrawl. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Nicoletta Calzolari et\u00a0al. (Eds.). European Language Resources Association (ELRA), Miyazaki, Japan."},{"key":"e_1_3_2_2_26_1","volume-title":"d.]. statistical models, hypothesis tests, and data exploration. Web document. https:\/\/www.statsmodels.org\/stable\/index.html Retrieved","author":"Project Statsmodels","year":"2022","unstructured":"Statsmodels Project. [n. d.]. statistical models, hypothesis tests, and data exploration. Web document. https:\/\/www.statsmodels.org\/stable\/index.html Retrieved: 28 November 2022."},{"key":"e_1_3_2_2_27_1","volume-title":"Compact Language Detector 2. Web document. https:\/\/github.com\/CLD2Owners\/cld2 Retrieved","author":"Sites Dick","year":"2023","unstructured":"Dick Sites. 2013. Compact Language Detector 2. Web document. https:\/\/github.com\/CLD2Owners\/cld2 Retrieved 7 December 2023."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184558.3191636"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0686-2"}],"event":{"name":"Websci '24: 16th ACM Web Science Conference","location":"Stuttgart Germany","acronym":"Websci '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["ACM Web Science Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3614419.3644018","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3614419.3644018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T16:55:07Z","timestamp":1755881707000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3614419.3644018"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,21]]},"references-count":29,"alternative-id":["10.1145\/3614419.3644018","10.1145\/3614419"],"URL":"https:\/\/doi.org\/10.1145\/3614419.3644018","relation":{},"subject":[],"published":{"date-parts":[[2024,5,21]]},"assertion":[{"value":"2024-05-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}