WEKO3
アイテム
{"_buckets": {"deposit": "24e0433a-df2e-4474-93ef-3237a01b42e8"}, "_deposit": {"created_by": 2, "id": "15650", "owners": [2], "pid": {"revision_id": 0, "type": "depid", "value": "15650"}, "status": "published"}, "_oai": {"id": "oai:nagasaki-u.repo.nii.ac.jp:00015650", "sets": ["65"]}, "author_link": ["58187", "58188", "58189", "58190", "58191"], "control_number": "15650", "item_9_biblio_info_6": {"attribute_name": "書誌情報", "attribute_value_mlt": [{"bibliographicIssueDates": {"bibliographicIssueDate": "2010", "bibliographicIssueDateType": "Issued"}, "bibliographicIssueNumber": "2", "bibliographicPageEnd": "311", "bibliographicPageStart": "302", "bibliographicVolumeNumber": "6064", "bibliographic_titles": [{"bibliographic_title": "Lecture Notes in Computer Science"}]}]}, "item_9_description_4": {"attribute_name": "抄録", "attribute_value_mlt": [{"subitem_description": "In this paper, we propose a new method for topical trend analysis. We model topical trends by per-topic Beta distributions as in Topics over Time (TOT), proposed as an extension of latent Dirichlet allocation (LDA). However, TOT is likely to overfit to timestamp data in extracting latent topics. Therefore, we apply prior distributions to Beta distributions in TOT. Since Beta distribution has no conjugate prior, we devise a trick, where we set one among the two parameters of each per-topic Beta distribution to one based on a Bernoulli trial and apply Gamma distribution as a conjugate prior. Consequently, we can marginalize out the parameters of Beta distributions and thus treat timestamp data in a Bayesian fashion. In the evaluation experiment, we compare our method with LDA and TOT in link detection task on TDT4 dataset. We use word predictive probabilities as term weights and estimate document similarities by using those weights in a TFIDF-like scheme. The results show that our method achieves a moderate fitting to timestamp data.", "subitem_description_type": "Abstract"}]}, "item_9_description_5": {"attribute_name": "内容記述", "attribute_value_mlt": [{"subitem_description": "Advances in Neural Networks - ISNN 2010 : 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part II", "subitem_description_type": "Other"}, {"subitem_description": "The original publication is available at www.springerlink.com", "subitem_description_type": "Other"}]}, "item_9_description_63": {"attribute_name": "引用", "attribute_value_mlt": [{"subitem_description": "Lecture Notes in Computer Science, 6064(2), pp.302-311; 2010", "subitem_description_type": "Other"}]}, "item_9_publisher_33": {"attribute_name": "出版者", "attribute_value_mlt": [{"subitem_publisher": "Springer"}]}, "item_9_relation_12": {"attribute_name": "DOI", "attribute_value_mlt": [{"subitem_relation_type": "isVersionOf", "subitem_relation_type_id": {"subitem_relation_type_id_text": "10.1007/978-3-642-13318-3_38", "subitem_relation_type_select": "DOI"}}]}, "item_9_relation_9": {"attribute_name": "ISBN", "attribute_value_mlt": [{"subitem_relation_type_id": {"subitem_relation_type_id_text": "3642133177", "subitem_relation_type_select": "ISBN"}}, {"subitem_relation_type_id": {"subitem_relation_type_id_text": "978-364213317-6", "subitem_relation_type_select": "ISBN"}}]}, "item_9_rights_13": {"attribute_name": "権利", "attribute_value_mlt": [{"subitem_rights": "© 2010 Springer-Verlag."}]}, "item_9_source_id_10": {"attribute_name": "書誌レコードID", "attribute_value_mlt": [{"subitem_source_identifier": "AA0071599X", "subitem_source_identifier_type": "NCID"}]}, "item_9_source_id_7": {"attribute_name": "ISSN", "attribute_value_mlt": [{"subitem_source_identifier": "03029743", "subitem_source_identifier_type": "ISSN"}]}, "item_9_source_id_8": {"attribute_name": "EISSN", "attribute_value_mlt": [{"subitem_source_identifier": "16113349", "subitem_source_identifier_type": "ISSN"}]}, "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_ab4af688f83e57aa", "subitem_version_type": "AM"}]}, "item_creator": {"attribute_name": "著者", "attribute_type": "creator", "attribute_value_mlt": [{"creatorNames": [{"creatorName": "Masada, Tomonari"}], "nameIdentifiers": [{"nameIdentifier": "58187", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Fukagawa, Daiji"}], "nameIdentifiers": [{"nameIdentifier": "58188", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Takasu, Atsuhiro"}], "nameIdentifiers": [{"nameIdentifier": "58189", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Shibata, Yuichiro"}], "nameIdentifiers": [{"nameIdentifier": "58190", "nameIdentifierScheme": "WEKO"}]}, {"creatorNames": [{"creatorName": "Oguri, Kiyoshi"}], "nameIdentifiers": [{"nameIdentifier": "58191", "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": "2020-12-23"}], "displaytype": "detail", "download_preview_message": "", "file_order": 