{"created":"2020-09-01T14:02:35.576467+00:00","id":4069,"links":{},"metadata":{"_buckets":{"deposit":"9b31d65a-80b1-474f-9240-e07338ce2c15"},"_deposit":{"id":"4069","owners":[],"pid":{"revision_id":0,"type":"recid","value":"4069"},"status":"published"},"_oai":{"id":"oai:meral.edu.mm:recid/4069","sets":["1582963302567:1597824273898"]},"communities":["ucsy"],"item_1583103067471":{"attribute_name":"Title","attribute_value_mlt":[{"subitem_1551255647225":"Constructing and Implementing a New DOM-based Content Extraction Algorithm","subitem_1551255648112":"en"}]},"item_1583103085720":{"attribute_name":"Description","attribute_value_mlt":[{"interim":"The Internet explosion has made enormous Information sources published as HTML pages on the internet. However, there are many redundant pages as being known web pages noise on the Web. For instance, almost all dot com present a large amount of noise such as service channels, navigation panels, copyright and privacy announcement, advertisements, etc. Such noises can seriously harm Web Mining, Information retrieval and Information extraction. In this paper, a new algorithm is proposed and how it can be used to deal with Web page noises is also presented. The proposed algorithm matches DOM trees to classify which nodes are noises and which are contents and, after classification, cluster into their group respectively. Finally, only the content group is extracted from the page. The resulting contents are useful for both users and systems. The proposed technique leads to boost up the performance of Web Content Extraction."}]},"item_1583103108160":{"attribute_name":"Keywords","attribute_value":[]},"item_1583103120197":{"attribute_name":"Files","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2019-08-05"}],"displaytype":"preview","filename":"55172.pdf","filesize":[{"value":"800 Kb"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"url":"https://meral.edu.mm/record/4069/files/55172.pdf"},"version_id":"72328387-d9f8-4686-8ba4-b3756c746ead"}]},"item_1583103131163":{"attribute_name":"Journal articles","attribute_value_mlt":[{"subitem_issue":"","subitem_journal_title":"Fourth Local Conference on Parallel and Soft Computing","subitem_pages":"","subitem_volume":""}]},"item_1583103147082":{"attribute_name":"Conference papers","attribute_value_mlt":[{"subitem_acronym":"","subitem_c_date":"","subitem_conference_title":"","subitem_part":"","subitem_place":"","subitem_session":"","subitem_website":""}]},"item_1583103211336":{"attribute_name":"Books/reports/chapters","attribute_value_mlt":[{"subitem_book_title":"","subitem_isbn":"","subitem_pages":"","subitem_place":"","subitem_publisher":""}]},"item_1583103233624":{"attribute_name":"Thesis/dissertations","attribute_value_mlt":[{"subitem_awarding_university":"","subitem_supervisor(s)":[{"subitem_supervisor":""}]}]},"item_1583105942107":{"attribute_name":"Authors","attribute_value_mlt":[{"subitem_authors":[{"subitem_authors_fullname":"Moong, Nang Kham Line"}]}]},"item_1583108359239":{"attribute_name":"Upload type","attribute_value_mlt":[{"interim":"Publication"}]},"item_1583108428133":{"attribute_name":"Publication type","attribute_value_mlt":[{"interim":"Article"}]},"item_1583159729339":{"attribute_name":"Publication date","attribute_value":"2009-12-30"},"item_1583159847033":{"attribute_name":"Identifier","attribute_value":"http://onlineresource.ucsy.edu.mm/handle/123456789/1775"},"item_title":"Constructing and Implementing a New DOM-based Content Extraction Algorithm","item_type_id":"21","owner":"1","path":["1597824273898"],"publish_date":"2019-08-05","publish_status":"0","recid":"4069","relation_version_is_last":true,"title":["Constructing and Implementing a New DOM-based Content Extraction Algorithm"],"weko_creator_id":"1","weko_shared_id":-1},"updated":"2021-12-13T01:24:46.605934+00:00"}