WEKO3
アイテム
{"_buckets": {"deposit": "aa76ae06-75f4-4c81-a522-183dae6bb135"}, "_deposit": {"created_by": 4, "id": "10139", "owners": [4], "pid": {"revision_id": 0, "type": "depid", "value": "10139"}, "status": "published"}, "_oai": {"id": "oai:naist.repo.nii.ac.jp:00010139", "sets": ["57"]}, "author_link": ["29890", "21"], "item_1698715929687": {"attribute_name": "会議情報", "attribute_value_mlt": [{"subitem_conference_country": "JPN", "subitem_conference_date": {"subitem_conference_period": "March 11, 2018"}, "subitem_conference_names": [{"subitem_conference_name": "IUI 2018 Workshop on User Interfaces for Spatial and Temporal Data Analysis (UISTDA 2018)"}], "subitem_conference_places": [{"subitem_conference_place": "Tokyo", "subitem_conference_place_language": "en"}]}]}, "item_9_biblio_info_7": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2018", "bibliographicIssueDateType": "Issued"}}]}, "item_9_description_5": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "In recent years, the protection of personal information has drawn much attention, requiring an advanced technology on de-identification to remove personal information from data. Among various personal information such as personal names, phone numbers, and so forth, this study focuses on location information. The conventional approaches to protect location information are to remove address expressions. However, there are complicated cases in which location information can be guessed with unexpected combinations of non-address words. For example, we can guess ‘the most traditional city in Japan’ is Kyoto. To our knowledge, such location-inferable expressions have not been dealt with. This study handles this phenomenon by using a location classifier. In addition, we assume two levels of location inferance; (1) inferable by machine and (2) inferable by human. To build the first-level inferance, we employed a collection of tweets with geo-tags. To build the second-level inferance, we created a new corpus with a flag for whether tweets are location-inferable by human or not. By using the two types of corpora, we classified texts into several categories such as a machine-inferable but human-non-inferable tweet, and so on. We also could obtain de-identified tweets by iterations of removing the highest weighted words for classifiers. We believe our novel concepts of de-identification are essential for various privacy protection.", "subitem_description_language": "en", "subitem_description_type": "Abstract"}]}, "item_9_publisher_8": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "UISTDA \u002718", "subitem_publisher_language": "en"}]}, "item_9_rights_14": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "(c) authors", "subitem_rights_language": "en"}]}, "item_9_rights_9": {"attribute_name": "出版者URL", "attribute_value_mlt": [{"subitem_rights": "http://ceur-ws.org/Vol-2068/#uistda"}]}, "item_9_version_type_16": {"attribute_name": "著者版フラグ", "attribute_value_mlt": [{"subitem_version_resource": "http://purl.org/coar/version/c_970fb48d4fbd8a85", "subitem_version_type": "VoR"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Taguchi, Katsuya", "creatorNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "29890", "nameIdentifierScheme": "WEKO"}]}, {"creatorAffiliations": [{"affiliationNameIdentifiers": [{"affiliationNameIdentifierScheme": "kakenhi"}], "affiliationNames": [{"affiliationNameLang": "ja"}]}], "creatorNames": [{"creatorName": "荒牧, 英治", "creatorNameLang": "ja"}, {"creatorName": "アラマキ, エイジ", "creatorNameLang": "ja-Kana"}, {"creatorName": "Aramaki, Eiji", "creatorNameLang": "en"}], "familyNames": [{"familyName": "荒牧", "familyNameLang": "ja"}, {"familyName": "アラマキ", "familyNameLang": "ja-Kana"}, {"familyName": "Aramaki", "familyNameLang": "en"}], "givenNames": [{"givenName": "英治", "givenNameLang": "ja"}, {"givenName": "エイジ", "givenNameLang": "ja-Kana"}, {"givenName": "Eiji", "givenNameLang": "en"}], "nameIdentifiers": [{"nameIdentifier": "21", "nameIdentifierScheme": "WEKO"}, {"nameIdentifier": "70401073", "nameIdentifierScheme": "e-Rad", "nameIdentifierURI": "https://kaken.nii.ac.jp/ja/search/?qm=70401073"}]}]}, "item_files": {"attribute_name": "ファイル情報", "attribute_type": "file", "attribute_value_mlt": [{"accessrole": "open_date", "date": [{"dateType": "Available", "dateValue": "2023-03-06"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "18ConstructingHome.pdf", "filesize": [{"value": "1.9 