{"created":"2024-11-22T06:52:35.347606+00:00","id":2008322,"links":{},"metadata":{"_buckets":{"deposit":"ef3ad849-31f8-4016-a753-4b8f3f8e3b19"},"_deposit":{"created_by":7,"id":"2008322","owners":[7],"pid":{"revision_id":0,"type":"depid","value":"2008322"},"status":"published"},"_oai":{"id":"oai:tokushima-u.repo.nii.ac.jp:02008322","sets":["1713853213384:1713853295607"]},"author_link":["401"],"item_10001_alternative_title_1":{"attribute_name":"タイトル別表記","attribute_value_mlt":[{"subitem_alternative_title":"MULTIPLE EMOTION DETECTION VIA EMOTION-SPECIFIED FEATURE EXTRACTION AND EMOTION CORRELATION LEARNING","subitem_alternative_title_language":"en"}]},"item_10001_biblio_info_7":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2020-10-27","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicPageEnd":"486","bibliographicPageStart":"475","bibliographicVolumeNumber":"14","bibliographic_titles":[{"bibliographic_title":"IEEE Transactions on Affective Computing","bibliographic_titleLang":"en"}]}]},"item_10001_description_5":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"Textual emotion detection is an attractive task while previous studies mainly focused on polarity or single-emotion classification. However, human expressions are complex, and multiple emotions often occur simultaneously with non-negligible emotion correlations. In this paper, a Multi-label Emotion Detection Architecture (MEDA) is proposed to detect all associated emotions expressed in a given piece of text. MEDA is mainly composed of two modules: Multi-Channel Emotion-Specified Feature Extractor (MC-ESFE) and Emotion Correlation Learner (ECorL). MEDA captures underlying emotion-specified features through MC-ESFE module in advance. MC-ESFE is composed of multiple channel-wise ESFE networks. Each channel is devoted to the feature extraction of a specified emotion from sentence-level to context-level through a hierarchical structure. Based on obtained features, emotion correlation learning is implemented through an emotion sequence predictor in ECorL. During model training, we define a new loss function, which is called multi-label focal loss. With this loss function, the model can focus more on misclassified positive-negative emotion pairs and improve the overall performance by balancing the prediction of positive and negative emotions. The evaluation of proposed MEDA architecture is carried out on emotional corpus: RenCECps and NLPCC2018 datasets. The experimental results indicate that the proposed method can achieve better performance than state-of-the-art methods in this task.","subitem_description_language":"en","subitem_description_type":"Abstract"}]},"item_10001_publisher_8":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"IEEE","subitem_publisher_language":"en"}]},"item_10001_rights_15":{"attribute_name":"権利情報","attribute_value_mlt":[{"subitem_rights":"© 2020 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.","subitem_rights_language":"en"}]},"item_10001_source_id_9":{"attribute_name":"収録物ID","attribute_value_mlt":[{"subitem_source_identifier":"19493045","subitem_source_identifier_type":"ISSN"}]},"item_10001_version_type_20":{"attribute_name":"出版タイプ","attribute_value_mlt":[{"subitem_version_resource":"http://purl.org/coar/version/c_ab4af688f83e57aa","subitem_version_type":"AM"}]},"item_1715043197608":{"attribute_name":"アクセス権","attribute_value_mlt":[{"subitem_access_right":"open access"}]},"item_1722929371688":{"attribute_name":"出版社版DOI","attribute_value_mlt":[{"subitem_relation_name":[{"subitem_relation_name_language":"ja","subitem_relation_name_text":"10.1109/TAFFC.2020.3034215"}],"subitem_relation_type_id":{"subitem_relation_type_id_text":"https://doi.org/10.1109/TAFFC.2020.3034215","subitem_relation_type_select":"DOI"}}]},"item_1723180141928":{"attribute_name":"EID","attribute_value_mlt":[{"subitem_identifier_type":"URI","subitem_identifier_uri":"371978"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Deng, Jiawen","creatorNameLang":"en"}]},{"creatorAffiliations":[{"affiliationNameIdentifiers":[{"affiliationNameIdentifier":"","affiliationNameIdentifierScheme":"ISNI","affiliationNameIdentifierURI":"http://www.isni.org/isni/"}],"affiliationNames":[{"affiliationName":"","affiliationNameLang":"ja"}]}],"creatorNames":[{"creatorName":"任, 福継","creatorNameLang":"ja"},{"creatorName":"ニン, フジ","creatorNameLang":"ja-Kana"},{"creatorName":"Ren, Fuji","creatorNameLang":"en"}],"familyNames":[{"familyName":"任","familyNameLang":"ja"},{"familyName":"ニン","familyNameLang":"ja-Kana"},{"familyName":"Ren","familyNameLang":"en"}],"givenNames":[{"givenName":"福継","givenNameLang":"ja"},{"givenName":"フジ","givenNameLang":"ja-Kana"},{"givenName":"Fuji","givenNameLang":"en"}],"nameIdentifiers":[{"nameIdentifier":"401","nameIdentifierScheme":"WEKO"},{"nameIdentifier":"19966/profile-ja.html","nameIdentifierScheme":"徳島大学 教育研究者総覧","nameIdentifierURI":"http://pub2.db.tokushima-u.ac.jp/ERD/person/19966/profile-ja.html"},{"nameIdentifier":"20264947","nameIdentifierScheme":"e-Rad","nameIdentifierURI":"https://nrid.nii.ac.jp/ja/search/?qm=20264947"}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_access","date":[{"dateType":"Available","dateValue":"2022-10-27"}],"displaytype":"detail","filename":"taffc_14_1_475.pdf","filesize":[{"value":"1.38 MB"}],"format":"application/pdf","mimetype":"application/pdf","url":{"objectType":"fulltext","url":"https://tokushima-u.repo.nii.ac.jp/record/2008322/files/taffc_14_1_475.pdf"},"version_id":"8d3b24b7-e6d2-43ae-a075-7c90def248fc"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"Multi-label","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Emotion Detection","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Emotion Correlation","subitem_subject_language":"en","subitem_subject_scheme":"Other"},{"subitem_subject":"Multi-label Focal Loss","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":"journal article","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"Multi-label Emotion Detection via Emotion-Specified Feature Extraction and Emotion Correlation Learning","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Multi-label Emotion Detection via Emotion-Specified Feature Extraction and Emotion Correlation Learning","subitem_title_language":"en"}]},"item_type_id":"40001","owner":"7","path":["1713853295607"],"pubdate":{"attribute_name":"PubDate","attribute_value":"2020-11-09"},"publish_date":"2020-11-09","publish_status":"0","recid":"2008322","relation_version_is_last":true,"title":["Multi-label Emotion Detection via Emotion-Specified Feature Extraction and Emotion Correlation Learning"],"weko_creator_id":"7","weko_shared_id":-1},"updated":"2025-02-13T05:58:29.356722+00:00"}