0, "filename": "LNCS6064_302.pdf", "filesize": [{"value": "322.1 kB"}], "format": "application/pdf", "future_date_message": "", "is_thumbnail": false, "licensetype": "license_free", "mimetype": "application/pdf", "size": 322100.0, "url": {"label": "LNCS6064_302.pdf", "url": "https://nagasaki-u.repo.nii.ac.jp/record/15650/files/LNCS6064_302.pdf"}, "version_id": "eddf7858-4cea-4fa1-9a85-a8af5b4c3697"}]}, "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": "Modeling topical trends over continuous time with priors", "item_titles": {"attribute_name": "タイトル", "attribute_value_mlt": [{"subitem_title": "Modeling topical trends over continuous time with priors", "subitem_title_language": "en"}]}, "item_type_id": "9", "owner": "2", "path": ["65"], "permalink_uri": "http://hdl.handle.net/10069/23580", "pubdate": {"attribute_name": "PubDate", "attribute_value": "2010-08-20"}, "publish_date": "2010-08-20", "publish_status": "0", "recid": "15650", "relation": {}, "relation_version_is_last": true, "title": ["Modeling topical trends over continuous time with priors"], "weko_shared_id": -1}
Modeling topical trends over continuous time with priors
http://hdl.handle.net/10069/23580
http://hdl.handle.net/10069/23580b0a4f2b9-843a-4f0d-81f6-aab7f9c9298b
名前 / ファイル | ライセンス | アクション |
---|---|---|
LNCS6064_302.pdf (322.1 kB)
|
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2010-08-20 | |||||
タイトル | ||||||
言語 | en | |||||
タイトル | Modeling topical trends over continuous time with priors | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
資源タイプ | conference paper | |||||
著者 |
Masada, Tomonari
× Masada, Tomonari× Fukagawa, Daiji× Takasu, Atsuhiro× Shibata, Yuichiro× Oguri, Kiyoshi |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | In this paper, we propose a new method for topical trend analysis. We model topical trends by per-topic Beta distributions as in Topics over Time (TOT), proposed as an extension of latent Dirichlet allocation (LDA). However, TOT is likely to overfit to timestamp data in extracting latent topics. Therefore, we apply prior distributions to Beta distributions in TOT. Since Beta distribution has no conjugate prior, we devise a trick, where we set one among the two parameters of each per-topic Beta distribution to one based on a Bernoulli trial and apply Gamma distribution as a conjugate prior. Consequently, we can marginalize out the parameters of Beta distributions and thus treat timestamp data in a Bayesian fashion. In the evaluation experiment, we compare our method with LDA and TOT in link detection task on TDT4 dataset. We use word predictive probabilities as term weights and estimate document similarities by using those weights in a TFIDF-like scheme. The results show that our method achieves a moderate fitting to timestamp data. | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | Advances in Neural Networks - ISNN 2010 : 7th International Symposium on Neural Networks, ISNN 2010, Shanghai, China, June 6-9, 2010, Proceedings, Part II | |||||
内容記述 | ||||||
内容記述タイプ | Other | |||||
内容記述 | The original publication is available at www.springerlink.com | |||||
書誌情報 |
Lecture Notes in Computer Science 巻 6064, 号 2, p. 302-311, 発行日 2010 |
|||||
ISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 03029743 | |||||
EISSN | ||||||
収録物識別子タイプ | ISSN | |||||
収録物識別子 | 16113349 | |||||
ISBN | ||||||
識別子タイプ | ISBN | |||||
関連識別子 | 3642133177 | |||||
ISBN | ||||||
識別子タイプ | ISBN | |||||
関連識別子 | 978-364213317-6 | |||||
書誌レコードID | ||||||
収録物識別子タイプ | NCID | |||||
収録物識別子 | AA0071599X | |||||
DOI | ||||||
関連タイプ | isVersionOf | |||||
識別子タイプ | DOI | |||||
関連識別子 | 10.1007/978-3-642-13318-3_38 | |||||
権利 | ||||||
権利情報 | © 2010 Springer-Verlag. | |||||
著者版フラグ | ||||||
出版タイプ | AM | |||||
出版タイプResource | http://purl.org/coar/version/c_ab4af688f83e57aa | |||||
出版者 | ||||||
出版者 | Springer | |||||
引用 | ||||||
内容記述タイプ | Other | |||||
内容記述 | Lecture Notes in Computer Science, 6064(2), pp.302-311; 2010 |