MB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_note", "mimetype": "application/pdf", "size": 1900000.0, "url": {"label": "fulltext", "objectType": "fulltext", "url": "https://naist.repo.nii.ac.jp/record/10139/files/18ConstructingHome.pdf"}, "version_id": "8af29dd0-7959-4892-8b6b-fea38ba7ff85"}]}, "item_keyword": {"attribute_name": "キーワード", "attribute_value_mlt": [{"subitem_subject": "De-identification", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Location inference", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "SNS", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Twitter", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}, {"subitem_subject": "Natural language processing", "subitem_subject_language": "en", "subitem_subject_scheme": "Other"}]}, "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": "Novel Location De-identification for Machine and Human", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Novel Location De-identification for Machine and Human", "subitem_title_language": "en"}]}, "item_type_id": "9", "owner": "4", "path": ["57"], "permalink_uri": "http://hdl.handle.net/10061/13106", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2019-01-30"}, "publish_date": "2019-01-30", "publish_status": "0", "recid": "10139", "relation": {}, "relation_version_is_last": true, "title": ["Novel Location De-identification for Machine and Human"], "weko_shared_id": -1}
Novel Location De-identification for Machine and Human
http://hdl.handle.net/10061/13106
http://hdl.handle.net/10061/131068452f2d1-d6dc-4baf-982a-0ae51267c0b5
名前 / ファイル | ライセンス | アクション |
---|---|---|
fulltext (1.9 MB)
|
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2019-01-30 | |||||
タイトル | ||||||
タイトル | Novel Location De-identification for Machine and Human | |||||
言語 | ||||||
言語 | eng | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | De-identification | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Location inference | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | SNS | |||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | ||||||
キーワード | ||||||
主題Scheme | Other | |||||
主題 | Natural language processing | |||||
資源タイプ | ||||||
資源タイプ | conference paper | |||||
著者 |
Taguchi, Katsuya
× Taguchi, Katsuya× 荒牧, 英治 |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | In recent years, the protection of personal information has drawn much attention, requiring an advanced technology on de-identification to remove personal information from data. Among various personal information such as personal names, phone numbers, and so forth, this study focuses on location information. The conventional approaches to protect location information are to remove address expressions. However, there are complicated cases in which location information can be guessed with unexpected combinations of non-address words. For example, we can guess ‘the most traditional city in Japan’ is Kyoto. To our knowledge, such location-inferable expressions have not been dealt with. This study handles this phenomenon by using a location classifier. In addition, we assume two levels of location inferance; (1) inferable by machine and (2) inferable by human. To build the first-level inferance, we employed a collection of tweets with geo-tags. To build the second-level inferance, we created a new corpus with a flag for whether tweets are location-inferable by human or not. By using the two types of corpora, we classified texts into several categories such as a machine-inferable but human-non-inferable tweet, and so on. We also could obtain de-identified tweets by iterations of removing the highest weighted words for classifiers. We believe our novel concepts of de-identification are essential for various privacy protection. | |||||
書誌情報 |
発行日 2018 |
|||||
会議情報 | ||||||
会議名 | IUI 2018 Workshop on User Interfaces for Spatial and Temporal Data Analysis (UISTDA 2018) | |||||
開催期間 | March 11, 2018 | |||||
開催地 | Tokyo | |||||
開催国 | JPN | |||||
出版者 | ||||||
出版者 | UISTDA '18 | |||||
出版者URL | ||||||
権利情報 | http://ceur-ws.org/Vol-2068/#uistda | |||||
権利 | ||||||
権利情報 | (c) authors | |||||
著者版フラグ | ||||||
出版タイプ | VoR |