WEKO3
アイテム
{"_buckets": {"deposit": "47b995d9-8fcd-4524-9bd4-c4aac0b23428"}, "_deposit": {"id": "8599", "owners": [], "pid": {"revision_id": 0, "type": "depid", "value": "8599"}, "status": "published"}, "_oai": {"id": "oai:nagoya.repo.nii.ac.jp:00008599", "sets": ["1038"]}, "author_link": ["24206", "24207", "24208"], "item_18_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2004-01", "bibliographicIssueDateType": "Issued"}, "bibliographicPageEnd": "147", "bibliographicPageStart": "141", "bibliographic_titles": [{"bibliographic_title": "Second Symposium on \"Intelligent Media Integration for Social Information Infrastructure\" January 8-9, 2004", "bibliographic_titleLang": "en"}]}]}, "item_18_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "We present discussion mining as a preliminary study of knowledge discovery from discussion records of offline face-to-face meetings. We produce minutes for such meetings semi-automatically. Our structured minutes include text manually inputted by a secretariat, participants\u0027 video images captured by person tracking cameras, screen images recorded by a fixed camera, speech audio captured by multiple microphones, metadata reflecting discussion structures (participant ID, utterance type, speech start/end time, etc.) and evaluation of the discussion by all participants. Multimedia data are automatically divided into chunks of utterances and linked with nodes in the minute data represented by XML (Extensible Markup Language). During the meetings, we hold up an electronic tag that transmits infrared signals to the infrared sensor array mounted on the ceiling when we start and stop speaking. This device is very simple, easy to use, effective for adding metadata to the digital minute, and helpful for the secretariat to segment and insert keywords related to each utterance. After creating multimodal minutes, not only do we search for the content of the minutes by date and attendants, we study a method of searching for a similar discussion to the ongoing discussion from past ones, and a method of producing an answer to a certain question based on the content of the minutes. In terms of mailing lists and bulletin boards, various studies have been done on digital (semi-structured) discussions. We analyze actual (physical) meetings from diversified perspectives using audio and visual information with metadata. We call this not just data mining but a kind of multimedia mining or human activity mining.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_18_identifier_60": {"attribute_name": "URI", "attribute_value_mlt": [{"subitem_identifier_type": "HDL", "subitem_identifier_uri": "http://hdl.handle.net/2237/10350"}]}, "item_18_publisher_32": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "INTELLIGENT MEDIA INTEGRATION NAGOYA UNIVERSITY / COE", "subitem_publisher_language": "en"}]}, "item_18_select_15": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_select_item": "publisher"}]}, "item_18_text_14": {"attribute_name": "フォーマット", "attribute_value_mlt": [{"subitem_text_value": "application/pdf"}]}, "item_access_right": {"attribute_name": "アクセス権", "attribute_value_mlt": [{"subitem_access_right": "open access", "subitem_access_right_uri": "http://purl.org/coar/access_right/c_abf2"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Nagao, Katashi", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24206", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Kaji, Katsuhiko", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24207", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Shimizu, Toshiyuki", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "24208", "nameIdentifierScheme": "WEKO"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2018-02-19"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "Katashi_Nagao_p141-147.pdf", "filesize": [{"value": "27.5 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 27500000.0, "url": {"label": "Katashi_Nagao_p141-147.pdf", "objectType": "fulltext", "url": "https://nagoya.repo.nii.ac.jp/record/8599/files/Katashi_Nagao_p141-147.pdf"}, "version_id": "1e6f2889-2906-46e5-88af-b0e3d2de983f"}]}, "item_language": {"attribute_name": "言語", "attribute_value_mlt": [{"subitem_language": "eng"}]}, "item_resource_type": {"attribute_name": "資源タイプ", "attribute_value_mlt": [{"resourcetype": "conference paper", "resourceuri": "http://purl.org/coar/resource_type/c_5794"}]}, "item_title": "Discussion Mining : Knowledge Discovery from Data on the Real World Activities", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Discussion Mining : Knowledge Discovery from Data on the Real World Activities", "subitem_title_language": "en"}]}, "item_type_id": "18", "owner": "1", "path": ["1038"], "permalink_uri": "http://hdl.handle.net/2237/10350", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2008-08-12"}, "publish_date": "2008-08-12", "publish_status": "0", "recid": "8599", "relation": {}, "relation_version_is_last": true, "title": ["Discussion Mining : Knowledge Discovery from Data on the Real World Activities"], "weko_shared_id": -1}
Discussion Mining : Knowledge Discovery from Data on the Real World Activities
http://hdl.handle.net/2237/10350
http://hdl.handle.net/2237/10350d877aeef-6c37-46ac-b667-4b4e2e6a2dec
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2008-08-12 | |||||
タイトル | ||||||
タイトル | Discussion Mining : Knowledge Discovery from Data on the Real World Activities | |||||
言語 | en | |||||
著者 |
Nagao, Katashi
× Nagao, Katashi× Kaji, Katsuhiko× Shimizu, Toshiyuki |
|||||
アクセス権 | ||||||
アクセス権 | open access | |||||
アクセス権URI | http://purl.org/coar/access_right/c_abf2 | |||||
抄録 | ||||||
内容記述 | We present discussion mining as a preliminary study of knowledge discovery from discussion records of offline face-to-face meetings. We produce minutes for such meetings semi-automatically. Our structured minutes include text manually inputted by a secretariat, participants' video images captured by person tracking cameras, screen images recorded by a fixed camera, speech audio captured by multiple microphones, metadata reflecting discussion structures (participant ID, utterance type, speech start/end time, etc.) and evaluation of the discussion by all participants. Multimedia data are automatically divided into chunks of utterances and linked with nodes in the minute data represented by XML (Extensible Markup Language). During the meetings, we hold up an electronic tag that transmits infrared signals to the infrared sensor array mounted on the ceiling when we start and stop speaking. This device is very simple, easy to use, effective for adding metadata to the digital minute, and helpful for the secretariat to segment and insert keywords related to each utterance. After creating multimodal minutes, not only do we search for the content of the minutes by date and attendants, we study a method of searching for a similar discussion to the ongoing discussion from past ones, and a method of producing an answer to a certain question based on the content of the minutes. In terms of mailing lists and bulletin boards, various studies have been done on digital (semi-structured) discussions. We analyze actual (physical) meetings from diversified perspectives using audio and visual information with metadata. We call this not just data mining but a kind of multimedia mining or human activity mining. | |||||
言語 | en | |||||
内容記述タイプ | Abstract | |||||
出版者 | ||||||
言語 | en | |||||
出版者 | INTELLIGENT MEDIA INTEGRATION NAGOYA UNIVERSITY / COE | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源 | http://purl.org/coar/resource_type/c_5794 | |||||
タイプ | conference paper | |||||
書誌情報 |
en : Second Symposium on "Intelligent Media Integration for Social Information Infrastructure" January 8-9, 2004 p. 141-147, 発行日 2004-01 |
|||||
フォーマット | ||||||
application/pdf | ||||||
著者版フラグ | ||||||
値 | publisher | |||||
URI | ||||||
識別子 | http://hdl.handle.net/2237/10350 | |||||
識別子タイプ | HDL |